Lina M. Rojas-Barahona

Léo Jacqmin, Lina M. Rojas-Barahona, Benoit Favre

While communicating with a user, a task-oriented dialogue system has to track the user's needs at each turn according to the conversation history. This process called dialogue state tracking (DST) is crucial because it directly informs the downstream dialogue policy. DST has received a lot of interest in recent years with the text-to-text paradigm emerging as the favored approach. In this review paper, we first present the task and its associated datasets. Then, considering a large number of recent publications, we identify highlights and advances of research in 2021-2022. Although neural approaches have enabled significant progress, we argue that some critical aspects of dialogue systems such as generalizability are still underexplored. To motivate future studies, we propose several research avenues.

Léo Jacqmin, Lucas Druart, Yannick Estève et al.

Though Dialogue State Tracking (DST) is a core component of spoken dialogue systems, recent work on this task mostly deals with chat corpora, disregarding the discrepancies between spoken and written language.In this paper, we propose OLISIA, a cascade system which integrates an Automatic Speech Recognition (ASR) model and a DST model. We introduce several adaptations in the ASR and DST modules to improve integration and robustness to spoken conversations.With these adaptations, our system ranked first in DSTC11 Track 3, a benchmark to evaluate spoken DST. We conduct an in-depth analysis of the results and find that normalizing the ASR outputs and adapting the DST inputs through data augmentation, along with increasing the pre-trained models size all play an important role in reducing the performance discrepancy between written and spoken conversations.

Quentin Brabant, Gwenole Lecorve, Lina M. Rojas-Barahona

Questions asked by humans during a conversation often contain contextual dependencies, i.e., explicit or implicit references to previous dialogue turns. These dependencies take the form of coreferences (e.g., via pronoun use) or ellipses, and can make the understanding difficult for automated systems. One way to facilitate the understanding and subsequent treatments of a question is to rewrite it into an out-of-context form, i.e., a form that can be understood without the conversational context. We propose CoQAR, a corpus containing $4.5$K conversations from the Conversational Question-Answering dataset CoQA, for a total of $53$K follow-up question-answer pairs. Each original question was manually annotated with at least 2 at most 3 out-of-context rewritings. CoQAR can be used in the supervised learning of three tasks: question paraphrasing, question rewriting and conversational question answering. In order to assess the quality of CoQAR's rewritings, we conduct several experiments consisting in training and evaluating models for these three tasks. Our results support the idea that question rewriting can be used as a preprocessing step for question answering models, thereby increasing their performances.

Michele Cafagna, Lina M. Rojas-Barahona, Kees van Deemter et al.

When applied to Image-to-text models, interpretability methods often provide token-by-token explanations namely, they compute a visual explanation for each token of the generated sequence. Those explanations are expensive to compute and unable to comprehensively explain the model's output. Therefore, these models often require some sort of approximation that eventually leads to misleading explanations. We develop a framework based on SHAP, that allows for generating comprehensive, meaningful explanations leveraging the meaning representation of the output sequence as a whole. Moreover, by exploiting semantic priors in the visual backbone, we extract an arbitrary number of features that allows the efficient computation of Shapley values on large-scale models, generating at the same time highly meaningful visual explanations. We demonstrate that our method generates semantically more expressive explanations than traditional methods at a lower compute cost and that it can be generalized over other explainability methods.

Sebastien Montella, Alexis Nasr, Johannes Heinecke et al.

Text generation from Abstract Meaning Representation (AMR) has substantially benefited from the popularized Pretrained Language Models (PLMs). Myriad approaches have linearized the input graph as a sequence of tokens to fit the PLM tokenization requirements. Nevertheless, this transformation jeopardizes the structural integrity of the graph and is therefore detrimental to its resulting representation. To overcome this issue, Ribeiro et al. have recently proposed StructAdapt, a structure-aware adapter which injects the input graph connectivity within PLMs using Graph Neural Networks (GNNs). In this paper, we investigate the influence of Relative Position Embeddings (RPE) on AMR-to-Text, and, in parallel, we examine the robustness of StructAdapt. Through ablation studies, graph attack and link prediction, we reveal that RPE might be partially encoding input graphs. We suggest further research regarding the role of RPE will provide valuable insights for Graph-to-Text generation.

