Lun-Wei Ku

Chih-Yao Chen, Tun-Min Hung, Yi-Li Hsu et al.

Fine-grained emotion classification (FEC) is a challenging task. Specifically, FEC needs to handle subtle nuance between labels, which can be complex and confusing. Most existing models only address text classification problem in the euclidean space, which we believe may not be the optimal solution as labels of close semantic (e.g., afraid and terrified) may not be differentiated in such space, which harms the performance. In this paper, we propose HypEmo, a novel framework that can integrate hyperbolic embeddings to improve the FEC task. First, we learn label embeddings in the hyperbolic space to better capture their hierarchical structure, and then our model projects contextualized representations to the hyperbolic space to compute the distance between samples and labels. Experimental results show that incorporating such distance to weight cross entropy loss substantially improves the performance with significantly higher efficiency. We evaluate our proposed model on two benchmark datasets and found 4.8% relative improvement compared to the previous state of the art with 43.2% fewer parameters and 76.9% less training time. Code is available at https: //github.com/dinobby/HypEmo.

Shih-Chieh Dai, Aiping Xiong, Lun-Wei Ku

Thematic analysis (TA) has been widely used for analyzing qualitative data in many disciplines and fields. To ensure reliable analysis, the same piece of data is typically assigned to at least two human coders. Moreover, to produce meaningful and useful analysis, human coders develop and deepen their data interpretation and coding over multiple iterations, making TA labor-intensive and time-consuming. Recently the emerging field of large language models (LLMs) research has shown that LLMs have the potential replicate human-like behavior in various tasks: in particular, LLMs outperform crowd workers on text-annotation tasks, suggesting an opportunity to leverage LLMs on TA. We propose a human-LLM collaboration framework (i.e., LLM-in-the-loop) to conduct TA with in-context learning (ICL). This framework provides the prompt to frame discussions with a LLM (e.g., GPT-3.5) to generate the final codebook for TA. We demonstrate the utility of this framework using survey datasets on the aspects of the music listening experience and the usage of a password manager. Results of the two case studies show that the proposed framework yields similar coding quality to that of human coders but reduces TA's labor and time demands.

Shih-Chieh Dai, Yi-Li Hsu, Aiping Xiong et al.

Automated fact checking systems have been proposed that quickly provide veracity prediction at scale to mitigate the negative influence of fake news on people and on public opinion. However, most studies focus on veracity classifiers of those systems, which merely predict the truthfulness of news articles. We posit that effective fact checking also relies on people's understanding of the predictions. In this paper, we propose elucidating fact checking predictions using counterfactual explanations to help people understand why a specific piece of news was identified as fake. In this work, generating counterfactual explanations for fake news involves three steps: asking good questions, finding contradictions, and reasoning appropriately. We frame this research question as contradicted entailment reasoning through question answering (QA). We first ask questions towards the false claim and retrieve potential answers from the relevant evidence documents. Then, we identify the most contradictory answer to the false claim by use of an entailment classifier. Finally, a counterfactual explanation is created using a matched QA pair with three different counterfactual explanation forms. Experiments are conducted on the FEVER dataset for both system and human evaluations. Results suggest that the proposed approach generates the most helpful explanations compared to state-of-the-art methods.

Nicholas Collin Suwono, Justin Chih-Yao Chen, Tun Min Hung et al.

This work introduces a novel task, location-aware visual question generation (LocaVQG), which aims to generate engaging questions from data relevant to a particular geographical location. Specifically, we represent such location-aware information with surrounding images and a GPS coordinate. To tackle this task, we present a dataset generation pipeline that leverages GPT-4 to produce diverse and sophisticated questions. Then, we aim to learn a lightweight model that can address the LocaVQG task and fit on an edge device, such as a mobile phone. To this end, we propose a method which can reliably generate engaging questions from location-aware information. Our proposed method outperforms baselines regarding human evaluation (e.g., engagement, grounding, coherence) and automatic evaluation metrics (e.g., BERTScore, ROUGE-2). Moreover, we conduct extensive ablation studies to justify our proposed techniques for both generating the dataset and solving the task.

Min-Hsuan Yeh, Vicent Chen, Ting-Hao 'Kenneth' Haung et al.

