中文
相关论文

相关论文: Increasing faithfulness in human-human dialog summ…

200 篇论文

Current researches on spoken language understanding (SLU) heavily are limited to a simple setting: the plain text-based SLU that takes the user utterance as input and generates its corresponding semantic frames (e.g., intent and slots).…

计算与语言 · 计算机科学 2022-01-13 Xiao Xu , Libo Qin , Kaiji Chen , Guoxing Wu , Linlin Li , Wanxiang Che

Persuasion dialogue systems reflect the machine's ability to make strategic moves beyond verbal communication, and therefore differentiate themselves from task-oriented or open-domain dialogue systems and have their own unique values.…

计算与语言 · 计算机科学 2022-10-25 Weiyan Shi , Yu Li , Saurav Sahay , Zhou Yu

An open challenge in constructing dialogue systems is developing methods for automatically learning dialogue strategies from large amounts of unlabelled data. Recent work has proposed Next-Utterance-Classification (NUC) as a surrogate task…

计算与语言 · 计算机科学 2016-07-26 Ryan Lowe , Iulian V. Serban , Mike Noseworthy , Laurent Charlin , Joelle Pineau

This paper addresses the problem of summarizing decisions in spoken meetings: our goal is to produce a concise {\it decision abstract} for each meeting decision. We explore and compare token-level and dialogue act-level automatic…

计算与语言 · 计算机科学 2016-06-28 Lu Wang , Claire Cardie

Abstractive Speech Summarization (SSum) aims to generate human-like text summaries from spoken content. It encounters difficulties in handling long speech input and capturing the intricate cross-modal mapping between long speech inputs and…

计算与语言 · 计算机科学 2024-07-03 Hengchao Shang , Zongyao Li , Jiaxin Guo , Shaojun Li , Zhiqiang Rao , Yuanchang Luo , Daimeng Wei , Hao Yang

Spoken Language Understanding (SLU) has progressed from traditional single-task methods to large audio language model (LALM) solutions. Yet, most existing speech benchmarks focus on single-speaker or isolated tasks, overlooking the…

音频与语音处理 · 电气工程与系统科学 2025-08-12 Shuai Wang , Zhaokai Sun , Zhennan Lin , Chengyou Wang , Zhou Pan , Lei Xie

Task-oriented dialogue systems have been plagued by the difficulties of obtaining large-scale and high-quality annotated conversations. Furthermore, most of the publicly available datasets only include written conversations, which are…

Recent advancements in large language models (LLMs) have considerably advanced the capabilities of summarization systems. However, they continue to face concerns about hallucinations. While prior work has evaluated LLMs extensively in news…

计算与语言 · 计算机科学 2024-06-06 Sanjana Ramprasad , Elisa Ferracane , Zachary C. Lipton

Automated metrics such as BLEU are widely used in the machine translation literature. They have also been used recently in the dialogue community for evaluating dialogue response generation. However, previous work in dialogue response…

计算与语言 · 计算机科学 2017-06-30 Shikhar Sharma , Layla El Asri , Hannes Schulz , Jeremie Zumer

Many conversation datasets have been constructed in the recent years using crowdsourcing. However, the data collection process can be time consuming and presents many challenges to ensure data quality. Since language generation has improved…

计算与语言 · 计算机科学 2021-06-08 Chulaka Gunasekara , Guy Feigenblat , Benjamin Sznajder , Sachindra Joshi , David Konopnicki

We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface…

计算与语言 · 计算机科学 2024-02-20 Tom Bocklisch , Thomas Werkmeister , Daksh Varshneya , Alan Nichol

We propose the shared task of cross-lingual conversation summarization, \emph{ConvSumX Challenge}, opening new avenues for researchers to investigate solutions that integrate conversation summarization and machine translation. This task can…

计算与语言 · 计算机科学 2022-05-04 Yulong Chen , Ming Zhong , Xuefeng Bai , Naihao Deng , Jing Li , Xianchao Zhu , Yue Zhang

Goal-oriented dialog systems enable users to complete specific goals like requesting information about a movie or booking a ticket. Typically the dialog system pipeline contains multiple ML models, including natural language understanding,…

In this paper, we investigate the problem of including relevant information as context in open-domain dialogue systems. Most models struggle to identify and incorporate important knowledge from dialogues and simply use the entire turns as…

计算与语言 · 计算机科学 2022-10-14 Rui Ribeiro , Luísa Coheur

We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the…

计算与语言 · 计算机科学 2019-04-02 Pushpendre Rastogi , Arpit Gupta , Tongfei Chen , Lambert Mathias

Summarization of multi-party dialogues is a critical capability in industry, enhancing knowledge transfer and operational effectiveness across many domains. However, automatically generating high-quality summaries is challenging, as the…

Abstractive speech summarization (SSUM) aims to generate human-like summaries from speech. Given variations in information captured and phrasing, recordings can be summarized in multiple ways. Therefore, it is more reasonable to consider a…

计算与语言 · 计算机科学 2024-10-28 Jee-weon Jung , Roshan Sharma , William Chen , Bhiksha Raj , Shinji Watanabe

Recent advances in Speech Large Language Models (Speech LLMs) have led to great progress in speech understanding tasks such as Automatic Speech Recognition (ASR) and Speech Emotion Recognition (SER). However, whether these models can…

声音 · 计算机科学 2025-12-01 Chen Li , Peiji Yang , Yicheng Zhong , Jianxing Yu , Zhisheng Wang , Zihao Gou , Wenqing Chen , Jian Yin

Reliable evaluation of large language model (LLM)-generated summaries remains an open challenge, particularly across heterogeneous domains and document lengths. We conduct a comprehensive meta-evaluation of 14 automatic summarization…

计算与语言 · 计算机科学 2026-04-29 Huyen Nguyen , Haoxuan Zhang , Yang Zhang , Junhua Ding , Haihua Chen

Recent studies leverage large language models with multi-tasking capabilities, using natural language prompts to guide the model's behavior and surpassing performance of task-specific models. Motivated by this, we ask: can we build a single…