Thibault Cordier, Tanguy Urvoy, Fabrice Lefevre et al.

Reinforcement learning has been widely adopted to model dialogue managers in task-oriented dialogues. However, the user simulator provided by state-of-the-art dialogue frameworks are only rough approximations of human behaviour. The ability to learn from a small number of human interactions is hence crucial, especially on multi-domain and multi-task environments where the action space is large. We therefore propose to use structured policies to improve sample efficiency when learning on these kinds of environments. We also evaluate the impact of learning from human vs simulated experts. Among the different levels of structure that we tested, the graph neural networks (GNNs) show a remarkable superiority by reaching a success rate above 80% with only 50 dialogues, when learning from simulated experts. They also show superiority when learning from human experts, although a performance drop was observed, indicating a possible difficulty in capturing the variability of human strategies. We therefore suggest to concentrate future research efforts on bridging the gap between human data, simulators and automatic evaluators in dialogue frameworks.

Thibault Cordier, Tanguy Urvoy, Fabrice Lefèvre et al.

Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. The dialogue manager must therefore be able to take into account domain changes and plan over different domains/tasks in order to deal with multidomain dialogues. However, learning with reinforcement in such context becomes difficult because the state-action dimension is larger while the reward signal remains scarce. Our experimental results suggest that structured policies based on graph neural networks combined with different degrees of imitation learning can effectively handle multi-domain dialogues. The reported experiments underline the benefit of structured policies over standard policies.

Quentin Brabant, Lina Maria Rojas-Barahona, Claire Gardent

In human conversations, ellipsis and coreference are commonly occurring linguistic phenomena. Although these phenomena are a mean of making human-machine conversations more fluent and natural, only few dialogue corpora contain explicit indications on which turns contain ellipses and/or coreferences. In this paper we address the task of automatically detecting ellipsis and coreferences in conversational question answering. We propose to use a multi-label classifier based on DistilBERT. Multi-label classification and active learning are employed to compensate the limited amount of labeled data. We show that these methods greatly enhance the performance of the classifier for detecting these phenomena on a manually labeled dataset.

Quentin Brabant, Gwenole Lecorve, Lina M. Rojas-Barahona et al.

We present KGConv, a large, conversational corpus of 71k conversations where each question-answer pair is grounded in a Wikidata fact. Conversations contain on average 8.6 questions and for each Wikidata fact, we provide multiple variants (12 on average) of the corresponding question using templates, human annotations, hand-crafted rules and a question rewriting neural model. We provide baselines for the task of Knowledge-Based, Conversational Question Generation. KGConv can further be used for other generation and analysis tasks such as single-turn question generation from Wikidata triples, question rewriting, question answering from conversation or from knowledge graphs and quiz generation.

Lucas Druart, Léo Jacqmin, Benoît Favre et al.

In Task-Oriented Dialogue (TOD) systems, correctly updating the system's understanding of the user's needs is key to a smooth interaction. Traditionally TOD systems are composed of several modules that interact with one another. While each of these components is the focus of active research communities, their behavior in interaction can be overlooked. This paper proposes a comprehensive analysis of the errors of state of the art systems in complex settings such as Dialogue State Tracking which highly depends on the dialogue context. Based on spoken MultiWoz, we identify that errors on non-categorical slots' values are essential to address in order to bridge the gap between spoken and chat-based dialogue systems. We explore potential solutions to improve transcriptions and help dialogue state tracking generative models correct such errors.

G. Charbel N. Kindji, Elisa Fromont, Lina Maria Rojas-Barahona et al.

Detecting synthetic tabular data is essential to prevent the distribution of false or manipulated datasets that could compromise data-driven decision-making. This study explores whether synthetic tabular data can be reliably identified across different tables. This challenge is unique to tabular data, where structures (such as number of columns, data types, and formats) can vary widely from one table to another. We propose four table-agnostic detectors combined with simple preprocessing schemes that we evaluate on six evaluation protocols, with different levels of ''wildness''. Our results show that cross-table learning on a restricted set of tables is possible even with naive preprocessing schemes. They confirm however that cross-table transfer (i.e. deployment on a table that has not been seen before) is challenging. This suggests that sophisticated encoding schemes are required to handle this problem.