Generating engaging content has drawn much recent attention in the NLP community. Asking questions is a natural way to respond to photos and promote awareness. However, most answers to questions in traditional question-answering (QA) datasets are factoids, which reduce individuals' willingness to answer. Furthermore, traditional visual question generation (VQG) confines the source data for question generation to single images, resulting in a limited ability to comprehend time-series information of the underlying event. In this paper, we propose generating engaging questions from multiple images. We present MVQG, a new dataset, and establish a series of baselines, including both end-to-end and dual-stage architectures. Results show that building stories behind the image sequence enables models to generate engaging questions, which confirms our assumption that people typically construct a picture of the event in their minds before asking questions. These results open up an exciting challenge for visual-and-language models to implicitly construct a story behind a series of photos to allow for creativity and experience sharing and hence draw attention to downstream applications.

Yi-Li Hsu, Shih-Chieh Dai, Aiping Xiong et al.

With advancements in natural language processing (NLP) models, automatic explanation generation has been proposed to mitigate misinformation on social media platforms in addition to adding warning labels to identified fake news. While many researchers have focused on generating good explanations, how these explanations can really help humans combat fake news is under-explored. In this study, we compare the effectiveness of a warning label and the state-of-the-art counterfactual explanations generated by GPT-4 in debunking misinformation. In a two-wave, online human-subject study, participants (N = 215) were randomly assigned to a control group in which false contents are shown without any intervention, a warning tag group in which the false claims were labeled, or an explanation group in which the false contents were accompanied by GPT-4 generated explanations. Our results show that both interventions significantly decrease participants' self-reported belief in fake claims in an equivalent manner for the short-term and long-term. We discuss the implications of our findings and directions for future NLP-based misinformation debunking strategies.

Chih-Yao Chen, Dennis Wu, Lun-Wei Ku

Current methods for generating attractive headlines often learn directly from data, which bases attractiveness on the number of user clicks and views. Although clicks or views do reflect user interest, they can fail to reveal how much interest is raised by the writing style and how much is due to the event or topic itself. Also, such approaches can lead to harmful inventions by over-exaggerating the content, aggravating the spread of false information. In this work, we propose HonestBait, a novel framework for solving these issues from another aspect: generating headlines using forward references (FRs), a writing technique often used for clickbait. A self-verification process is included during training to avoid spurious inventions. We begin with a preliminary user study to understand how FRs affect user interest, after which we present PANCO1, an innovative dataset containing pairs of fake news with verified news for attractive but faithful news headline generation. Automatic metrics and human evaluations show that our framework yields more attractive results (+11.25% compared to human-written verified news headlines) while maintaining high veracity, which helps promote real information to fight against fake news.

Luis Frentzen Salim, Esteban Carlin, Alexandre Morinvil et al.

Building machine translation (MT) systems for low-resource languages is notably difficult due to the scarcity of high-quality data. Although Large Language Models (LLMs) have improved MT system performance, adapting them to lesser-represented languages remains challenging. In-context learning (ICL) may offer novel ways to adapt LLMs for low-resource MT by conditioning models on demonstration at inference time. In this study, we explore scaling low-resource machine translation ICL beyond the few-shot setting to thousands of examples with long-context models. We scale in-context token budget to 1M tokens and compare three types of training corpora used as in-context supervision: monolingual unsupervised data, instruction-style data, and parallel data (English--target and Indonesian--target). Our experiments on Javanese and Sundanese show that gains from additional context saturate quickly and can degrade near the maximum context window, with scaling behavior strongly dependent on corpus type. Notably, some forms of monolingual supervision can be competitive with parallel data, despite the latter offering additional supervision. Overall, our results characterize the effective limits and corpus-type sensitivity of long-context ICL for low-resource MT, highlighting that larger context windows do not necessarily yield proportional quality gains.

Shih-Han Chan, Tsai-Lun Yang, Yun-Wei Chu et al.

An engaging and provocative question can open up a great conversation. In this work, we explore a novel scenario: a conversation agent views a set of the user's photos (for example, from social media platforms) and asks an engaging question to initiate a conversation with the user. The existing vision-to-question models mostly generate tedious and obvious questions, which might not be ideals conversation starters. This paper introduces a two-phase framework that first generates a visual story for the photo set and then uses the story to produce an interesting question. The human evaluation shows that our framework generates more response-provoking questions for starting conversations than other vision-to-question baselines.

