paper-with-me

Papers

ConfNet2Seq: Full Length Answer Generation from Spoken Questions

2020-06-09 · Vaishali Pal, Manish Shrivastava, Laurent Besacier

Conversational and task-oriented dialogue systems aim to interact with the user using natural responses through multi-modal interfaces, such as text or speech. These desired responses are in the form of full-length natural answers generated over facts retrieved from a knowledge source. While the task of generating natural answers to questions from an answer span has been widely studied, there has been little research on natural sentence generation over spoken content. We propose a novel system to generate full length natural language answers from spoken questions and factoid answers. The spoken sequence is compactly represented as a confusion network extracted from a pre-trained Automatic Speech Recognizer. This is the first attempt towards generating full-length natural answers from a graph input(confusion network) to the best of our knowledge. We release a large-scale dataset of 259,788 samples of spoken questions, their factoid answers and corresponding full-length textual answers. Following our proposed approach, we achieve comparable performance with best ASR hypothesis.

📄 PDF Abstract BibTeX arXiv:2006.05163

Code (1)

kolk/ConfnetPointerGenBaseline 공식 구현 pytorch

Tasks

Answer GenerationSentenceTask-Oriented Dialogue Systems

Similar Papers 제목 키워드 기반

Modeling ASR Ambiguity for Dialogue State Tracking Using Word Confusion Networks

2020-02-03 · Vaishali Pal, Fabien Guillot, Manish Shrivastava, Jean-Michel Renders 외

Spoken dialogue systems typically use a list of top-N ASR hypotheses for inferring the semantic meaning and tracking the state of the dialogue. However ASR graphs, such as confusion networks (confnets), provide a compact…

Dialogue State TrackingSpoken Dialogue Systems

How Should LLMs Listen While Speaking? A Study of User-Stream Routing in Full-Duplex Spoken Dialogue

2026-05-11 · Hui Lu, Xueyuan Chen, Huimeng Wang, Shuhai Peng 외 arxiv

Full-duplex spoken dialogue requires a model to keep listening while generating its own spoken response. This is challenging for large language models (LLMs), which are designed to extend a single coherent sequence and d…

Question Answering

Answering Naturally: Factoid to Full length Answer Generation

2019-11-01 · WS 2019 11 · Vaishali Pal, Manish Shrivastava, Irshad Bhat

In recent years, the task of Question Answering over passages, also pitched as a reading comprehension, has evolved into a very active research area. A reading comprehension system extracts a span of text, comprising of …

Answer GenerationQuestion AnsweringReading ComprehensionText Generation

Learning When to Think While Listening in Large Audio-Language Models

2026-05-26 · Zhiyuan Song, Weici Zhao, Yang Xiao, Suhao Yu 외 arxiv

Recent advances in Large Audio-Language Models (LALMs) have made real-time, streaming spoken interaction increasingly practical. In this setting, reasoning quality and responsiveness are tightly coupled: delaying reasoni…

Question Answering

Generating Self-Contained and Summary-Centric Question Answer Pairs via Differentiable Reward Imitation Learning

2021-09-10 · EMNLP 2021 11 · Li Zhou, Kevin Small, Yong Zhang, Sandeep Atluri

Motivated by suggested question generation in conversational news recommendation systems, we propose a model for generating question-answer pairs (QA pairs) with self-contained, summary-centric questions and length-const…

ArticlesImitation LearningNews RecommendationQuestion Generation+3