Michelle Elizabeth, Morgan Veyret, Miguel Couceiro et al.

Large language models (LLMs) gained immense popularity due to their impressive capabilities in unstructured conversations. Empowering LLMs with advanced prompting strategies such as reasoning and acting (ReAct) (Yao et al., 2022) has shown promise in solving complex tasks traditionally requiring reinforcement learning. In this work, we apply the ReAct strategy to guide LLMs performing task-oriented dialogue (TOD). We evaluate ReAct-based LLMs (ReAct-LLMs) both in simulation and with real users. While ReAct-LLMs severely underperform state-of-the-art approaches on success rate in simulation, this difference becomes less pronounced in human evaluation. Moreover, compared to the baseline, humans report higher subjective satisfaction with ReAct-LLM despite its lower success rate, most likely thanks to its natural and confidently phrased responses.

Michelle Elizabeth, Alicja Kasicka, Natalia Krawczyk et al.

The growing number of generative AI-based dialogue systems has made their evaluation a crucial challenge. This paper presents our contribution to this important problem through the Dialogue System Technology Challenge (DSTC-12, Track 1), where we developed models to predict dialogue-level, dimension-specific scores. Given the constraint of using relatively small models (i.e. fewer than 13 billion parameters) our work follows two main strategies: employing Language Models (LMs) as evaluators through prompting, and training encoder-based classification and regression models. Our results show that while LM prompting achieves only modest correlations with human judgments, it still ranks second on the test set, outperformed only by the baseline. The regression and classification models, with significantly fewer parameters, demonstrate high correlation for some dimensions on the validation set. Although their performance decreases on the test set, it is important to note that the test set contains annotations with significantly different score ranges for some of the dimensions with respect to the train and validation sets.

G. Charbel N. Kindji, Elisa Fromont, Lina Maria Rojas-Barahona et al.

The rise of powerful generative models has sparked concerns over data authenticity. While detection methods have been extensively developed for images and text, the case of tabular data, despite its ubiquity, has been largely overlooked. Yet, detecting synthetic tabular data is especially challenging due to its heterogeneous structure and unseen formats at test time. We address the underexplored task of detecting synthetic tabular data in the wild, where tables have variable and previously unseen schemas. We introduce a novel datum-wise transformer architecture that significantly outperforms the only previously published baseline, improving both AUC and accuracy by 7 points. By incorporating a table-adaptation component, our model gains an additional 7 accuracy points, demonstrating enhanced robustness. This work provides the first strong evidence that detecting synthetic tabular data in real-world conditions is not only feasible, but can be done with high reliability.

G. Charbel N. Kindji, Elisa Fromont, Lina Maria Rojas-Barahona et al.

The growing power of generative models raises major concerns about the authenticity of published content. To address this problem, several synthetic content detection methods have been proposed for uniformly structured media such as image or text. However, little work has been done on the detection of synthetic tabular data, despite its importance in industry and government. This form of data is complex to handle due to the diversity of its structures: the number and types of the columns may vary wildly from one table to another. We tackle the tough problem of detecting synthetic tabular data ''in the wild'', i.e. when the model is deployed on table structures it has never seen before. We introduce a novel datum-wise transformer architecture and show that it outperforms existing models. Furthermore, we investigate the application of domain adaptation techniques to enhance the effectiveness of our model, thereby providing a more robust data-forgery detection solution.

G. Charbel N. Kindji, Lina Maria Rojas-Barahona, Elisa Fromont et al.

Detecting synthetic tabular data is essential to prevent the distribution of false or manipulated datasets that could compromise data-driven decision-making. This study explores whether synthetic tabular data can be reliably identified ''in the wild''-meaning across different generators, domains, and table formats. This challenge is unique to tabular data, where structures (such as number of columns, data types, and formats) can vary widely from one table to another. We propose three cross-table baseline detectors and four distinct evaluation protocols, each corresponding to a different level of ''wildness''. Our very preliminary results confirm that cross-table adaptation is a challenging task.

