Zhou Yu

Jianguo Zhang, Kun Qian, Zhiwei Liu et al. · salesforce

Despite advancements in conversational AI, language models encounter challenges to handle diverse conversational tasks, and existing dialogue dataset collections often lack diversity and comprehensiveness. To tackle these issues, we introduce DialogStudio: the largest and most diverse collection of dialogue datasets, unified under a consistent format while preserving their original information. Our collection encompasses data from open-domain dialogues, task-oriented dialogues, natural language understanding, conversational recommendation, dialogue summarization, and knowledge-grounded dialogues, making it an incredibly rich and diverse resource for dialogue research and model training. To further enhance the utility of DialogStudio, we identify the licenses for each dataset, design external knowledge and domain-aware prompts for selected dialogues to facilitate instruction-aware fine-tuning. Furthermore, we develop conversational AI models using the dataset collection, and our experiments in both zero-shot and few-shot learning scenarios demonstrate the superiority of DialogStudio. To improve transparency and support dataset and task-based research, as well as language model pre-training, all datasets, licenses, codes, and models associated with DialogStudio are made publicly accessible\footnote{\url{https://github.com/salesforce/DialogStudio}}.

Maximillian Chen, Zhou Yu

Speech models have long been known to overfit individual speakers for many classification tasks. This leads to poor generalization in settings where the speakers are out-of-domain or out-of-distribution, as is common in production environments. We view speaker adaptation as a few-shot learning problem and propose investigating transfer learning approaches inspired by recent success with pre-trained models in natural language tasks. We propose pre-finetuning speech models on difficult tasks to distill knowledge into few-shot downstream classification objectives. We pre-finetune Wav2Vec2.0 on every permutation of four multiclass emotional speech recognition corpora and evaluate our pre-finetuned models through 33,600 few-shot fine-tuning trials on the Emotional Speech Dataset.

Yingjie Zhou, Xilei Zhu, Siyu Ren et al.

Speech-driven Talking Human (TH) generation, commonly known as "Talker," currently faces limitations in multi-subject driving capabilities. Extending this paradigm to "Multi-Talker," capable of animating multiple subjects simultaneously, introduces richer interactivity and stronger immersion in audiovisual communication. However, current Multi-Talkers still exhibit noticeable quality degradation caused by technical limitations, resulting in suboptimal user experiences. To address this challenge, we construct THQA-MT, the first large-scale Multi-Talker-generated Talking Human Quality Assessment dataset, consisting of 5,492 Multi-Talker-generated THs (MTHs) from 15 representative Multi-Talkers using 400 real portraits collected online. Through subjective experiments, we analyze perceptual discrepancies among different Multi-Talkers and identify 12 common types of distortion. Furthermore, we introduce EvalTalker, a novel TH quality assessment framework. This framework possesses the ability to perceive global quality, human characteristics, and identity consistency, while integrating Qwen-Sync to perceive multimodal synchrony. Experimental results demonstrate that EvalTalker achieves superior correlation with subjective scores, providing a robust foundation for future research on high-quality Multi-Talker generation and evaluation.

Donglei Yu, Yang Zhao, Jie Zhu et al.

Simultaneous Machine Translation (SiMT) generates translations while receiving streaming source inputs. This requires the SiMT model to learn a read/write policy, deciding when to translate and when to wait for more source input. Numerous linguistic studies indicate that audiences in SiMT scenarios have distinct preferences, such as accurate translations, simpler syntax, and no unnecessary latency. Aligning SiMT models with these human preferences is crucial to improve their performances. However, this issue still remains unexplored. Additionally, preference optimization for SiMT task is also challenging. Existing methods focus solely on optimizing the generated responses, ignoring human preferences related to latency and the optimization of read/write policy during the preference optimization phase. To address these challenges, we propose Simultaneous Preference Learning (SimulPL), a preference learning framework tailored for the SiMT task. In the SimulPL framework, we categorize SiMT human preferences into five aspects: \textbf{translation quality preference}, \textbf{monotonicity preference}, \textbf{key point preference}, \textbf{simplicity preference}, and \textbf{latency preference}. By leveraging the first four preferences, we construct human preference prompts to efficiently guide GPT-4/4o in generating preference data for the SiMT task. In the preference optimization phase, SimulPL integrates \textbf{latency preference} into the optimization objective and enables SiMT models to improve the read/write policy, thereby aligning with human preferences more effectively. Experimental results indicate that SimulPL exhibits better alignment with human preferences across all latency levels in Zh$\rightarrow$En, De$\rightarrow$En and En$\rightarrow$Zh SiMT tasks. Our data and code will be available at https://github.com/EurekaForNLP/SimulPL.

Dayou Huang, Feng Xue, Xurui Li et al.

Zero-shot industrial anomaly detection (ZSAD) methods typically yield coarse anomaly maps as vision transformers (ViTs) extract patch-level features only. To solve this, recent solutions attempt to predict finer anomalies using features from ZSAD, but they still struggle to recover fine-grained anomalies without missed detections, mainly due to the gap between randomly synthesized training anomalies and real ones. We observe that anomaly score maps exactly provide complementary spatial cues that are largely absent from ZSAD's image features, a fact overlooked before. Inspired by this, we propose an anomaly-aware refiner (AnoRefiner) that can be plugged into most ZSAD models and improve patch-level anomaly maps to the pixel level. First, we design an anomaly refinement decoder (ARD) that progressively enhances image features using anomaly score maps, reducing the reliance on synthetic anomaly data. Second, motivated by the mass production paradigm, we propose a progressive group-wise test-time training (PGT) strategy that trains ARD in each product group for the refinement process in the next group, while staying compatible with any ZSAD method. Experiments on the MVTec AD and VisA datasets show that AnoRefiner boosts various ZSAD models by up to a 5.2\% gain in pixel-AP metrics, which can also be directly observed in many visualizations. The code will be available at https://github.com/HUST-SLOW/AnoRefiner.

