Related papers: Guider l'attention dans les modeles de sequence a …

Multistep traffic forecasting on road networks is a crucial task in successful intelligent transportation system applications. To capture the complex non-stationary temporal dynamics and spatial dependency in multistep traffic-condition…

We introduce a novel approach to transformers that learns hierarchical representations in multiparty dialogue. First, three language modeling tasks are used to pre-train the transformers, token- and utterance-level language modeling and…

We introduce Language World Models, a class of language-conditional generative model which interpret natural language messages by predicting latent codes of future observations. This provides a visual grounding of the message, similar to an…

QA models based on pretrained language mod-els have achieved remarkable performance on various benchmark datasets.However, QA models do not generalize well to unseen data that falls outside the training distribution, due to distributional…

We investigate how encoder-decoder models trained on a synthetic dataset of task-oriented dialogues process disfluencies, such as hesitations and self-corrections. We find that, contrary to earlier results, disfluencies have very little…

Dialogue act recognition is an important part of natural language understanding. We investigate the way dialogue act corpora are annotated and the learning approaches used so far. We find that the dialogue act is context-sensitive within…

Attention mechanism has been used as an ancillary means to help RNN or CNN. However, the Transformer (Vaswani et al., 2017) recently recorded the state-of-the-art performance in machine translation with a dramatic reduction in training time…

While end-to-end neural conversation models have led to promising advances in reducing hand-crafted features and errors induced by the traditional complex system architecture, they typically require an enormous amount of data due to the…

A key challenge of dialog systems research is to effectively and efficiently adapt to new domains. A scalable paradigm for adaptation necessitates the development of generalizable models that perform well in few-shot settings. In this…

Obtaining accurate information about future traffic flows of all links in a traffic network is of great importance for traffic management and control applications. This research studies two particular problems in traffic forecasting: (1)…

The attention model has become a standard component in neural machine translation (NMT) and it guides translation process by selectively focusing on parts of the source sentence when predicting each target word. However, we find that the…

In human dialogue, nonverbal information such as nodding and facial expressions is as crucial as verbal information, and spoken dialogue systems are also expected to express such nonverbal behaviors. We focus on nodding, which is critical…

While most conversational AI systems focus on textual dialogue only, conditioning utterances on visual context (when it's available) can lead to more realistic conversations. Unfortunately, a major challenge for incorporating visual context…

Attention-based sequence-to-sequence models have shown promising results in automatic speech recognition. Using these architectures, one-dimensional input and output sequences are related by an attention approach, thereby replacing more…

Recent advances in deep neural networks, language modeling and language generation have introduced new ideas to the field of conversational agents. As a result, deep neural models such as sequence-to-sequence, Memory Networks, and the…

Word segmentation, the problem of finding word boundaries in speech, is of interest for a range of tasks. Previous papers have suggested that for sequence-to-sequence models trained on tasks such as speech translation or speech recognition,…

Paraphasias are speech errors that are often characteristic of aphasia and they represent an important signal in assessing disease severity and subtype. Traditionally, clinicians manually identify paraphasias by transcribing and analyzing…

Learning an effective speaker representation is crucial for achieving reliable performance in speaker verification tasks. Speech signals are high-dimensional, long, and variable-length sequences containing diverse information at each…

There are many settings where it is useful to predict and explain the success or failure of a dialogue. Circumplex theory from psychology models the social orientations (e.g., Warm-Agreeable, Arrogant-Calculating) of conversation…

Predicting human interaction is challenging as the on-going activity has to be inferred based on a partially observed video. Essentially, a good algorithm should effectively model the mutual influence between the two interacting subjects.…