G. Charbel N. Kindji, Lina Maria Rojas-Barahona, Elisa Fromont et al.

The ability to train generative models that produce realistic, safe and useful tabular data is essential for data privacy, imputation, oversampling, explainability or simulation. However, generating tabular data is not straightforward due to its heterogeneity, non-smooth distributions, complex dependencies and imbalanced categorical features. Although diverse methods have been proposed in the literature, there is a need for a unified evaluation, under the same conditions, on a variety of datasets. This study addresses this need by fully considering the optimization of: hyperparameters, feature encodings, and architectures. We investigate the impact of dataset-specific tuning on five recent model families for tabular data generation through an extensive benchmark on 16 datasets. These datasets vary in terms of size (an average of 80,000 rows), data types, and domains. We also propose a reduced search space for each model that allows for quick optimization, achieving nearly equivalent performance at a significantly lower cost. Our benchmark demonstrates that, for most models, large-scale dataset-specific tuning substantially improves performance compared to the original configurations. Furthermore, we confirm that diffusion-based models generally outperform other models on tabular data. However, this advantage is not significant when the entire tuning and training process is restricted to the same GPU budget.

Juliette Faille, Quentin Brabant, Gwenole Lecorve et al.

We explore question generation in the context of knowledge-grounded dialogs focusing on explainability and evaluation. Inspired by previous work on planning-based summarisation, we present a model which instead of directly generating a question, sequentially predicts first a fact then a question. We evaluate our approach on 37k test dialogs adapted from the KGConv dataset and we show that, although more demanding in terms of inference, our approach performs on par with a standard model which solely generates a question while allowing for a detailed referenceless evaluation of the model behaviour in terms of relevance, factuality and pronominalisation.

Morgan Veyret, Jean-Baptiste Duchene, Kekeli Afonouvi et al.

Typically available dialogue frameworks have adopted a semantic representation based on dialogue-acts and slot-value pairs. Despite its simplicity, this representation has disadvantages such as the lack of expressivity, scalability and explainability. We present WEBDial: a dialogue framework that relies on a graph formalism by using RDF triples instead of slot-value pairs. We describe its overall architecture and the graph-based semantic representation. We show its applicability from simple to complex applications, by varying the complexity of domains and tasks: from single domain and tasks to multiple domains and complex tasks.

Jay Kejriwal, Stefan Benus, Lina M. Rojas-Barahona

Speakers tend to engage in adaptive behavior, known as entrainment, when they become similar to their interlocutor in various aspects of speaking. We present an unsupervised deep learning framework that derives meaningful representation from textual features for developing semantic entrainment. We investigate the model's performance by extracting features using different variations of the BERT model (DistilBERT and XLM-RoBERTa) and Google's universal sentence encoder (USE) embeddings on two human-human (HH) corpora (The Fisher Corpus English Part 1, Columbia games corpus) and one human-machine (HM) corpus (Voice Assistant Conversation Corpus (VACC)). In addition to semantic features we also trained DNN-based models utilizing two auditory embeddings (TRIpLet Loss network (TRILL) vectors, Low-level descriptors (LLD) features) and two units of analysis (Inter pausal unit and Turn). The results show that semantic entrainment can be assessed with our model, that models can distinguish between HH and HM interactions and that the two units of analysis for extracting acoustic features provide comparable findings.

Sebastien Montella, Lina Rojas-Barahona, Johannes Heinecke

Knowledge Graph (KG) completion has been excessively studied with a massive number of models proposed for the Link Prediction (LP) task. The main limitation of such models is their insensitivity to time. Indeed, the temporal aspect of stored facts is often ignored. To this end, more and more works consider time as a parameter to complete KGs. In this paper, we first demonstrate that, by simply increasing the number of negative samples, the recent AttH model can achieve competitive or even better performance than the state-of-the-art on Temporal KGs (TKGs), albeit its nontemporality. We further propose Hercules, a time-aware extension of AttH model, which defines the curvature of a Riemannian manifold as the product of both relation and time. Our experiments show that both Hercules and AttH achieve competitive or new state-of-the-art performances on ICEWS04 and ICEWS05-15 datasets. Therefore, one should raise awareness when learning TKGs representations to identify whether time truly boosts performances.