Junnan Zhu, Min Xiao, Yining Wang et al.

LLMs have achieved remarkable fluency and coherence in text generation, yet their widespread adoption has raised concerns about content reliability and accountability. In high-stakes domains, it is crucial to understand where and how the content is created. To address this, we introduce the Text pROVEnance (TROVE) challenge, designed to trace each sentence of a target text back to specific source sentences within potentially lengthy or multi-document inputs. Beyond identifying sources, TROVE annotates the fine-grained relationships (quotation, compression, inference, and others), providing a deep understanding of how each target sentence is formed. To benchmark TROVE, we construct our dataset by leveraging three public datasets covering 11 diverse scenarios (e.g., QA and summarization) in English and Chinese, spanning source texts of varying lengths (0-5k, 5-10k, 10k+), emphasizing the multi-document and long-document settings essential for provenance. To ensure high-quality data, we employ a three-stage annotation process: sentence retrieval, GPT-4o provenance, and human provenance. We evaluate 11 LLMs under direct prompting and retrieval-augmented paradigms, revealing that retrieval is essential for robust performance, larger models perform better in complex relationship classification, and closed-source models often lead, yet open-source models show significant promise, particularly with retrieval augmentation. We make our dataset available here: https://github.com/ZNLP/ZNLP-Dataset.

Weiyan Shi, Aiqi Cui, Evan Li et al.

With the increasing applications of language models, it has become crucial to protect these models from leaking private information. Previous work has attempted to tackle this challenge by training RNN-based language models with differential privacy guarantees. However, applying classical differential privacy to language models leads to poor model performance as the underlying privacy notion is over-pessimistic and provides undifferentiated protection for all tokens in the data. Given that the private information in natural language is sparse (for example, the bulk of an email might not carry personally identifiable information), we propose a new privacy notion, selective differential privacy, to provide rigorous privacy guarantees on the sensitive portion of the data to improve model utility. To realize such a new notion, we develop a corresponding privacy mechanism, Selective-DPSGD, for RNN-based language models. Besides language modeling, we also apply the method to a more concrete application--dialog systems. Experiments on both language modeling and dialog system building show that the proposed privacy-preserving mechanism achieves better utilities while remaining safe under various privacy attacks compared to the baselines. The data and code are released at https://github.com/wyshi/lm_privacy to facilitate future research .

Kai-Hui Liang, Patrick Lange, Yoo Jung Oh et al.

Artificial intelligence chatbots are the vanguard in technology-based intervention to change people's behavior. To develop intervention chatbots, the first step is to understand natural language conversation strategies in human conversation. This work introduces an intervention conversation dataset collected from a real-world physical activity intervention program for women. We designed comprehensive annotation schemes in four dimensions (domain, strategy, social exchange, and task-focused exchange) and annotated a subset of dialogs. We built a strategy classifier with context information to detect strategies from both trainers and participants based on the annotation. To understand how human intervention induces effective behavior changes, we analyzed the relationships between the intervention strategies and the participants' changes in the barrier and social support for physical activity. We also analyzed how participant's baseline weight correlates to the amount of occurrence of the corresponding strategy. This work lays the foundation for developing a personalized physical activity intervention bot. The dataset and code are available at https://github.com/KaihuiLiang/physical-activity-counseling

Yu Li, Josh Arnold, Feifan Yan et al.

We present LEGOEval, an open-source toolkit that enables researchers to easily evaluate dialogue systems in a few lines of code using the online crowdsource platform, Amazon Mechanical Turk. Compared to existing toolkits, LEGOEval features a flexible task design by providing a Python API that maps to commonly used React.js interface components. Researchers can personalize their evaluation procedures easily with our built-in pages as if playing with LEGO blocks. Thus, LEGOEval provides a fast, consistent method for reproducing human evaluation results. Besides the flexible task design, LEGOEval also offers an easy API to review collected data.

Emily Sheng, Josh Arnold, Zhou Yu et al.

Dialogue systems in the form of chatbots and personal assistants are being increasingly integrated into people's lives. Modern dialogue systems may consider adopting anthropomorphic personas, mimicking societal demographic groups to appear more approachable and trustworthy to users. However, the adoption of a persona can result in the adoption of biases. In this paper, we present the first large-scale study on persona biases in dialogue systems and conduct analyses on personas of different social classes, sexual orientations, races, and genders. We define persona biases as harmful differences in responses (e.g., varying levels of offensiveness, agreement with harmful statements) generated from adopting different demographic personas. Furthermore, we introduce an open-source framework, UnitPersonaBias, to explore and aggregate persona biases in dialogue systems. By analyzing the Blender and DialoGPT dialogue systems, we observe that adopting personas can actually decrease harmful responses, compared to not using any personas. Additionally, we find that persona choices can affect the degree of harms in generated responses and thus should be systematically evaluated before deployment. We also analyze how personas can result in different amounts of harm towards specific demographics.

Wenmian Yang, Guangtao Zeng, Bowen Tan et al.

Under the pandemic of COVID-19, people experiencing COVID19-related symptoms or exposed to risk factors have a pressing need to consult doctors. Due to hospital closure, a lot of consulting services have been moved online. Because of the shortage of medical professionals, many people cannot receive online consultations timely. To address this problem, we aim to develop a medical dialogue system that can provide COVID19-related consultations. We collected two dialogue datasets -- CovidDialog -- (in English and Chinese respectively) containing conversations between doctors and patients about COVID-19. On these two datasets, we train several dialogue generation models based on Transformer, GPT, and BERT-GPT. Since the two COVID-19 dialogue datasets are small in size, which bear high risk of overfitting, we leverage transfer learning to mitigate data deficiency. Specifically, we take the pretrained models of Transformer, GPT, and BERT-GPT on dialog datasets and other large-scale texts, then finetune them on our CovidDialog tasks. We perform both automatic and human evaluation of responses generated by these models. The results show that the generated responses are promising in being doctor-like, relevant to the conversation history, and clinically informative. The data and code are available at https://github.com/UCSD-AI4H/COVID-Dialogue.

