Related papers: Context-Aware Sequence-to-Sequence Models for Conv…
Impressive milestones have been achieved in text matching by adopting a cross-attention mechanism to capture pertinent semantic connections between two sentence representations. However, regular cross-attention focuses on word-level links…
How can we better understand the mechanisms behind multi-turn information seeking dialogues? How can we use these insights to design a dialogue system that does not require explicit query formulation upfront as in question answering? To…
In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via…
Multiturn dialogue models aim to generate human-like responses by leveraging conversational context, consisting of utterances from previous exchanges. Existing methods often neglect the interactions between these utterances or treat all of…
An important task for the design of Question Answering systems is the selection of the sentence containing (or constituting) the answer from documents relevant to the asked question. Most previous work has only used the target sentence to…
In this paper, we describe the use of recurrent neural networks to capture sequential information from the self-attention representations to improve the Transformers. Although self-attention mechanism provides a means to exploit long…
Sequences have become first class citizens in supervised learning thanks to the resurgence of recurrent neural networks. Many complex tasks that require mapping from or to a sequence of observations can now be formulated with the…
This paper presents our latest investigations on dialog act (DA) classification on automatically generated transcriptions. We propose a novel approach that combines convolutional neural networks (CNNs) and conditional random fields (CRFs)…
Conversational speech, while being unstructured at an utterance level, typically has a macro topic which provides larger context spanning multiple utterances. The current language models in speech recognition systems using recurrent neural…
Recent advances in text-to-speech have significantly improved the expressiveness of synthesized speech. However, it is still challenging to generate speech with contextually appropriate and coherent speaking style for multi-sentence text in…
We investigate the task of modeling open-domain, multi-turn, unstructured, multi-participant, conversational dialogue. We specifically study the effect of incorporating different elements of the conversation. Unlike previous efforts, which…
Open-domain multi-turn conversations mainly have three features, which are hierarchical semantic structure, redundant information, and long-term dependency. Grounded on these, selecting relevant context becomes a challenge step for…
We envisage future context-aware applications will dynamically adapt their behaviors to various context data from sources in wide-area networks, such as the Internet. Facing the changing context and the sheer number of context sources, a…
In multi-turn dialogue generation, response is usually related with only a few contexts. Therefore, an ideal model should be able to detect these relevant contexts and produce a suitable response accordingly. However, the widely used…
Conversational text-to-SQL aims at converting multi-turn natural language queries into their corresponding SQL (Structured Query Language) representations. One of the most intractable problems of conversational text-to-SQL is modelling the…
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…
Sequence-to-sequence (Seq2seq) models have played an important role in the recent success of various natural language processing methods, such as machine translation, text summarization, and speech recognition. However, current Seq2seq…
Transformer is the state-of-the-art model for many natural language processing, computer vision, and audio analysis problems. Transformer effectively combines information from the past input and output samples in auto-regressive manner so…
Conditional set generation learns a mapping from an input sequence of tokens to a set. Several NLP tasks, such as entity typing and dialogue emotion tagging, are instances of set generation. Seq2Seq models, a popular choice for set…
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…