Task-oriented dialogue (TOD) systems function as digital assistants, guiding users through various tasks such as booking flights or finding restaurants. Existing toolkits for building TOD systems often fall short in delivering comprehensive arrays of data, model, and experimental environments with a user-friendly experience. We introduce ConvLab-3: a multifaceted dialogue system toolkit crafted to bridge this gap. Our unified data format simplifies the integration of diverse datasets and models, significantly reducing complexity and cost for studying generalization and transfer. Enhanced with robust reinforcement learning (RL) tools, featuring a streamlined training process, in-depth evaluation tools, and a selection of user simulators, ConvLab-3 supports the rapid development and evaluation of robust dialogue policies. Through an extensive study, we demonstrate the efficacy of transfer learning and RL and showcase that ConvLab-3 is not only a powerful tool for seasoned researchers but also an accessible platform for newcomers.
Emotion recognition in conversations (ERC) is a crucial task for building human-like conversational agents. While substantial efforts have been devoted to ERC for chit-chat dialogues, the task-oriented counterpart is largely left unattended. Directly applying chit-chat ERC models to task-oriented dialogues (ToDs) results in suboptimal performance as these models overlook key features such as the correlation between emotions and task completion in ToDs. In this paper, we propose a framework that turns a chit-chat ERC model into a task-oriented one, addressing three critical aspects: data, features and objective. First, we devise two ways of augmenting rare emotions to improve ERC performance. Second, we use dialogue states as auxiliary features to incorporate key information from the goal of the user. Lastly, we leverage a multi-aspect emotion definition in ToDs to devise a multi-task learning objective and a novel emotion-distance weighted loss function. Our framework yields significant improvements for a range of chit-chat ERC models on EmoWOZ, a large-scale dataset for user emotions in ToDs. We further investigate the generalisability of the best resulting model to predict user satisfaction in different ToD datasets. A comparison with supervised baselines shows a strong zero-shot capability, highlighting the potential usage of our framework in wider scenarios.
Recent research on dialog state tracking (DST) focuses on methods that allow few- and zero-shot transfer to new domains or schemas. However, performance gains heavily depend on aggressive data augmentation and fine-tuning of ever larger language model based architectures. In contrast, general purpose language models, trained on large amounts of diverse data, hold the promise of solving any kind of task without task-specific training. We present preliminary experimental results on the ChatGPT research preview, showing that ChatGPT achieves state-of-the-art performance in zero-shot DST. Despite our findings, we argue that properties inherent to general purpose models limit their ability to replace specialized systems. We further theorize that the in-context learning capabilities of such models will likely become powerful tools to support the development of dedicated dialog state trackers and enable dynamic methods.
Continual learning is one of the key components of human learning and a necessary requirement of artificial intelligence. As dialogue can potentially span infinitely many topics and tasks, a task-oriented dialogue system must have the capability to continually learn, dynamically adapting to new challenges while preserving the knowledge it already acquired. Despite the importance, continual reinforcement learning of the dialogue policy has remained largely unaddressed. The lack of a framework with training protocols, baseline models and suitable metrics, has so far hindered research in this direction. In this work we fill precisely this gap, enabling research in dialogue policy optimisation to go from static to dynamic learning. We provide a continual learning algorithm, baseline architectures and metrics for assessing continual learning models. Moreover, we propose the dynamic dialogue policy transformer (DDPT), a novel dynamic architecture that can integrate new knowledge seamlessly, is capable of handling large state spaces and obtains significant zero-shot performance when being exposed to unseen domains, without any growth in network parameter size. We validate the strengths of DDPT in simulation with two user simulators as well as with humans.