Chao-Chun Hsu, Zi-Yuan Chen, Chi-Yang Hsu et al.

Stories are diverse and highly personalized, resulting in a large possible output space for story generation. Existing end-to-end approaches produce monotonous stories because they are limited to the vocabulary and knowledge in a single training dataset. This paper introduces KG-Story, a three-stage framework that allows the story generation model to take advantage of external Knowledge Graphs to produce interesting stories. KG-Story distills a set of representative words from the input prompts, enriches the word set by using external knowledge graphs, and finally generates stories based on the enriched word set. This distill-enrich-generate framework allows the use of external resources not only for the enrichment phase, but also for the distillation and generation phases. In this paper, we show the superiority of KG-Story for visual storytelling, where the input prompt is a sequence of five photos and the output is a short story. Per the human ranking evaluation, stories generated by KG-Story are on average ranked better than that of the state-of-the-art systems. Our code and output stories are available at https://github.com/zychen423/KE-VIST.

Wei-Hsin Yeh, Pei Hsin Lin, Yu-An Su et al.

Many people engage in self-directed sports training at home but lack the real-time guidance of professional coaches, making them susceptible to injuries or the development of incorrect habits. In this paper, we propose a novel application framework called MAAIG(Motion Analysis And Instruction Generation). It can generate embedding vectors for each frame based on user-provided sports action videos. These embedding vectors are associated with the 3D skeleton of each frame and are further input into a pretrained T5 model. Ultimately, our model utilizes this information to generate specific sports instructions. It has the capability to identify potential issues and provide real-time guidance in a manner akin to professional coaches, helping users improve their sports skills and avoid injuries.

Ting-Yao E. Hsu, Yi-Li Hsu, Shaurya Rohatgi et al.

Since the SciCap datasets launch in 2021, the research community has made significant progress in generating captions for scientific figures in scholarly articles. In 2023, the first SciCap Challenge took place, inviting global teams to use an expanded SciCap dataset to develop models for captioning diverse figure types across various academic fields. At the same time, text generation models advanced quickly, with many powerful pre-trained large multimodal models (LMMs) emerging that showed impressive capabilities in various vision-and-language tasks. This paper presents an overview of the first SciCap Challenge and details the performance of various models on its data, capturing a snapshot of the fields state. We found that professional editors overwhelmingly preferred figure captions generated by GPT-4V over those from all other models and even the original captions written by authors. Following this key finding, we conducted detailed analyses to answer this question: Have advanced LMMs solved the task of generating captions for scientific figures?

Wei-Yi Chen, Yi-Ling Lin, Yu-An Su et al.

Combining sports and machine learning involves leveraging ML algorithms and techniques to extract insight from sports-related data such as player statistics, game footage, and other relevant information. However, datasets related to figure skating in the literature focus primarily on element classification and are currently unavailable or exhibit only limited access, which greatly raise the entry barrier to developing visual sports technology for it. Moreover, when using such data to help athletes improve their skills, we find they are very coarse-grained: they work for learning what an element is, but they are poorly suited to learning whether the element is good or bad. Here we propose air time detection, a novel motion analysis task, the goal of which is to accurately detect the duration of the air time of a jump. We present YourSkatingCoach, a large, novel figure skating dataset which contains 454 videos of jump elements, the detected skater skeletons in each video, along with the gold labels of the start and ending frames of each jump, together as a video benchmark for figure skating. In addition, although this type of task is often viewed as classification, we cast it as a sequential labeling problem and propose a Transformer-based model to calculate the duration. Experimental results show that the proposed model yields a favorable results for a strong baseline. To further verify the generalizability of the fine-grained labels, we apply the same process to other sports as cross-sports tasks but for coarse-grained task action classification. Here we fine-tune the classification to demonstrate that figure skating, as it contains the essential body movements, constitutes a strong foundation for adaptation to other sports.