Lina M. Rojas-Barahona

The impact of user satisfaction in policy learning task-oriented dialogue systems has long been a subject of research interest. Most current models for estimating the user satisfaction either (i) treat out-of-context short-texts, such as product reviews, or (ii) rely on turn features instead of on distributed semantic representations. In this work we adopt deep neural networks that use distributed semantic representation learning for estimating the user satisfaction in conversations. We evaluate the impact of modelling context length in these networks. Moreover, we show that the proposed hierarchical network outperforms state-of-the-art quality estimators. Furthermore, we show that applying these networks to infer the reward function in a Partial Observable Markov Decision Process (POMDP) yields to a great improvement in the task success rate.

Sebastien Montella, Betty Fabre, Tanguy Urvoy et al.

The task of verbalization of RDF triples has known a growth in popularity due to the rising ubiquity of Knowledge Bases (KBs). The formalism of RDF triples is a simple and efficient way to store facts at a large scale. However, its abstract representation makes it difficult for humans to interpret. For this purpose, the WebNLG challenge aims at promoting automated RDF-to-text generation. We propose to leverage pre-trainings from augmented data with the Transformer model using a data augmentation strategy. Our experiment results show a minimum relative increases of 3.73%, 126.05% and 88.16% in BLEU score for seen categories, unseen entities and unseen categories respectively over the standard training.

Thibault Cordier, Tanguy Urvoy, Lina M. Rojas-Barahona et al.

A learning dialogue agent can infer its behaviour from interactions with the users. These interactions can be taken from either human-to-human or human-machine conversations. However, human interactions are scarce and costly, making learning from few interactions essential. One solution to speedup the learning process is to guide the agent's exploration with the help of an expert. We present in this paper several imitation learning strategies for dialogue policy where the guiding expert is a near-optimal handcrafted policy. We incorporate these strategies with state-of-the-art reinforcement learning methods based on Q-learning and actor-critic. We notably propose a randomised exploration policy which allows for a seamless hybridisation of the learned policy and the expert. Our experiments show that our hybridisation strategy outperforms several baselines, and that it can accelerate the learning when facing real humans.

Lina M. Rojas-Barahona, Pascal Bellec, Benoit Besset et al.

We present a spoken conversational question answering proof of concept that is able to answer questions about general knowledge from Wikidata. The dialogue component does not only orchestrate various components but also solve coreferences and ellipsis.

Stefan Ultes, Paweł\ Budzianowski, Iñigo Casanueva et al.

Statistical spoken dialogue systems usually rely on a single- or multi-domain dialogue model that is restricted in its capabilities of modelling complex dialogue structures, e.g., relations. In this work, we propose a novel dialogue model that is centred around entities and is able to model relations as well as multiple entities of the same type. We demonstrate in a prototype implementation benefits of relation modelling on the dialogue level and show that a trained policy using these relations outperforms the multi-domain baseline. Furthermore, we show that by modelling the relations on the dialogue level, the system is capable of processing relations present in the user input and even learns to address them in the system response.

Lina Rojas-Barahona, Bo-Hsiang Tseng, Yinpei Dai et al.

In recent years, we have seen deep learning and distributed representations of words and sentences make impact on a number of natural language processing tasks, such as similarity, entailment and sentiment analysis. Here we introduce a new task: understanding of mental health concepts derived from Cognitive Behavioural Therapy (CBT). We define a mental health ontology based on the CBT principles, annotate a large corpus where this phenomena is exhibited and perform understanding using deep learning and distributed representations. Our results show that the performance of deep learning models combined with word embeddings or sentence embeddings significantly outperform non-deep-learning models in this difficult task. This understanding module will be an essential component of a statistical dialogue system delivering therapy.

Lina M. Rojas-Barahona, Stefan Ultes, Pawel Budzianowski et al.