The ability to recognise emotions lends a conversational artificial intelligence a human touch. While emotions in chit-chat dialogues have received substantial attention, emotions in task-oriented dialogues remain largely unaddressed. This is despite emotions and dialogue success having equally important roles in a natural system. Existing emotion-annotated task-oriented corpora are limited in size, label richness, and public availability, creating a bottleneck for downstream tasks. To lay a foundation for studies on emotions in task-oriented dialogues, we introduce EmoWOZ, a large-scale manually emotion-annotated corpus of task-oriented dialogues. EmoWOZ is based on MultiWOZ, a multi-domain task-oriented dialogue dataset. It contains more than 11K dialogues with more than 83K emotion annotations of user utterances. In addition to Wizard-of-Oz dialogues from MultiWOZ, we collect human-machine dialogues within the same set of domains to sufficiently cover the space of various emotions that can happen during the lifetime of a data-driven dialogue system. To the best of our knowledge, this is the first large-scale open-source corpus of its kind. We propose a novel emotion labelling scheme, which is tailored to task-oriented dialogues. We report a set of experimental results to show the usability of this corpus for emotion recognition and state tracking in task-oriented dialogues.
User simulators (USs) are commonly used to train task-oriented dialogue systems via reinforcement learning. The interactions often take place on semantic level for efficiency, but there is still a gap from semantic actions to natural language, which causes a mismatch between training and deployment environment. Incorporating a natural language generation (NLG) module with USs during training can partly deal with this problem. However, since the policy and NLG of USs are optimised separately, these simulated user utterances may not be natural enough in a given context. In this work, we propose a generative transformer-based user simulator (GenTUS). GenTUS consists of an encoder-decoder structure, which means it can optimise both the user policy and natural language generation jointly. GenTUS generates both semantic actions and natural language utterances, preserving interpretability and enhancing language variation. In addition, by representing the inputs and outputs as word sequences and by using a large pre-trained language model we can achieve generalisability in feature representation. We evaluate GenTUS with automatic metrics and human evaluation. Our results show that GenTUS generates more natural language and is able to transfer to an unseen ontology in a zero-shot fashion. In addition, its behaviour can be further shaped with reinforcement learning opening the door to training specialised user simulators.
Task-oriented dialogue systems aim to fulfill user goals through natural language interactions. They are ideally evaluated with human users, which however is unattainable to do at every iteration of the development phase. Simulated users could be an alternative, however their development is nontrivial. Therefore, researchers resort to offline metrics on existing human-human corpora, which are more practical and easily reproducible. They are unfortunately limited in reflecting real performance of dialogue systems. BLEU for instance is poorly correlated with human judgment, and existing corpus-based metrics such as success rate overlook dialogue context mismatches. There is still a need for a reliable metric for task-oriented systems with good generalization and strong correlation with human judgements. In this paper, we propose the use of offline reinforcement learning for dialogue evaluation based on static data. Such an evaluator is typically called a critic and utilized for policy optimization. We go one step further and show that offline RL critics can be trained for any dialogue system as external evaluators, allowing dialogue performance comparisons across various types of systems. This approach has the benefit of being corpus- and model-independent, while attaining strong correlation with human judgements, which we confirm via an interactive user trial.
Goal oriented dialogue systems were originally designed as a natural language interface to a fixed data-set of entities that users might inquire about, further described by domain, slots and values. As we move towards adaptable dialogue systems where knowledge about domains, slots and values may change, there is an increasing need to automatically extract these terms from raw dialogues or related non-dialogue data on a large scale. In this paper, we take an important step in this direction by exploring different features that can enable systems to discover realisations of domains, slots and values in dialogues in a purely data-driven fashion. The features that we examine stem from word embeddings, language modelling features, as well as topological features of the word embedding space. To examine the utility of each feature set, we train a seed model based on the widely used MultiWOZ data-set. Then, we apply this model to a different corpus, the Schema-guided dialogue data-set. Our method outperforms the previously proposed approach that relies solely on word embeddings. We also demonstrate that each of the features is responsible for discovering different kinds of content. We believe our results warrant further research towards ontology induction, and continued harnessing of topological data analysis for dialogue and natural language processing research.