Luis Frentzen Salim, Lun-Wei Ku, Hsing-Kuo Kenneth Pao

Adapting large language models (LLMs) to new languages is an expensive and opaque process. Understanding how language models acquire new languages and multilingual abilities is key to achieve efficient adaptation. Prior work on multilingual interpretability research focuses primarily on how trained models process multilingual instructions, leaving unexplored the mechanisms through which they acquire new languages during training. We investigate these training dynamics on decoder-only transformers through the lens of two functional cognitive specializations: language perception (input comprehension) and production (output generation). Through experiments on low-resource languages, we demonstrate how perceptual and productive specialization emerges in different regions of a language model by running layer ablation sweeps from the model's input and output directions. Based on the observed specialization patterns, we propose CogSym, a layer-wise heuristic that enables effective adaptation by exclusively fine-tuning a few early and late layers. We show that tuning only the 25% outermost layers achieves downstream task performance within 2-3% deviation from the full fine-tuning baseline. CogSym yields consistent performance with adapter methods such as LoRA, showcasing generalization beyond full fine-tuning. These findings provide insights to better understand how LLMs learn new languages and push toward accessible and inclusive language modeling.

Shi-Wei Dai, Yan-Wei Shie, Tsung-Huan Yang et al.

Personalized Large Language Models (LLMs) have been shown to be an effective way to create more engaging and enjoyable user-AI interactions. While previous studies have explored using prompts to elicit specific personality traits in LLMs, they have not optimized these prompts to maximize personality expression. To address this limitation, we propose PersonaPulse: Dynamic Profile Optimization for Realistic Personality Expression in LLMs, a framework that leverages LLMs' inherent knowledge of personality traits to iteratively enhance role-play prompts while integrating a situational response benchmark as a scoring tool, ensuring a more realistic and contextually grounded evaluation to guide the optimization process. Quantitative evaluations demonstrate that the prompts generated by PersonaPulse outperform those of prior work, which were designed based on personality descriptions from psychological studies. Additionally, we explore the relationship between model size and personality modeling through extensive experiments. Finally, we find that, for certain personality traits, the extent of personality evocation can be partially controlled by pausing the optimization process. These findings underscore the importance of prompt optimization in shaping personality expression within LLMs, offering valuable insights for future research on adaptive AI interactions.

Wei-Hsin Yeh, Yu-An Su, Chih-Ning Chen et al.

Motion instruction is a crucial task that helps athletes refine their technique by analyzing movements and providing corrective guidance. Although recent advances in multimodal models have improved motion understanding, generating precise and sport-specific instruction remains challenging due to the highly domain-specific nature of sports and the need for informative guidance. We propose CoachMe, a reference-based model that analyzes the differences between a learner's motion and a reference under temporal and physical aspects. This approach enables both domain-knowledge learning and the acquisition of a coach-like thinking process that identifies movement errors effectively and provides feedback to explain how to improve. In this paper, we illustrate how CoachMe adapts well to specific sports such as skating and boxing by learning from general movements and then leveraging limited data. Experiments show that CoachMe provides high-quality instructions instead of directions merely in the tone of a coach but without critical information. CoachMe outperforms GPT-4o by 31.6% in G-Eval on figure skating and by 58.3% on boxing. Analysis further confirms that it elaborates on errors and their corresponding improvement methods in the generated instructions. You can find CoachMe here: https://motionxperts.github.io/

Chang-You Tai, Ming-Yao Li, Lun-Wei Ku

Automatic identification of salient aspects from user reviews is especially useful for opinion analysis. There has been significant progress in utilizing weakly supervised approaches, which require only a small set of seed words for training aspect classifiers. However, there is always room for improvement. First, no weakly supervised approaches fully utilize latent hierarchies between words. Second, each seed words representation should have different latent semantics and be distinct when it represents a different aspect. In this paper, we propose HDAE, a hyperbolic disentangled aspect extractor in which a hyperbolic aspect classifier captures words latent hierarchies, and aspect-disentangled representation models the distinct latent semantics of each seed word. Compared to previous baselines, HDAE achieves average F1 performance gains of 18.2% and 24.1% on Amazon product review and restaurant review datasets, respectively. In addition, the em-bedding visualization experience demonstrates that HDAE is a more effective approach to leveraging seed words. An ablation study and a case study further attest to the effectiveness of the proposed components

Boaz Shmueli, Soumya Ray, Lun-Wei Ku

Datasets with induced emotion labels are scarce but of utmost importance for many NLP tasks. We present a new, automated method for collecting texts along with their induced reaction labels. The method exploits the online use of reaction GIFs, which capture complex affective states. We show how to augment the data with induced emotion and induced sentiment labels. We use our method to create and publish ReactionGIF, a first-of-its-kind affective dataset of 30K tweets. We provide baselines for three new tasks, including induced sentiment prediction and multilabel classification of induced emotions. Our method and dataset open new research opportunities in emotion detection and affective computing.