Yu Zhou, Yunqiu Han, Hanyu Zhou et al.

Recent advances in general purpose pre-trained language models have shown great potential in commonsense reasoning. However, current works still perform poorly on standard commonsense reasoning benchmarks including the Com2Sense Dataset. We argue that this is due to a disconnect with current cutting-edge machine learning methods. In this work, we aim to bridge the gap by introducing current ML-based methods to improve general purpose pre-trained language models in the task of commonsense reasoning. Specifically, we experiment with and systematically evaluate methods including knowledge transfer, model ensemble, and introducing an additional pairwise contrastive objective. Our best model outperforms the strongest previous works by ~15\% absolute gains in Pairwise Accuracy and ~8.7\% absolute gains in Standard Accuracy.

Jiahao Lyu, Wei Wang, Dongbao Yang et al.

Scene text spotting has attracted the enthusiasm of relative researchers in recent years. Most existing scene text spotters follow the detection-then-recognition paradigm, where the vanilla detection module hardly determines the reading order and leads to failure recognition. After rethinking the auto-regressive scene text recognition method, we find that a well-trained recognizer can implicitly perceive the local semantics of all characters in a complete word or a sentence without a character-level detection module. Local semantic knowledge not only includes text content but also spatial information in the right reading order. Motivated by the above analysis, we propose the Local Semantics Guided scene text Spotter (LSGSpotter), which auto-regressively decodes the position and content of characters guided by the local semantics. Specifically, two effective modules are proposed in LSGSpotter. On the one hand, we design a Start Point Localization Module (SPLM) for locating text start points to determine the right reading order. On the other hand, a Multi-scale Adaptive Attention Module (MAAM) is proposed to adaptively aggregate text features in a local area. In conclusion, LSGSpotter achieves the arbitrary reading order spotting task without the limitation of sophisticated detection, while alleviating the cost of computational resources with the grid sampling strategy. Extensive experiment results show LSGSpotter achieves state-of-the-art performance on the InverseText benchmark. Moreover, our spotter demonstrates superior performance on English benchmarks for arbitrary-shaped text, achieving improvements of 0.7\% and 2.5\% on Total-Text and SCUT-CTW1500, respectively. These results validate our text spotter is effective for scene texts in arbitrary reading order and shape.

Huawen Shen, Gengluo Li, Jinwen Zhong et al.

Visual Information Extraction (VIE) plays a crucial role in the comprehension of semi-structured documents, and several pre-trained models have been developed to enhance performance. However, most of these works are monolingual (usually English). Due to the extremely unbalanced quantity and quality of pre-training corpora between English and other languages, few works can extend to non-English scenarios. In this paper, we conduct systematic experiments to show that vision and layout modality hold invariance among images with different languages. If decoupling language bias from document images, a vision-layout-based model can achieve impressive cross-lingual generalization. Accordingly, we present a simple but effective multilingual training paradigm LDP (Language Decoupled Pre-training) for better utilization of monolingual pre-training data. Our proposed model LDM (Language Decoupled Model) is first pre-trained on the language-independent data, where the language knowledge is decoupled by a diffusion model, and then the LDM is fine-tuned on the downstream languages. Extensive experiments show that the LDM outperformed all SOTA multilingual pre-trained models, and also maintains competitiveness on downstream monolingual/English benchmarks.

Daiqing Wu, Dongbao Yang, Sicheng Zhao et al.

The advancements in Multimodal Large Language Models (MLLMs) have enabled various multimodal tasks to be addressed under a zero-shot paradigm. This paradigm sidesteps the cost of model fine-tuning, emerging as a dominant trend in practical application. Nevertheless, Multimodal Sentiment Analysis (MSA), a pivotal challenge in the quest for general artificial intelligence, fails to accommodate this convenience. The zero-shot paradigm exhibits undesirable performance on MSA, casting doubt on whether MLLMs can perceive sentiments as competent as supervised models. By extending the zero-shot paradigm to In-Context Learning (ICL) and conducting an in-depth study on configuring demonstrations, we validate that MLLMs indeed possess such capability. Specifically, three key factors that cover demonstrations' retrieval, presentation, and distribution are comprehensively investigated and optimized. A sentimental predictive bias inherent in MLLMs is also discovered and later effectively counteracted. By complementing each other, the devised strategies for three factors result in average accuracy improvements of 15.9% on six MSA datasets against the zero-shot paradigm and 11.2% against the random ICL baseline.

Naimeng Ye, Xiao Yu, Ruize Xu et al.

Automated web testing plays a critical role in ensuring high-quality user experiences and delivering business value. Traditional approaches primarily focus on code coverage and load testing, but often fall short of capturing complex user behaviors, leaving many usability issues undetected. The emergence of large language models (LLM) and AI agents opens new possibilities for web testing by enabling human-like interaction with websites and a general awareness of common usability problems. In this work, we present WebProber, a prototype AI agent-based web testing framework. Given a URL, WebProber autonomously explores the website, simulating real user interactions, identifying bugs and usability issues, and producing a human-readable report. We evaluate WebProber through a case study of 120 academic personal websites, where it uncovered 29 usability issues--many of which were missed by traditional tools. Our findings highlight agent-based testing as a promising direction while outlining directions for developing next-generation, user-centered testing frameworks.

Aman Gupta, Yingying Zhuang, Zhou Yu et al.

