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.

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, 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.

Lina M. Rojas-Barahona

In this dissertation I would like to guide the reader to the research on dialogue but more precisely the research I have conducted during my career since my PhD thesis. Starting from modular architectures with machine learning/deep learning and reinforcement learning to end-to-end deep neural networks. Besides my work as research associate, I also present the work I have supervised in the last years. I review briefly the state of the art and highlight the open research problems on conversational agents. Afterwards, I present my contribution to Task-Oriented Dialogues (TOD), both as research associate and as the industrial supervisor of CIFRE theses. I discuss conversational QA. Particularly, I present the work of two PhD candidates Thibault Cordier and Sebastien Montella; as well as the work of the young researcher Quentin Brabant. Finally, I present the scientific project, where I discuss about Large Language Models (LLMs) for Task-Oriented Dialogue and Multimodal Task-Oriented Dialogue.

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.

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.

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.

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.

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.

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.

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.