Chi-Yang Hsu, Yun-Wei Chu, Ting-Hao 'Kenneth' Huang et al.

Writing a coherent and engaging story is not easy. Creative writers use their knowledge and worldview to put disjointed elements together to form a coherent storyline, and work and rework iteratively toward perfection. Automated visual storytelling (VIST) models, however, make poor use of external knowledge and iterative generation when attempting to create stories. This paper introduces PR-VIST, a framework that represents the input image sequence as a story graph in which it finds the best path to form a storyline. PR-VIST then takes this path and learns to generate the final story via an iterative training process. This framework produces stories that are superior in terms of diversity, coherence, and humanness, per both automatic and human evaluations. An ablation study shows that both plotting and reworking contribute to the model's superiority.

Boaz Shmueli, Jan Fell, Soumya Ray et al.

The use of crowdworkers in NLP research is growing rapidly, in tandem with the exponential increase in research production in machine learning and AI. Ethical discussion regarding the use of crowdworkers within the NLP research community is typically confined in scope to issues related to labor conditions such as fair pay. We draw attention to the lack of ethical considerations related to the various tasks performed by workers, including labeling, evaluation, and production. We find that the Final Rule, the common ethical framework used by researchers, did not anticipate the use of online crowdsourcing platforms for data collection, resulting in gaps between the spirit and practice of human-subjects ethics in NLP research. We enumerate common scenarios where crowdworkers performing NLP tasks are at risk of harm. We thus recommend that researchers evaluate these risks by considering the three ethical principles set up by the Belmont Report. We also clarify some common misconceptions regarding the Institutional Review Board (IRB) application. We hope this paper will serve to reopen the discussion within our community regarding the ethical use of crowdworkers.

Boaz Shmueli, Lun-Wei Ku, Soumya Ray

We present an overview of the EmotionGIF2020 Challenge, held at the 8th International Workshop on Natural Language Processing for Social Media (SocialNLP), in conjunction with ACL 2020. The challenge required predicting affective reactions to online texts, and included the EmotionGIF dataset, with tweets labeled for the reaction categories. The novel dataset included 40K tweets with their reaction GIFs. Due to the special circumstances of year 2020, two rounds of the competition were conducted. A total of 84 teams registered for the task. Of these, 25 teams success-fully submitted entries to the evaluation phase in the first round, while 13 teams participated successfully in the second round. Of the top participants, five teams presented a technical report and shared their code. The top score of the winning team using the Recall@K metric was 62.47%.

Yun-Hsuan Jen, Chieh-Yang Huang, Mei-Hua Chen et al.

Many English-as-a-second language learners have trouble using near-synonym words (e.g., small vs.little; briefly vs.shortly) correctly, and often look for example sentences to learn how two nearly synonymous terms differ. Prior work uses hand-crafted scores to recommend sentences but has difficulty in adopting such scores to all the near-synonyms as near-synonyms differ in various ways. We notice that the helpfulness of the learning material would reflect on the learners' performance. Thus, we propose the inference-based learner-like agent to mimic learner behavior and identify good learning materials by examining the agent's performance. To enable the agent to behave like a learner, we leverage entailment modeling's capability of inferring answers from the provided materials. Experimental results show that the proposed agent is equipped with good learner-like behavior to achieve the best performance in both fill-in-the-blank (FITB) and good example sentence selection tasks. We further conduct a classroom user study with college ESL learners. The results of the user study show that the proposed agent can find out example sentences that help students learn more easily and efficiently. Compared to other models, the proposed agent improves the score of more than 17% of students after learning.

Boaz Shmueli, Lun-Wei Ku, Soumya Ray

Sarcasm detection is an important task in affective computing, requiring large amounts of labeled data. We introduce reactive supervision, a novel data collection method that utilizes the dynamics of online conversations to overcome the limitations of existing data collection techniques. We use the new method to create and release a first-of-its-kind large dataset of tweets with sarcasm perspective labels and new contextual features. The dataset is expected to advance sarcasm detection research. Our method can be adapted to other affective computing domains, thus opening up new research opportunities.

Chang-You Tai, Meng-Ru Wu, Yun-Wei Chu et al.

