Related papers: Representation Learning for Conversational Data us…

Pre-trained large language models have recently achieved ground-breaking performance in a wide variety of language understanding tasks. However, the same model can not be applied to multimodal behavior understanding tasks (e.g., video…

Sequence-to-sequence neural network models for generation of conversational responses tend to generate safe, commonplace responses (e.g., "I don't know") regardless of the input. We suggest that the traditional objective function, i.e., the…

Learning good representations is of crucial importance in deep learning. Mutual Information (MI) or similar measures of statistical dependence are promising tools for learning these representations in an unsupervised way. Even though the…

Responsing with image has been recognized as an important capability for an intelligent conversational agent. Yet existing works only focus on exploring the multimodal dialogue models which depend on retrieval-based methods, but neglecting…

Multi-role dialogue understanding comprises a wide range of diverse tasks such as question answering, act classification, dialogue summarization etc. While dialogue corpora are abundantly available, labeled data, for specific learning…

Recent advances in pre-trained language models have significantly improved neural response generation. However, existing methods usually view the dialogue context as a linear sequence of tokens and learn to generate the next word through…

Existing studies on self-supervised speech representation learning have focused on developing new training methods and applying pre-trained models for different applications. However, the quality of these models is often measured by the…

We show state-of-the-art word representation learning methods maximize an objective function that is a lower bound on the mutual information between different parts of a word sequence (i.e., a sentence). Our formulation provides an…

Many recent methods for unsupervised or self-supervised representation learning train feature extractors by maximizing an estimate of the mutual information (MI) between different views of the data. This comes with several immediate…

With the development of pre-trained language models, remarkable success has been witnessed in dialogue understanding (DU). However, current DU approaches usually employ independent models for each distinct DU task without considering shared…

The predominant approach to open-domain dialog generation relies on end-to-end training of neural models on chat datasets. However, this approach provides little insight as to what these models learn (or do not learn) about engaging in…

Building robust and general dialogue models for spoken conversations is challenging due to the gap in distributions of spoken and written data. This paper presents our approach to build generalized models for the Knowledge-grounded…

Training machines to understand natural language and interact with humans is one of the major goals of artificial intelligence. Recent years have witnessed an evolution from matching networks to pre-trained language models (PrLMs). In…

Multi-party dialogues are more difficult for models to understand than one-to-one two-party dialogues, since they involve multiple interlocutors, resulting in interweaving reply-to relations and information flows. To step over these…

Discourse analysis is an important task because it models intrinsic semantic structures between sentences in a document. Discourse markers are natural representations of discourse in our daily language. One challenge is that the markers as…

Current language models are usually trained using a self-supervised scheme, where the main focus is learning representations at the word or sentence level. However, there has been limited progress in generating useful discourse-level…

We propose learning discrete structured representations from unlabeled data by maximizing the mutual information between a structured latent variable and a target variable. Calculating mutual information is intractable in this setting. Our…

Recent literature shows that large-scale language modeling provides excellent reusable sentence representations with both recurrent and self-attentive architectures. However, there has been less clarity on the commonalities and differences…

In this paper, we investigate the problem of learning disentangled representations. Given a pair of images sharing some attributes, we aim to create a low-dimensional representation which is split into two parts: a shared representation…

Multi-modal dialog modeling is of growing interest. In this work, we propose frameworks to resolve a specific case of multi-modal dialog generation that better mimics multi-modal dialog generation in the real world, where each dialog turn…