Despite advances in the multilingual capabilities of Large Language Models (LLMs), their performance varies substantially across different languages and tasks. In multilingual retrieval-augmented generation (RAG)-based systems, knowledge bases (KB) are often shared from high-resource languages (such as English) to low-resource ones, resulting in retrieved information from the KB being in a different language than the rest of the context. In such scenarios, two common practices are pre-translation to create a mono-lingual prompt and cross-lingual prompting for direct inference. However, the impact of these choices remains unclear. In this paper, we systematically evaluate the impact of different prompt translation strategies for classification tasks with RAG-enhanced LLMs in multilingual systems. Experimental results show that an optimized prompting strategy can significantly improve knowledge sharing across languages, therefore improve the performance on the downstream classification task. The findings advocate for a broader utilization of multilingual resource sharing and cross-lingual prompt optimization for non-English languages, especially the low-resource ones.

Donglei Yu, Xiaomian Kang, Yuchen Liu et al.

Simultaneous Machine Translation (SiMT) generates target outputs while receiving stream source inputs and requires a read/write policy to decide whether to wait for the next source token or generate a new target token, whose decisions form a \textit{decision path}. Existing SiMT methods, which learn the policy by exploring various decision paths in training, face inherent limitations. These methods not only fail to precisely optimize the policy due to the inability to accurately assess the individual impact of each decision on SiMT performance, but also cannot sufficiently explore all potential paths because of their vast number. Besides, building decision paths requires unidirectional encoders to simulate streaming source inputs, which impairs the translation quality of SiMT models. To solve these issues, we propose \textbf{S}elf-\textbf{M}odifying \textbf{S}tate \textbf{M}odeling (SM$^2$), a novel training paradigm for SiMT task. Without building decision paths, SM$^2$ individually optimizes decisions at each state during training. To precisely optimize the policy, SM$^2$ introduces Self-Modifying process to independently assess and adjust decisions at each state. For sufficient exploration, SM$^2$ proposes Prefix Sampling to efficiently traverse all potential states. Moreover, SM$^2$ ensures compatibility with bidirectional encoders, thus achieving higher translation quality. Experiments show that SM$^2$ outperforms strong baselines. Furthermore, SM$^2$ allows offline machine translation models to acquire SiMT ability with fine-tuning.

Ming Gu, Yan Yang, Chengcai Chen et al.

Recently, low-resource dialogue state tracking (DST) has received increasing attention. First obtaining state values then based on values to generate slot types has made great progress in this task. However, obtaining state values is still an under-studied problem. Existing extraction-based approaches cannot capture values that require the understanding of context and are not generalizable either. To address these issues, we propose a novel State VAlue Generation based framework (SVAG), decomposing DST into state value generation and domain slot generation. Specifically, we propose to generate state values and use self-training to further improve state value generation. Moreover, we design an estimator aiming at detecting incomplete generation and incorrect generation for pseudo-labeled data selection during self-training. Experimental results on the MultiWOZ 2.1 dataset show that our method which has only less than 1 billion parameters achieves state-of-the-art performance under the data ratio settings of 5%, 10%, and 25% when limited to models under 100 billion parameters. Compared to models with more than 100 billion parameters, SVAG still reaches competitive results.

Xiao Yu, Maximillian Chen, Zhou Yu

Planning for goal-oriented dialogue often requires simulating future dialogue interactions and estimating task progress. Many approaches thus consider training neural networks to perform look-ahead search algorithms such as A* search and Monte Carlo Tree Search (MCTS). However, this training often requires abundant annotated data, which creates challenges when faced with noisy annotations or low-resource settings. We introduce GDP-Zero, an approach using Open-Loop MCTS to perform goal-oriented dialogue policy planning without any model training. GDP-Zero prompts a large language model to act as a policy prior, value function, user simulator, and system model during the tree search. We evaluate GDP-Zero on the goal-oriented task PersuasionForGood, and find that its responses are preferred over ChatGPT up to 59.32% of the time, and are rated more persuasive than ChatGPT during interactive evaluations.

Narutatsu Ri, Bill Sun, Sam Davidson et al.

Although significant progress has been made in developing methods for Grammatical Error Correction (GEC), addressing word choice improvements has been notably lacking and enhancing sentence expressivity by replacing phrases with advanced expressions is an understudied aspect. In this paper, we focus on this area and present our investigation into the task of incorporating the usage of idiomatic expressions in student writing. To facilitate our study, we curate extensive training sets and expert-annotated testing sets using real-world data and evaluate various approaches and compare their performance against human experts.

Zhaojiang Lin, Bing Liu, Andrea Madotto et al.

Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the \textit{cross-task} knowledge from general question answering (QA) corpora for the zero-shot DST task. Specifically, we propose TransferQA, a transferable generative QA model that seamlessly combines extractive QA and multi-choice QA via a text-to-text transformer framework, and tracks both categorical slots and non-categorical slots in DST. In addition, we introduce two effective ways to construct unanswerable questions, namely, negative question sampling and context truncation, which enable our model to handle "none" value slots in the zero-shot DST setting. The extensive experiments show that our approaches substantially improve the existing zero-shot and few-shot results on MultiWoz. Moreover, compared to the fully trained baseline on the Schema-Guided Dialogue dataset, our approach shows better generalization ability in unseen domains.

Haitao Lin, Lu Xiang, Yu Zhou et al.

Spoken Language Understanding (SLU) is one essential step in building a dialogue system. Due to the expensive cost of obtaining the labeled data, SLU suffers from the data scarcity problem. Therefore, in this paper, we focus on data augmentation for slot filling task in SLU. To achieve that, we aim at generating more diverse data based on existing data. Specifically, we try to exploit the latent language knowledge from pretrained language models by finetuning them. We propose two strategies for finetuning process: value-based and context-based augmentation. Experimental results on two public SLU datasets have shown that compared with existing data augmentation methods, our proposed method can generate more diverse sentences and significantly improve the performance on SLU.