Researchers have begun to utilize heterogeneous knowledge graphs (KGs) as auxiliary information in recommendation systems to mitigate the cold start and sparsity issues. However, utilizing a graph neural network (GNN) to capture information in KG and further apply in RS is still problematic as it is unable to see each item's properties from multiple perspectives. To address these issues, we propose the multi-view item network (MVIN), a GNN-based recommendation model which provides superior recommendations by describing items from a unique mixed view from user and entity angles. MVIN learns item representations from both the user view and the entity view. From the user view, user-oriented modules score and aggregate features to make recommendations from a personalized perspective constructed according to KG entities which incorporates user click information. From the entity view, the mixing layer contrasts layer-wise GCN information to further obtain comprehensive features from internal entity-entity interactions in the KG. We evaluate MVIN on three real-world datasets: MovieLens-1M (ML-1M), LFM-1b 2015 (LFM-1b), and Amazon-Book (AZ-book). Results show that MVIN significantly outperforms state-of-the-art methods on these three datasets. In addition, from user-view cases, we find that MVIN indeed captures entities that attract users. Figures further illustrate that mixing layers in a heterogeneous KG plays a vital role in neighborhood information aggregation.

Yun-Zhu Song, Hong-Han Shuai, Sung-Lin Yeh et al.

With the rapid proliferation of online media sources and published news, headlines have become increasingly important for attracting readers to news articles, since users may be overwhelmed with the massive information. In this paper, we generate inspired headlines that preserve the nature of news articles and catch the eye of the reader simultaneously. The task of inspired headline generation can be viewed as a specific form of Headline Generation (HG) task, with the emphasis on creating an attractive headline from a given news article. To generate inspired headlines, we propose a novel framework called POpularity-Reinforced Learning for inspired Headline Generation (PORL-HG). PORL-HG exploits the extractive-abstractive architecture with 1) Popular Topic Attention (PTA) for guiding the extractor to select the attractive sentence from the article and 2) a popularity predictor for guiding the abstractor to rewrite the attractive sentence. Moreover, since the sentence selection of the extractor is not differentiable, techniques of reinforcement learning (RL) are utilized to bridge the gap with rewards obtained from a popularity score predictor. Through quantitative and qualitative experiments, we show that the proposed PORL-HG significantly outperforms the state-of-the-art headline generation models in terms of attractiveness evaluated by both human (71.03%) and the predictor (at least 27.60%), while the faithfulness of PORL-HG is also comparable to the state-of-the-art generation model.

Yun-Wei Chu, Kuan-Yen Lin, Chao-Chun Hsu et al.

Understanding dynamic scenes and dialogue contexts in order to converse with users has been challenging for multimodal dialogue systems. The 8-th Dialog System Technology Challenge (DSTC8) proposed an Audio Visual Scene-Aware Dialog (AVSD) task, which contains multiple modalities including audio, vision, and language, to evaluate how dialogue systems understand different modalities and response to users. In this paper, we proposed a multi-step joint-modality attention network (JMAN) based on recurrent neural network (RNN) to reason on videos. Our model performs a multi-step attention mechanism and jointly considers both visual and textual representations in each reasoning process to better integrate information from the two different modalities. Compared to the baseline released by AVSD organizers, our model achieves a relative 12.1% and 22.4% improvement over the baseline on ROUGE-L score and CIDEr score.

Boaz Shmueli, Lun-Wei Ku

We present an overview of the EmotionX 2019 Challenge, held at the 7th International Workshop on Natural Language Processing for Social Media (SocialNLP), in conjunction with IJCAI 2019. The challenge entailed predicting emotions in spoken and chat-based dialogues using augmented EmotionLines datasets. EmotionLines contains two distinct datasets: the first includes excerpts from a US-based TV sitcom episode scripts (Friends) and the second contains online chats (EmotionPush). A total of thirty-six teams registered to participate in the challenge. Eleven of the teams successfully submitted their predictions performance evaluation. The top-scoring team achieved a micro-F1 score of 81.5% for the spoken-based dialogues (Friends) and 79.5% for the chat-based dialogues (EmotionPush).

Kuan-Yen Lin, Chao-Chun Hsu, Yun-Nung Chen et al.