This paper presents two ways of dealing with scarce data in semantic decoding using N-Best speech recognition hypotheses. First, we learn features by using a deep learning architecture in which the weights for the unknown and known categories are jointly optimised. Second, an unsupervised method is used for further tuning the weights. Sharing weights injects prior knowledge to unknown categories. The unsupervised tuning (i.e. the risk minimisation) improves the F-Measure when recognising nearly zero-shot data on the DSTC3 corpus. This unsupervised method can be applied subject to two assumptions: the rank of the class marginal is assumed to be known and the class-conditional scores of the classifier are assumed to follow a Gaussian distribution.

Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su et al.

Reinforcement learning (RL) is a promising approach to solve dialogue policy optimisation. Traditional RL algorithms, however, fail to scale to large domains due to the curse of dimensionality. We propose a novel Dialogue Management architecture, based on Feudal RL, which decomposes the decision into two steps; a first step where a master policy selects a subset of primitive actions, and a second step where a primitive action is chosen from the selected subset. The structural information included in the domain ontology is used to abstract the dialogue state space, taking the decisions at each step using different parts of the abstracted state. This, combined with an information sharing mechanism between slots, increases the scalability to large domains. We show that an implementation of this approach, based on Deep-Q Networks, significantly outperforms previous state of the art in several dialogue domains and environments, without the need of any additional reward signal.

Iñigo Casanueva, Paweł Budzianowski, Pei-Hao Su et al.

Dialogue assistants are rapidly becoming an indispensable daily aid. To avoid the significant effort needed to hand-craft the required dialogue flow, the Dialogue Management (DM) module can be cast as a continuous Markov Decision Process (MDP) and trained through Reinforcement Learning (RL). Several RL models have been investigated over recent years. However, the lack of a common benchmarking framework makes it difficult to perform a fair comparison between different models and their capability to generalise to different environments. Therefore, this paper proposes a set of challenging simulated environments for dialogue model development and evaluation. To provide some baselines, we investigate a number of representative parametric algorithms, namely deep reinforcement learning algorithms - DQN, A2C and Natural Actor-Critic and compare them to a non-parametric model, GP-SARSA. Both the environments and policy models are implemented using the publicly available PyDial toolkit and released on-line, in order to establish a testbed framework for further experiments and to facilitate experimental reproducibility.

Stefan Ultes, Paweł Budzianowski, Iñigo Casanueva et al.

Reinforcement learning is widely used for dialogue policy optimization where the reward function often consists of more than one component, e.g., the dialogue success and the dialogue length. In this work, we propose a structured method for finding a good balance between these components by searching for the optimal reward component weighting. To render this search feasible, we use multi-objective reinforcement learning to significantly reduce the number of training dialogues required. We apply our proposed method to find optimized component weights for six domains and compare them to a default baseline.

Paweł Budzianowski, Stefan Ultes, Pei-Hao Su et al.

Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcement learning methods do not provide an efficient framework for modelling such dialogues. In this paper, we focus on the under-explored problem of multi-domain dialogue management. First, we propose a new method for hierarchical reinforcement learning using the option framework. Next, we show that the proposed architecture learns faster and arrives at a better policy than the existing flat ones do. Moreover, we show how pretrained policies can be adapted to more complex systems with an additional set of new actions. In doing that, we show that our approach has the potential to facilitate policy optimisation for more sophisticated multi-domain dialogue systems.

Milica Gasic, Nikola Mrksic, Lina M. Rojas-Barahona et al.

Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they have many benefits. By using speech as the primary communication medium, a computer interface can facilitate swift, human-like acquisition of information. In recent years, speech interfaces have become ever more popular, as is evident from the rise of personal assistants such as Siri, Google Now, Cortana and Amazon Alexa. Recently, data-driven machine learning methods have been applied to dialogue modelling and the results achieved for limited-domain applications are comparable to or outperform traditional approaches. Methods based on Gaussian processes are particularly effective as they enable good models to be estimated from limited training data. Furthermore, they provide an explicit estimate of the uncertainty which is particularly useful for reinforcement learning. This article explores the additional steps that are necessary to extend these methods to model multiple dialogue domains. We show that Gaussian process reinforcement learning is an elegant framework that naturally supports a range of methods, including prior knowledge, Bayesian committee machines and multi-agent learning, for facilitating extensible and adaptable dialogue systems.

Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic et al.

Recently a variety of LSTM-based conditional language models (LM) have been applied across a range of language generation tasks. In this work we study various model architectures and different ways to represent and aggregate the source information in an end-to-end neural dialogue system framework. A method called snapshot learning is also proposed to facilitate learning from supervised sequential signals by applying a companion cross-entropy objective function to the conditioning vector. The experimental and analytical results demonstrate firstly that competition occurs between the conditioning vector and the LM, and the differing architectures provide different trade-offs between the two. Secondly, the discriminative power and transparency of the conditioning vector is key to providing both model interpretability and better performance. Thirdly, snapshot learning leads to consistent performance improvements independent of which architecture is used.

Pei-Hao Su, Milica Gasic, Nikola Mrksic et al.

We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then continuously improve its behaviour via reinforcement learning, all using gradient-based algorithms on one single model. The experiments demonstrate the supervised model's effectiveness in the corpus-based evaluation, with user simulation, and with paid human subjects. The use of reinforcement learning further improves the model's performance in both interactive settings, especially under higher-noise conditions.

Pei-Hao Su, Milica Gasic, Nikola Mrksic et al.

The ability to compute an accurate reward function is essential for optimising a dialogue policy via reinforcement learning. In real-world applications, using explicit user feedback as the reward signal is often unreliable and costly to collect. This problem can be mitigated if the user's intent is known in advance or data is available to pre-train a task success predictor off-line. In practice neither of these apply for most real world applications. Here we propose an on-line learning framework whereby the dialogue policy is jointly trained alongside the reward model via active learning with a Gaussian process model. This Gaussian process operates on a continuous space dialogue representation generated in an unsupervised fashion using a recurrent neural network encoder-decoder. The experimental results demonstrate that the proposed framework is able to significantly reduce data annotation costs and mitigate noisy user feedback in dialogue policy learning.

Tsung-Hsien Wen, David Vandyke, Nikola Mrksic et al.

Teaching machines to accomplish tasks by conversing naturally with humans is challenging. Currently, developing task-oriented dialogue systems requires creating multiple components and typically this involves either a large amount of handcrafting, or acquiring costly labelled datasets to solve a statistical learning problem for each component. In this work we introduce a neural network-based text-in, text-out end-to-end trainable goal-oriented dialogue system along with a new way of collecting dialogue data based on a novel pipe-lined Wizard-of-Oz framework. This approach allows us to develop dialogue systems easily and without making too many assumptions about the task at hand. The results show that the model can converse with human subjects naturally whilst helping them to accomplish tasks in a restaurant search domain.

Tsung-Hsien Wen, Milica Gasic, Nikola Mrksic et al.

Moving from limited-domain natural language generation (NLG) to open domain is difficult because the number of semantic input combinations grows exponentially with the number of domains. Therefore, it is important to leverage existing resources and exploit similarities between domains to facilitate domain adaptation. In this paper, we propose a procedure to train multi-domain, Recurrent Neural Network-based (RNN) language generators via multiple adaptation steps. In this procedure, a model is first trained on counterfeited data synthesised from an out-of-domain dataset, and then fine tuned on a small set of in-domain utterances with a discriminative objective function. Corpus-based evaluation results show that the proposed procedure can achieve competitive performance in terms of BLEU score and slot error rate while significantly reducing the data needed to train generators in new, unseen domains. In subjective testing, human judges confirm that the procedure greatly improves generator performance when only a small amount of data is available in the domain.

Nikola Mrkšić, Diarmuid Ó Séaghdha, Blaise Thomson et al.

In this work, we present a novel counter-fitting method which injects antonymy and synonymy constraints into vector space representations in order to improve the vectors' capability for judging semantic similarity. Applying this method to publicly available pre-trained word vectors leads to a new state of the art performance on the SimLex-999 dataset. We also show how the method can be used to tailor the word vector space for the downstream task of dialogue state tracking, resulting in robust improvements across different dialogue domains.