David Gros, Yu Li, Zhou Yu

Humans are increasingly interacting with machines through language, sometimes in contexts where the user may not know they are talking to a machine (like over the phone or a text chatbot). We aim to understand how system designers and researchers might allow their systems to confirm its non-human identity. We collect over 2,500 phrasings related to the intent of ``Are you a robot?". This is paired with over 2,500 adversarially selected utterances where only confirming the system is non-human would be insufficient or disfluent. We compare classifiers to recognize the intent and discuss the precision/recall and model complexity tradeoffs. Such classifiers could be integrated into dialog systems to avoid undesired deception. We then explore how both a generative research model (Blender) as well as two deployed systems (Amazon Alexa, Google Assistant) handle this intent, finding that systems often fail to confirm their non-human identity. Finally, we try to understand what a good response to the intent would be, and conduct a user study to compare the important aspects when responding to this intent.

Siyang Liu, Chujie Zheng, Orianna Demasi et al.

Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats. Following reasonable procedures and using various support skills can help to effectively provide support. However, due to the lack of a well-designed task and corpora of effective emotional support conversations, research on building emotional support into dialog systems remains untouched. In this paper, we define the Emotional Support Conversation (ESC) task and propose an ESC Framework, which is grounded on the Helping Skills Theory. We construct an Emotion Support Conversation dataset (ESConv) with rich annotation (especially support strategy) in a help-seeker and supporter mode. To ensure a corpus of high-quality conversations that provide examples of effective emotional support, we take extensive effort to design training tutorials for supporters and several mechanisms for quality control during data collection. Finally, we evaluate state-of-the-art dialog models with respect to the ability to provide emotional support. Our results show the importance of support strategies in providing effective emotional support and the utility of ESConv in training more emotional support systems.

Liang Qiu, Yuan Liang, Yizhou Zhao et al.

Inferring social relations from dialogues is vital for building emotionally intelligent robots to interpret human language better and act accordingly. We model the social network as an And-or Graph, named SocAoG, for the consistency of relations among a group and leveraging attributes as inference cues. Moreover, we formulate a sequential structure prediction task, and propose an $α$-$β$-$γ$ strategy to incrementally parse SocAoG for the dynamic inference upon any incoming utterance: (i) an $α$ process predicting attributes and relations conditioned on the semantics of dialogues, (ii) a $β$ process updating the social relations based on related attributes, and (iii) a $γ$ process updating individual's attributes based on interpersonal social relations. Empirical results on DialogRE and MovieGraph show that our model infers social relations more accurately than the state-of-the-art methods. Moreover, the ablation study shows the three processes complement each other, and the case study demonstrates the dynamic relational inference.

Weixin Liang, Kai-Hui Liang, Zhou Yu

Open-domain dialog systems have a user-centric goal: to provide humans with an engaging conversation experience. User engagement is one of the most important metrics for evaluating open-domain dialog systems, and could also be used as real-time feedback to benefit dialog policy learning. Existing work on detecting user disengagement typically requires hand-labeling many dialog samples. We propose HERALD, an efficient annotation framework that reframes the training data annotation process as a denoising problem. Specifically, instead of manually labeling training samples, we first use a set of labeling heuristics to label training samples automatically. We then denoise the weakly labeled data using the Shapley algorithm. Finally, we use the denoised data to train a user engagement detector. Our experiments show that HERALD improves annotation efficiency significantly and achieves 86% user disengagement detection accuracy in two dialog corpora.

Zhaojiang Lin, Bing Liu, Seungwhan Moon et al.

Zero-shot cross-domain dialogue state tracking (DST) enables us to handle task-oriented dialogue in unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot description enhanced generative approach for zero-shot cross-domain DST. Specifically, our model first encodes dialogue context and slots with a pre-trained self-attentive encoder, and generates slot values in an auto-regressive manner. In addition, we incorporate Slot Type Informed Descriptions that capture the shared information across slots to facilitate cross-domain knowledge transfer. Experimental results on the MultiWOZ dataset show that our proposed method significantly improves existing state-of-the-art results in the zero-shot cross-domain setting.

Yu Li, Shirley Anugrah Hayati, Weiyan Shi et al.

It is important for sociable recommendation dialog systems to perform as both on-task content and social content to engage users and gain their favor. In addition to understand the user preferences and provide a satisfying recommendation, such systems must be able to generate coherent and natural social conversations to the user. Traditional dialog state tracking cannot be applied to such systems because it does not track the attributes in the social content. To address this challenge, we propose DEUX, a novel attribute-guided framework to create better user experiences while accomplishing a movie recommendation task. DEUX has a module that keeps track of the movie attributes (e.g., favorite genres, actors,etc.) in both user utterances and system responses. This allows the system to introduce new movie attributes in its social content. Then, DEUX has multiple values for the same attribute type which suits the recommendation task since a user may like multiple genres, for instance. Experiments suggest that DEUX outperforms all the baselines on being more consistent, fitting the user preferences better, and providing a more engaging chat experience. Our approach can be used for any similar problems of sociable task-oriented dialog system.

Derek Chen, Howard Chen, Yi Yang et al.

Existing goal-oriented dialogue datasets focus mainly on identifying slots and values. However, customer support interactions in reality often involve agents following multi-step procedures derived from explicitly-defined company policies as well. To study customer service dialogue systems in more realistic settings, we introduce the Action-Based Conversations Dataset (ABCD), a fully-labeled dataset with over 10K human-to-human dialogues containing 55 distinct user intents requiring unique sequences of actions constrained by policies to achieve task success. We propose two additional dialog tasks, Action State Tracking and Cascading Dialogue Success, and establish a series of baselines involving large-scale, pre-trained language models on this dataset. Empirical results demonstrate that while more sophisticated networks outperform simpler models, a considerable gap (50.8% absolute accuracy) still exists to reach human-level performance on ABCD.

Jing Gu, Mostafa Mirshekari, Zhou Yu et al.