With increasing information from social media, there are more and more videos available. Therefore, the ability to reason on a video is important and deserves to be discussed. TheDialog System Technology Challenge (DSTC7) (Yoshino et al. 2018) proposed an Audio Visual Scene-aware Dialog (AVSD) task, which contains five modalities including video, dialogue history, summary, and caption, as a scene-aware environment. In this paper, we propose the entropy-enhanced dynamic memory network (DMN) to effectively model video modality. The attention-based GRU in the proposed model can improve the model's ability to comprehend and memorize sequential information. The entropy mechanism can control the attention distribution higher, so each to-be-answered question can focus more specifically on a small set of video segments. After the entropy-enhanced DMN secures the video context, we apply an attention model that in-corporates summary and caption to generate an accurate answer given the question about the video. In the official evaluation, our system can achieve improved performance against the released baseline model for both subjective and objective evaluation metrics.

Chieh-Yang Huang, Yi-Ting Huang, Mei-Hua Chen et al.

Knowing how to use words appropriately has been a key to improving language proficiency. Previous studies typically discuss how students learn receptively to select the correct candidate from a set of confusing words in the fill-in-the-blank task where specific context is given. In this paper, we go one step further, assisting students to learn to use confusing words appropriately in a productive task: sentence translation. We leverage the GiveMeExample system, which suggests example sentences for each confusing word, to achieve this goal. In this study, students learn to differentiate the confusing words by reading the example sentences, and then choose the appropriate word(s) to complete the sentence translation task. Results show students made substantial progress in terms of sentence structure. In addition, highly proficient students better managed to learn confusing words. In view of the influence of the first language on learners, we further propose an effective approach to improve the quality of the suggested sentences.

Zi-Yuan Chen, Chih-Hung Chang, Yi-Pei Chen et al.

In relation extraction for knowledge-based question answering, searching from one entity to another entity via a single relation is called "one hop". In related work, an exhaustive search from all one-hop relations, two-hop relations, and so on to the max-hop relations in the knowledge graph is necessary but expensive. Therefore, the number of hops is generally restricted to two or three. In this paper, we propose UHop, an unrestricted-hop framework which relaxes this restriction by use of a transition-based search framework to replace the relation-chain-based search one. We conduct experiments on conventional 1- and 2-hop questions as well as lengthy questions, including datasets such as WebQSP, PathQuestion, and Grid World. Results show that the proposed framework enables the ability to halt, works well with state-of-the-art models, achieves competitive performance without exhaustive searches, and opens the performance gap for long relation paths.

Chao-Chun Hsu, Yu-Hua Chen, Zi-Yuan Chen et al.

In this paper, we introduce Dixit, an interactive visual storytelling system that the user interacts with iteratively to compose a short story for a photo sequence. The user initiates the process by uploading a sequence of photos. Dixit first extracts text terms from each photo which describe the objects (e.g., boy, bike) or actions (e.g., sleep) in the photo, and then allows the user to add new terms or remove existing terms. Dixit then generates a short story based on these terms. Behind the scenes, Dixit uses an LSTM-based model trained on image caption data and FrameNet to distill terms from each image and utilizes a transformer decoder to compose a context-coherent story. Users change images or terms iteratively with Dixit to create the most ideal story. Dixit also allows users to manually edit and rate stories. The proposed procedure opens up possibilities for interpretable and controllable visual storytelling, allowing users to understand the story formation rationale and to intervene in the generation process.

Chia-Wei Chen, Sheng-Chuan Chou, Lun-Wei Ku

Recent deep learning methods for recommendation systems are highly sophisticated. For article recommendation task, a neural network encoder which generates a latent representation of the article content would prove useful. However, using raw text with embedding for models could degrade sentence meanings and deteriorate performance. In this paper, we propose PhrecSys (Phrase-based Recommendation System), which injects phrase-level features into content-based recommendation systems to enhance feature informativeness and model interpretability. Experiments conducted on six months of real-world data demonstrate that phrase features boost content-based models in predicting both user click and view behavior. Furthermore, the attention mechanism illustrates that phrase awareness benefits the learning of textual focus by putting the model's attention on meaningful text spans, which leads to interpretable article recommendation.

Chao-Chun Hsu, Szu-Min Chen, Ming-Hsun Hsieh et al.

