相关论文: Jointly Optimizing State Operation Prediction and …

Bidirectional Encoder Representations from Transformers (BERT) reach state-of-the-art results in a variety of Natural Language Processing tasks. However, understanding of their internal functioning is still insufficient and unsatisfactory.…

Over the past few decades, Artificial Intelligence(AI) has progressed from the initial machine learning stage to the deep learning stage, and now to the stage of foundational models. Foundational models have the characteristics of…

Attention-based encoder-decoder neural network models have recently shown promising results in goal-oriented dialogue systems. However, these models struggle to reason over and incorporate state-full knowledge while preserving their…

Dialogue state tracking (DST) module is an important component for task-oriented dialog systems to understand users' goals and needs. Collecting dialogue state labels including slots and values can be costly, especially with the wide…

Dialogue State Tracking (DST) is an essential element of conversational AI with the objective of deeply understanding the conversation context and leading it toward answering user requests. Due to high demands for open-domain and multi-turn…

This paper describes our approach in DSTC 8 Track 4: Schema-Guided Dialogue State Tracking. The goal of this task is to predict the intents and slots in each user turn to complete the dialogue state tracking (DST) based on the information…

Dialogue State Tracking (DST), a key component of task-oriented conversation systems, represents user intentions by determining the values of pre-defined slots in an ongoing dialogue. Existing approaches use hand-crafted templates and…

Maintaining consistent personas is essential for dialogue agents. Although tremendous advancements have been brought, the limited-scale of annotated persona-dense data are still barriers towards training robust and consistent persona-based…

Recently, BERT has become an essential ingredient of various NLP deep models due to its effectiveness and universal-usability. However, the online deployment of BERT is often blocked by its large-scale parameters and high computational…

Audio captioning aims at using natural language to describe the content of an audio clip. Existing audio captioning systems are generally based on an encoder-decoder architecture, in which acoustic information is extracted by an audio…

In task-oriented dialogue systems, spoken language understanding, or SLU, refers to the task of parsing natural language user utterances into semantic frames. Making use of context from prior dialogue history holds the key to more effective…

We present DiffusionBERT, a new generative masked language model based on discrete diffusion models. Diffusion models and many pre-trained language models have a shared training objective, i.e., denoising, making it possible to combine the…

Tremendous amounts of multimedia associated with speech information are driving an urgent need to develop efficient and effective automatic summarization methods. To this end, we have seen rapid progress in applying supervised deep neural…

End-to-end (E2E) automatic speech recognition (ASR) systems often have difficulty recognizing uncommon words, that appear infrequently in the training data. One promising method, to improve the recognition accuracy on such rare words, is to…

Augmentation of task-oriented dialogues has followed standard methods used for plain-text such as back-translation, word-level manipulation, and paraphrasing despite its richly annotated structure. In this work, we introduce an augmentation…

In typical multi-talker speech recognition systems, a neural network-based acoustic model predicts senone state posteriors for each speaker. These are later used by a single-talker decoder which is applied on each speaker-specific output…

Pre-trained language models like BERT achieve superior performances in various NLP tasks without explicit consideration of syntactic information. Meanwhile, syntactic information has been proved to be crucial for the success of NLP…

Neural transducers (NT) provide an effective framework for speech streaming, demonstrating strong performance in automatic speech recognition (ASR). However, the application of NT to speech translation (ST) remains challenging, as existing…

Recently, document-level neural machine translation (NMT) has become a hot topic in the community of machine translation. Despite its success, most of existing studies ignored the discourse structure information of the input document to be…

A typical conversation comprises of multiple turns between participants where they go back-and-forth between different topics. At each user turn, dialogue state tracking (DST) aims to estimate user's goal by processing the current…