Conversational systems enable numerous valuable applications, and question-answering is an important component underlying many of these. However, conversational question-answering remains challenging due to the lack of realistic, domain-specific training data. Inspired by this bottleneck, we focus on conversational question generation as a means to generate synthetic conversations for training and evaluation purposes. We present a number of novel strategies to improve conversational flow and accommodate varying question types and overall fluidity. Specifically, we design ChainCQG as a two-stage architecture that learns question-answer representations across multiple dialogue turns using a flow propagation training strategy.ChainCQG significantly outperforms both answer-aware and answer-unaware SOTA baselines (e.g., up to 48% BLEU-1 improvement). Additionally, our model is able to generate different types of questions, with improved fluidity and coreference alignment.

Andrea Madotto, Zhaojiang Lin, Zhenpeng Zhou et al.

Continual learning in task-oriented dialogue systems can allow us to add new domains and functionalities through time without incurring the high cost of a whole system retraining. In this paper, we propose a continual learning benchmark for task-oriented dialogue systems with 37 domains to be learned continuously in four settings, such as intent recognition, state tracking, natural language generation, and end-to-end. Moreover, we implement and compare multiple existing continual learning baselines, and we propose a simple yet effective architectural method based on residual adapters. Our experiments demonstrate that the proposed architectural method and a simple replay-based strategy perform comparably well but they both achieve inferior performance to the multi-task learning baseline, in where all the data are shown at once, showing that continual learning in task-oriented dialogue systems is a challenging task. Furthermore, we reveal several trade-offs between different continual learning methods in term of parameter usage and memory size, which are important in the design of a task-oriented dialogue system. The proposed benchmark is released together with several baselines to promote more research in this direction.

Kaihui Liang, Austin Chau, Yu Li et al.

Gunrock 2.0 is built on top of Gunrock with an emphasis on user adaptation. Gunrock 2.0 combines various neural natural language understanding modules, including named entity detection, linking, and dialog act prediction, to improve user understanding. Its dialog management is a hierarchical model that handles various topics, such as movies, music, and sports. The system-level dialog manager can handle question detection, acknowledgment, error handling, and additional functions, making downstream modules much easier to design and implement. The dialog manager also adapts its topic selection to accommodate different users' profile information, such as inferred gender and personality. The generation model is a mix of templates and neural generation models. Gunrock 2.0 is able to achieve an average rating of 3.73 at its latest build from May 29th to June 4th.

David Gros, Hariharan Sezhiyan, Prem Devanbu et al.

The relationship of comments to code, and in particular, the task of generating useful comments given the code, has long been of interest. The earliest approaches have been based on strong syntactic theories of comment-structures, and relied on textual templates. More recently, researchers have applied deep learning methods to this task, and specifically, trainable generative translation models which are known to work very well for Natural Language translation (e.g., from German to English). We carefully examine the underlying assumption here: that the task of generating comments sufficiently resembles the task of translating between natural languages, and so similar models and evaluation metrics could be used. We analyze several recent code-comment datasets for this task: CodeNN, DeepCom, FunCom, and DocString. We compare them with WMT19, a standard dataset frequently used to train state of the art natural language translators. We found some interesting differences between the code-comment data and the WMT19 natural language data. Next, we describe and conduct some studies to calibrate BLEU (which is commonly used as a measure of comment quality). using "affinity pairs" of methods, from different projects, in the same project, in the same class, etc; Our study suggests that the current performance on some datasets might need to be improved substantially. We also argue that fairly naive information retrieval (IR) methods do well enough at this task to be considered a reasonable baseline. Finally, we make some suggestions on how our findings might be used in future research in this area.

Shirley Anugrah Hayati, Dongyeop Kang, Qingxiaoyang Zhu et al.

In recommendation dialogs, humans commonly disclose their preference and make recommendations in a friendly manner. However, this is a challenge when developing a sociable recommendation dialog system, due to the lack of dialog dataset annotated with such sociable strategies. Therefore, we present INSPIRED, a new dataset of 1,001 human-human dialogs for movie recommendation with measures for successful recommendations. To better understand how humans make recommendations in communication, we design an annotation scheme related to recommendation strategies based on social science theories and annotate these dialogs. Our analysis shows that sociable recommendation strategies, such as sharing personal opinions or communicating with encouragement, more frequently lead to successful recommendations. Based on our dataset, we train end-to-end recommendation dialog systems with and without our strategy labels. In both automatic and human evaluation, our model with strategy incorporation outperforms the baseline model. This work is a first step for building sociable recommendation dialog systems with a basis of social science theories.

Liang Qiu, Yizhou Zhao, Weiyan Shi et al.

Inducing a meaningful structural representation from one or a set of dialogues is a crucial but challenging task in computational linguistics. Advancement made in this area is critical for dialogue system design and discourse analysis. It can also be extended to solve grammatical inference. In this work, we propose to incorporate structured attention layers into a Variational Recurrent Neural Network (VRNN) model with discrete latent states to learn dialogue structure in an unsupervised fashion. Compared to a vanilla VRNN, structured attention enables a model to focus on different parts of the source sentence embeddings while enforcing a structural inductive bias. Experiments show that on two-party dialogue datasets, VRNN with structured attention learns semantic structures that are similar to templates used to generate this dialogue corpus. While on multi-party dialogue datasets, our model learns an interactive structure demonstrating its capability of distinguishing speakers or addresses, automatically disentangling dialogues without explicit human annotation.

Yucan Zhou, Yu Wang, Jianfei Cai et al.

Deep neural networks are highly effective when a large number of labeled samples are available but fail with few-shot classification tasks. Recently, meta-learning methods have received much attention, which train a meta-learner on massive additional tasks to gain the knowledge to instruct the few-shot classification. Usually, the training tasks are randomly sampled and performed indiscriminately, often making the meta-learner stuck into a bad local optimum. Some works in the optimization of deep neural networks have shown that a better arrangement of training data can make the classifier converge faster and perform better. Inspired by this idea, we propose an easy-to-hard expert meta-training strategy to arrange the training tasks properly, where easy tasks are preferred in the first phase, then, hard tasks are emphasized in the second phase. A task hardness aware module is designed and integrated into the training procedure to estimate the hardness of a task based on the distinguishability of its categories. In addition, we explore multiple hardness measurements including the semantic relation, the pairwise Euclidean distance, the Hausdorff distance, and the Hilbert-Schmidt independence criterion. Experimental results on the miniImageNet and tieredImageNetSketch datasets show that the meta-learners can obtain better results with our expert training strategy.