Visual storytelling includes two important parts: coherence between the story and images as well as the story structure. For image to text neural network models, similar images in the sequence would provide close information for story generator to obtain almost identical sentence. However, repeatedly narrating same objects or events will undermine a good story structure. In this paper, we proposed an inter-sentence diverse beam search to generate a more expressive story. Comparing to some recent models of visual storytelling task, which generate story without considering the generated sentence of the previous picture, our proposed method can avoid generating identical sentence even given a sequence of similar pictures.

Sheng-Yeh Chen, Chao-Chun Hsu, Chuan-Chun Kuo et al.

Feeling emotion is a critical characteristic to distinguish people from machines. Among all the multi-modal resources for emotion detection, textual datasets are those containing the least additional information in addition to semantics, and hence are adopted widely for testing the developed systems. However, most of the textual emotional datasets consist of emotion labels of only individual words, sentences or documents, which makes it challenging to discuss the contextual flow of emotions. In this paper, we introduce EmotionLines, the first dataset with emotions labeling on all utterances in each dialogue only based on their textual content. Dialogues in EmotionLines are collected from Friends TV scripts and private Facebook messenger dialogues. Then one of seven emotions, six Ekman's basic emotions plus the neutral emotion, is labeled on each utterance by 5 Amazon MTurkers. A total of 29,245 utterances from 2,000 dialogues are labeled in EmotionLines. We also provide several strong baselines for emotion detection models on EmotionLines in this paper.

Chieh-Yang Huang, Tristan Labetoulle, Ting-Hao Kenneth Huang et al.

We present MoodSwipe, a soft keyboard that suggests text messages given the user-specified emotions utilizing the real dialog data. The aim of MoodSwipe is to create a convenient user interface to enjoy the technology of emotion classification and text suggestion, and at the same time to collect labeled data automatically for developing more advanced technologies. While users select the MoodSwipe keyboard, they can type as usual but sense the emotion conveyed by their text and receive suggestions for their message as a benefit. In MoodSwipe, the detected emotions serve as the medium for suggested texts, where viewing the latter is the incentive to correcting the former. We conduct several experiments to show the superiority of the emotion classification models trained on the dialog data, and further to verify good emotion cues are important context for text suggestion.

Chieh-Yang Huang, Ting-Hao, Huang et al.

Instant messaging is one of the major channels of computer mediated communication. However, humans are known to be very limited in understanding others' emotions via text-based communication. Aiming on introducing emotion sensing technologies to instant messaging, we developed EmotionPush, a system that automatically detects the emotions of the messages end-users received on Facebook Messenger and provides colored cues on their smartphones accordingly. We conducted a deployment study with 20 participants during a time span of two weeks. In this paper, we revealed five challenges, along with examples, that we observed in our study based on both user's feedback and chat logs, including (i)the continuum of emotions, (ii)multi-user conversations, (iii)different dynamics between different users, (iv)misclassification of emotions and (v)unconventional content. We believe this discussion will benefit the future exploration of affective computing for instant messaging, and also shed light on research of conversational emotion sensing.

Wei-Fan Chen, Lun-Wei Ku

Most neural network models for document classification on social media focus on text infor-mation to the neglect of other information on these platforms. In this paper, we classify post stance on social media channels and develop UTCNN, a neural network model that incorporates user tastes, topic tastes, and user comments on posts. UTCNN not only works on social media texts, but also analyzes texts in forums and message boards. Experiments performed on Chinese Facebook data and English online debate forum data show that UTCNN achieves a 0.755 macro-average f-score for supportive, neutral, and unsupportive stance classes on Facebook data, which is significantly better than models in which either user, topic, or comment information is withheld. This model design greatly mitigates the lack of data for the minor class without the use of oversampling. In addition, UTCNN yields a 0.842 accuracy on English online debate forum data, which also significantly outperforms results from previous work as well as other deep learning models, showing that UTCNN performs well regardless of language or platform.

Shih-Ming Wang, Chun-Hui Li, Yu-Chun Lo et al.

Instant messaging and push notifications play important roles in modern digital life. To enable robust sense-making and rich context awareness in computer mediated communications, we introduce EmotionPush, a system that automatically conveys the emotion of received text with a colored push notification on mobile devices. EmotionPush is powered by state-of-the-art emotion classifiers and is deployed for Facebook Messenger clients on Android. The study showed that the system is able to help users prioritize interactions.