Generalizing dialogue state tracking (DST) to new data is especially challenging due to the strong reliance on abundant and fine-grained supervision during training. Sample sparsity, distributional shift, and the occurrence of new concepts and topics frequently lead to severe performance degradation during inference. In this paper we propose a training strategy to build extractive DST models without the need for fine-grained manual span labels. Two novel input-level dropout methods mitigate the negative impact of sample sparsity. We propose a new model architecture with a unified encoder that supports value as well as slot independence by leveraging the attention mechanism. We combine the strengths of triple copy strategy DST and value matching to benefit from complementary predictions without violating the principle of ontology independence. Our experiments demonstrate that an extractive DST model can be trained without manual span labels. Our architecture and training strategies improve robustness towards sample sparsity, new concepts, and topics, leading to state-of-the-art performance on a range of benchmarks. We further highlight our model’s ability to effectively learn from non-dialogue data.
Dialogue policy optimisation via reinforcement learning requires a large number of training interactions, which makes learning with real users time consuming and expensive. Many set-ups therefore rely on a user simulator instead of humans. These user simulators have their own problems. While hand-coded, rule-based user simulators have been shown to be sufficient in small, simple domains, for complex domains the number of rules quickly becomes intractable. State-of-the-art data-driven user simulators, on the other hand, are still domain-dependent. This means that adaptation to each new domain requires redesigning and retraining. In this work, we propose a domain-independent transformer-based user simulator (TUS). The structure of TUS is not tied to a specific domain, enabling domain generalization and the learning of cross-domain user behaviour from data. We compare TUS with the state-of-the-art using automatic as well as human evaluations. TUS can compete with rule-based user simulators on pre-defined domains and is able to generalize to unseen domains in a zero-shot fashion.
The ability to identify and resolve uncertainty is crucial for the robustness of a dialogue system. Indeed, this has been confirmed empirically on systems that utilise Bayesian approaches to dialogue belief tracking. However, such systems consider only confidence estimates and have difficulty scaling to more complex settings. Neural dialogue systems, on the other hand, rarely take uncertainties into account. They are therefore overconfident in their decisions and less robust. Moreover, the performance of the tracking task is often evaluated in isolation, without consideration of its effect on the downstream policy optimisation. We propose the use of different uncertainty measures in neural belief tracking. The effects of these measures on the downstream task of policy optimisation are evaluated by adding selected measures of uncertainty to the feature space of the policy and training policies through interaction with a user simulator. Both human and simulated user results show that incorporating these measures leads to improvements both of the performance and of the robustness of the downstream dialogue policy. This highlights the importance of developing neural dialogue belief trackers that take uncertainty into account.
Reinforcement learning (RL) can enable task-oriented dialogue systems to steer the conversation towards successful task completion. In an end-to-end setting, a response can be constructed in a word-level sequential decision making process with the entire system vocabulary as action space. Policies trained in such a fashion do not require expert-defined action spaces, but they have to deal with large action spaces and long trajectories, making RL impractical. Using the latent space of a variational model as action space alleviates this problem. However, current approaches use an uninformed prior for training and optimize the latent distribution solely on the context. It is therefore unclear whether the latent representation truly encodes the characteristics of different actions. In this paper, we explore three ways of leveraging an auxiliary task to shape the latent variable distribution: via pre-training, to obtain an informed prior, and via multitask learning. We choose response auto-encoding as the auxiliary task, as this captures the generative factors of dialogue responses while requiring low computational cost and neither additional data nor labels. Our approach yields a more action-characterized latent representations which support end-to-end dialogue policy optimization and achieves state-of-the-art success rates. These results warrant a more wide-spread use of RL in end-to-end dialogue models.
Dialog state tracking (DST) suffers from severe data sparsity. While many natural language processing (NLP) tasks benefit from transfer learning and multi-task learning, in dialog these methods are limited by the amount of available data and by the specificity of dialog applications. In this work, we successfully utilize non-dialog data from unrelated NLP tasks to train dialog state trackers. This opens the door to the abundance of unrelated NLP corpora to mitigate the data sparsity issue inherent to DST.
The ability to accurately track what happens during a conversation is essential for the performance of a dialogue system. Current state-of-the-art multi-domain dialogue state trackers achieve just over 55% accuracy on the current go-to benchmark, which means that in almost every second dialogue turn they place full confidence in an incorrect dialogue state. Belief trackers, on the other hand, maintain a distribution over possible dialogue states. However, they lack in performance compared to dialogue state trackers, and do not produce well calibrated distributions. In this work we present state-of-the-art performance in calibration for multi-domain dialogue belief trackers using a calibrated ensemble of models. Our resulting dialogue belief tracker also outperforms previous dialogue belief tracking models in terms of accuracy.