Jing Gu, Zhou Yu

There is a huge performance gap between formal and informal language understanding tasks. The recent pre-trained models that improved the performance of formal language understanding tasks did not achieve a comparable result on informal language. We pro-pose a data annealing transfer learning procedure to bridge the performance gap on informal natural language understanding tasks. It successfully utilizes a pre-trained model such as BERT in informal language. In our data annealing procedure, the training set contains mainly formal text data at first; then, the proportion of the informal text data is gradually increased during the training process. Our data annealing procedure is model-independent and can be applied to various tasks. We validate its effectiveness in exhaustive experiments. When BERT is implemented with our learning procedure, it outperforms all the state-of-the-art models on the three common informal language tasks.

Jing Gu, Qingyang Wu, Chongruo Wu et al.

The recent success of large pre-trained language models such as BERT and GPT-2 has suggested the effectiveness of incorporating language priors in downstream dialog generation tasks. However, the performance of pre-trained models on the dialog task is not as optimal as expected. In this paper, we propose a Pre-trained Role Alternating Language model (PRAL), designed specifically for task-oriented conversational systems. We adopted (Wu et al., 2019) that models two speakers separately. We also design several techniques, such as start position randomization, knowledge distillation, and history discount to improve pre-training performance. We introduce a task-oriented dialog pretraining dataset by cleaning 13 existing data sets. We test PRAL on three different downstream tasks. The results show that PRAL performs better or on par with state-of-the-art methods.

Qingyang Wu, Lei Li, Zhou Yu

Generative Adversarial Networks (GANs) for text generation have recently received many criticisms, as they perform worse than their MLE counterparts. We suspect previous text GANs' inferior performance is due to the lack of a reliable guiding signal in their discriminators. To address this problem, we propose a generative adversarial imitation learning framework for text generation that uses large pre-trained language models to provide more reliable reward guidance. Our approach uses contrastive discriminator, and proximal policy optimization (PPO) to stabilize and improve text generation performance. For evaluation, we conduct experiments on a diverse set of unconditional and conditional text generation tasks. Experimental results show that TextGAIL achieves better performance in terms of both quality and diversity than the MLE baseline. We also validate our intuition that TextGAIL's discriminator demonstrates the capability of providing reasonable rewards with an additional task.

Xixi Zhou, Chengxi Li, Jiajun Bu et al.

Text matching is a core natural language processing research problem. How to retain sufficient information on both content and structure information is one important challenge. In this paper, we present a neural approach for general-purpose text matching with deep mutual information estimation incorporated. Our approach, Text matching with Deep Info Max (TIM), is integrated with a procedure of unsupervised learning of representations by maximizing the mutual information between text matching neural network's input and output. We use both global and local mutual information to learn text representations. We evaluate our text matching approach on several tasks including natural language inference, paraphrase identification, and answer selection. Compared to the state-of-the-art approaches, the experiments show that our method integrated with mutual information estimation learns better text representation and achieves better experimental results of text matching tasks without exploiting pretraining on external data.

Weiyan Shi, Xuewei Wang, Yoo Jung Oh et al.

Intelligent conversational agents, or chatbots, can take on various identities and are increasingly engaging in more human-centered conversations with persuasive goals. However, little is known about how identities and inquiry strategies influence the conversation's effectiveness. We conducted an online study involving 790 participants to be persuaded by a chatbot for charity donation. We designed a two by four factorial experiment (two chatbot identities and four inquiry strategies) where participants were randomly assigned to different conditions. Findings showed that the perceived identity of the chatbot had significant effects on the persuasion outcome (i.e., donation) and interpersonal perceptions (i.e., competence, confidence, warmth, and sincerity). Further, we identified interaction effects among perceived identities and inquiry strategies. We discuss the findings for theoretical and practical implications for developing ethical and effective persuasive chatbots. Our published data, codes, and analyses serve as the first step towards building competent ethical persuasive chatbots.

Xiyuan Zhang, Chengxi Li, Dian Yu et al.

The phenomenon of ellipsis is prevalent in social conversations. Ellipsis increases the difficulty of a series of downstream language understanding tasks, such as dialog act prediction and semantic role labeling. We propose to resolve ellipsis through automatic sentence completion to improve language understanding. However, automatic ellipsis completion can result in output which does not accurately reflect user intent. To address this issue, we propose a method which considers both the original utterance that has ellipsis and the automatically completed utterance in dialog act and semantic role labeling tasks. Specifically, we first complete user utterances to resolve ellipsis using an end-to-end pointer network model. We then train a prediction model using both utterances containing ellipsis and our automatically completed utterances. Finally, we combine the prediction results from these two utterances using a selection model that is guided by expert knowledge. Our approach improves dialog act prediction and semantic role labeling by 1.3% and 2.5% in F1 score respectively in social conversations. We also present an open-domain human-machine conversation dataset with manually completed user utterances and annotated semantic role labeling after manual completion.

Yu Li, Kun Qian, Weiyan Shi et al.

End-to-end task-oriented dialog models have achieved promising performance on collaborative tasks where users willingly coordinate with the system to complete a given task. While in non-collaborative settings, for example, negotiation and persuasion, users and systems do not share a common goal. As a result, compared to collaborate tasks, people use social content to build rapport and trust in these non-collaborative settings in order to advance their goals. To handle social content, we introduce a hierarchical intent annotation scheme, which can be generalized to different non-collaborative dialog tasks. Building upon TransferTransfo (Wolf et al. 2019), we propose an end-to-end neural network model to generate diverse coherent responses. Our model utilizes intent and semantic slots as the intermediate sentence representation to guide the generation process. In addition, we design a filter to select appropriate responses based on whether these intermediate representations fit the designed task and conversation constraints. Our non-collaborative dialog model guides users to complete the task while simultaneously keeps them engaged. We test our approach on our newly proposed ANTISCAM dataset and an existing PERSUASIONFORGOOD dataset. Both automatic and human evaluations suggest that our model outperforms multiple baselines in these two non-collaborative tasks.

Qingyang Wu, Lei Li, Hao Zhou et al.

Many social media news writers are not professionally trained. Therefore, social media platforms have to hire professional editors to adjust amateur headlines to attract more readers. We propose to automate this headline editing process through neural network models to provide more immediate writing support for these social media news writers. To train such a neural headline editing model, we collected a dataset which contains articles with original headlines and professionally edited headlines. However, it is expensive to collect a large number of professionally edited headlines. To solve this low-resource problem, we design an encoder-decoder model which leverages large scale pre-trained language models. We further improve the pre-trained model's quality by introducing a headline generation task as an intermediate task before the headline editing task. Also, we propose Self Importance-Aware (SIA) loss to address the different levels of editing in the dataset by down-weighting the importance of easily classified tokens and sentences. With the help of Pre-training, Adaptation, and SIA, the model learns to generate headlines in the professional editor's style. Experimental results show that our method significantly improves the quality of headline editing comparing against previous methods.

Yichi Zhang, Zhijian Ou, Zhou Yu

Conversations have an intrinsic one-to-many property, which means that multiple responses can be appropriate for the same dialog context. In task-oriented dialogs, this property leads to different valid dialog policies towards task completion. However, none of the existing task-oriented dialog generation approaches takes this property into account. We propose a Multi-Action Data Augmentation (MADA) framework to utilize the one-to-many property to generate diverse appropriate dialog responses. Specifically, we first use dialog states to summarize the dialog history, and then discover all possible mappings from every dialog state to its different valid system actions. During dialog system training, we enable the current dialog state to map to all valid system actions discovered in the previous process to create additional state-action pairs. By incorporating these additional pairs, the dialog policy learns a balanced action distribution, which further guides the dialog model to generate diverse responses. Experimental results show that the proposed framework consistently improves dialog policy diversity, and results in improved response diversity and appropriateness. Our model obtains state-of-the-art results on MultiWOZ.

Qingyang Wu, Yichi Zhang, Yu Li et al.

Existing dialog system models require extensive human annotations and are difficult to generalize to different tasks. The recent success of large pre-trained language models such as BERT and GPT-2 (Devlin et al., 2019; Radford et al., 2019) have suggested the effectiveness of incorporating language priors in down-stream NLP tasks. However, how much pre-trained language models can help dialog response generation is still under exploration. In this paper, we propose a simple, general, and effective framework: Alternating Roles Dialog Model (ARDM). ARDM models each speaker separately and takes advantage of the large pre-trained language model. It requires no supervision from human annotations such as belief states or dialog acts to achieve effective conversations. ARDM outperforms or is on par with state-of-the-art methods on two popular task-oriented dialog datasets: CamRest676 and MultiWOZ. Moreover, we can generalize ARDM to more challenging, non-collaborative tasks such as persuasion. In persuasion tasks, ARDM is capable of generating human-like responses to persuade people to donate to a charity.

Dian Yu, Michelle Cohn, Yi Mang Yang et al.

Gunrock is the winner of the 2018 Amazon Alexa Prize, as evaluated by coherence and engagement from both real users and Amazon-selected expert conversationalists. We focus on understanding complex sentences and having in-depth conversations in open domains. In this paper, we introduce some innovative system designs and related validation analysis. Overall, we found that users produce longer sentences to Gunrock, which are directly related to users' engagement (e.g., ratings, number of turns). Additionally, users' backstory queries about Gunrock are positively correlated to user satisfaction. Finally, we found dialog flows that interleave facts and personal opinions and stories lead to better user satisfaction.

Yiheng Zhou, Yulia Tsvetkov, Alan W Black et al.

We study non-collaborative dialogs, where two agents have a conflict of interest but must strategically communicate to reach an agreement (e.g., negotiation). This setting poses new challenges for modeling dialog history because the dialog's outcome relies not only on the semantic intent, but also on tactics that convey the intent. We propose to model both semantic and tactic history using finite state transducers (FSTs). Unlike RNN, FSTs can explicitly represent dialog history through all the states traversed, facilitating interpretability of dialog structure. We train FSTs on a set of strategies and tactics used in negotiation dialogs. The trained FSTs show plausible tactic structure and can be generalized to other non-collaborative domains (e.g., persuasion). We evaluate the FSTs by incorporating them in an automated negotiating system that attempts to sell products and a persuasion system that persuades people to donate to a charity. Experiments show that explicitly modeling both semantic and tactic history is an effective way to improve both dialog policy planning and generation performance.

Weixin Liang, Youzhi Tian, Chengcai Chen et al.

A major bottleneck in training end-to-end task-oriented dialog system is the lack of data. To utilize limited training data more efficiently, we propose Modular Supervision Network (MOSS), an encoder-decoder training framework that could incorporate supervision from various intermediate dialog system modules including natural language understanding, dialog state tracking, dialog policy learning, and natural language generation. With only 60% of the training data, MOSS-all (i.e., MOSS with supervision from all four dialog modules) outperforms state-of-the-art models on CamRest676. Moreover, introducing modular supervision has even bigger benefits when the dialog task has a more complex dialog state and action space. With only 40% of the training data, MOSS-all outperforms the state-of-the-art model on a complex laptop network troubleshooting dataset, LaptopNetwork, that we introduced. LaptopNetwork consists of conversations between real customers and customer service agents in Chinese. Moreover, MOSS framework can accommodate dialogs that have supervision from different dialog modules at both the framework level and model level. Therefore, MOSS is extremely flexible to update in a real-world deployment.