Task-oriented dialog systems rely on dialog state tracking (DST) to monitor the user’s goal during the course of an interaction. Multi-domain and open-vocabulary settings complicate the task considerably and demand scalable solutions. In this paper we present a new approach to DST which makes use of various copy mechanisms to fill slots with values. Our model has no need to maintain a list of candidate values. Instead, all values are extracted from the dialog context on-the-fly. A slot is filled by one of three copy mechanisms: (1) Span prediction may extract values directly from the user input; (2) a value may be copied from a system inform memory that keeps track of the system’s inform operations (3) a value may be copied over from a different slot that is already contained in the dialog state to resolve coreferences within and across domains. Our approach combines the advantages of span-based slot filling methods with memory methods to avoid the use of value picklists altogether. We argue that our strategy simplifies the DST task while at the same time achieving state of the art performance on various popular evaluation sets including Multiwoz 2.1, where we achieve a joint goal accuracy beyond 55%.
This paper describes our German, Italian and English Speech-to-Text (STT) systems for the 2014 IWSLT TED ASR track. Our setup uses ROVER and confusion network combination from various subsystems to achieve a good overall performance. The individual subsystems are built by using different front-ends, (e.g., MVDR-MFCC or lMel), acoustic models (GMM or modular DNN) and phone sets and by training on various subsets of the training data. Decoding is performed in two stages, where the GMM systems are adapted in an unsupervised manner on the combination of the first stage outputs using VTLN, MLLR, and cMLLR. The combination setup produces a final hypothesis that has a significantly lower WER than any of the individual subsystems.
This paper describes our English Speech-to-Text (STT) systems for the 2013 IWSLT TED ASR track. The systems consist of multiple subsystems that are combinations of different front-ends, e.g. MVDR-MFCC based and lMel based ones, GMM and NN acoustic models and different phone sets. The outputs of the subsystems are combined via confusion network combination. Decoding is done in two stages, where the systems of the second stage are adapted in an unsupervised manner on the combination of the first stage outputs using VTLN, MLLR, and cMLLR.
In this paper we describe our work on unsupervised adaptation of the acoustic model of our simultaneous lecture translation system. We trained a speaker independent acoustic model, with which we produce automatic transcriptions of new lectures in order to improve the system for a specific lecturer. We compare our results against a model that was trained in a supervised way on an exact manual transcription. We examine four different ways of processing the decoder outputs of the automatic transcription with respect to the treatment of pronunciation variants and noise words. We will show that, instead of fixating the latter informations in the transcriptions, it is of advantage to let the Viterbi algorithm during training decide which pronunciations to use and where to insert which noise words. Further, we utilize word level posterior probabilities obtained during decoding by weighting and thresholding the words of a transcription.
This paper describes our English Speech-to-Text (STT) systems for the 2012 IWSLT TED ASR track evaluation. The systems consist of 10 subsystems that are combinations of different front-ends, e.g. MVDR based and MFCC based ones, and two different phone sets. The outputs of the subsystems are combined via confusion network combination. Decoding is done in two stages, where the systems of the second stage are adapted in an unsupervised manner on the combination of the first stage outputs using VTLN, MLLR, and cM-LLR.
This paper describes the KIT-NAIST (Contrastive) English speech recognition system for the IWSLT 2012 Evaluation Campaign. In particular, we participated in the ASR track of the IWSLT TED task. The system was developed by Karlsruhe Institute of Technology (KIT) and Nara Institute of Science and Technology (NAIST) teams in collaboration within the interACT project. We employ single system decoding with fully continuous and semi-continuous models, as well as a three-stage, multipass system combination framework built with the Janus Recognition Toolkit. On the IWSLT 2010 test set our single system introduced in this work achieves a WER of 17.6%, and our final combination achieves a WER of 14.4%.