中文
相关论文

相关论文: Look Who's Talking: Inferring Speaker Attributes f…

200 篇论文

Open-domain dialogue agents must be able to converse about many topics while incorporating knowledge about the user into the conversation. In this work we address the acquisition of such knowledge, for personalization in downstream Web…

计算与语言 · 计算机科学 2019-04-25 Anna Tigunova , Andrew Yates , Paramita Mirza , Gerhard Weikum

Research on human spoken language has shown that speech plays an important role in identifying speaker personality traits. In this work, we propose an approach for identifying speaker personality traits using overlap dynamics in multiparty…

计算与语言 · 计算机科学 2019-09-04 Mingzhi Yu , Emer Gilmartin , Diane Litman

Personal attributes represent structured information about a person, such as their hobbies, pets, family, likes and dislikes. We introduce the tasks of extracting and inferring personal attributes from human-human dialogue, and analyze the…

计算与语言 · 计算机科学 2022-04-20 Zhilin Wang , Xuhui Zhou , Rik Koncel-Kedziorski , Alex Marin , Fei Xia

User attributes provide rich and useful information for user understanding, yet structured and easy-to-use attributes are often sparsely populated. In this paper, we leverage dialogues with conversational agents, which contain strong…

计算与语言 · 计算机科学 2019-08-14 Chien-Sheng Wu , Andrea Madotto , Zhaojiang Lin , Peng Xu , Pascale Fung

People spend a substantial portion of their lives engaged in conversation, and yet our scientific understanding of conversation is still in its infancy. In this report we advance an interdisciplinary science of conversation, with findings…

Endowing a dialogue system with particular personality traits is essential to deliver more human-like conversations. However, due to the challenge of embodying personality via language expression and the lack of large-scale persona-labeled…

计算与语言 · 计算机科学 2020-01-03 Yinhe Zheng , Guanyi Chen , Minlie Huang , Song Liu , Xuan Zhu

An intrinsic aspect of every conversation is the way talk-time is shared between multiple speakers. Conversations can be balanced, with each speaker claiming a similar amount of talk-time, or imbalanced when one talks disproportionately.…

计算与语言 · 计算机科学 2025-09-16 Kaixiang Zhang , Justine Zhang , Cristian Danescu-Niculescu-Mizil

Personas are useful for dialogue response prediction. However, the personas used in current studies are pre-defined and hard to obtain before a conversation. To tackle this issue, we study a new task, named Speaker Persona Detection (SPD),…

计算与语言 · 计算机科学 2021-09-06 Jia-Chen Gu , Zhen-Hua Ling , Yu Wu , Quan Liu , Zhigang Chen , Xiaodan Zhu

This paper focuses on simulating text dialogues in which impressions between speakers improve during speed dating. This simulation involves selecting an utterance from multiple candidates generated by a text generation model that replicates…

Existing argumentation datasets have succeeded in allowing researchers to develop computational methods for analyzing the content, structure and linguistic features of argumentative text. They have been much less successful in fostering…

计算与语言 · 计算机科学 2019-09-26 Esin Durmus , Claire Cardie

Current methods for active speak er detection focus on modeling short-term audiovisual information from a single speaker. Although this strategy can be enough for addressing single-speaker scenarios, it prevents accurate detection when the…

计算机视觉与模式识别 · 计算机科学 2020-05-21 Juan Leon Alcazar , Fabian Caba Heilbron , Long Mai , Federico Perazzi , Joon-Young Lee , Pablo Arbelaez , Bernard Ghanem

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…

计算与语言 · 计算机科学 2016-06-02 Rami Al-Rfou , Marc Pickett , Javier Snaider , Yun-hsuan Sung , Brian Strope , Ray Kurzweil

Understanding how the social context of an interaction affects our dialog behavior is of great interest to social scientists who study human behavior, as well as to computer scientists who build automatic methods to infer those social…

计算与语言 · 计算机科学 2017-06-13 Vinodkumar Prabhakaran , Owen Rambow

Tangled multi-party dialogue contexts lead to challenges for dialogue reading comprehension, where multiple dialogue threads flow simultaneously within a common dialogue record, increasing difficulties in understanding the dialogue history…

计算与语言 · 计算机科学 2022-03-16 Xinbei Ma , Zhuosheng Zhang , Hai Zhao

In order to build self-consistent personalized dialogue agents, previous research has mostly focused on textual persona that delivers personal facts or personalities. However, to fully describe the multi-faceted nature of persona, image…

计算与语言 · 计算机科学 2023-05-30 Jaewoo Ahn , Yeda Song , Sangdoo Yun , Gunhee Kim

We introduce an approach to identifying speaker names in dialogue transcripts, a crucial task for enhancing content accessibility and searchability in digital media archives. Despite the advancements in speech recognition, the task of…

A good conversation requires balance -- between simplicity and detail; staying on topic and changing it; asking questions and answering them. Although dialogue agents are commonly evaluated via human judgments of overall quality, the…

计算与语言 · 计算机科学 2019-04-11 Abigail See , Stephen Roller , Douwe Kiela , Jason Weston

Conversational agents are gaining popularity with the increasing ubiquity of smart devices. However, training agents in a data driven manner is challenging due to a lack of suitable corpora. This paper presents a novel method for gathering…

Existing conversational datasets consist either of written proxies for dialog or small-scale transcriptions of natural speech. We introduce 'Interview': a large-scale (105K conversations) media dialog dataset collected from news interview…

计算与语言 · 计算机科学 2020-04-08 Bodhisattwa Prasad Majumder , Shuyang Li , Jianmo Ni , Julian McAuley

In this work, we report on the effectiveness of our efforts to tailor the personality and conversational style of a conversational agent based on GPT-3.5 and GPT-4 through prompts. We use three personality dimensions with two levels each to…

人机交互 · 计算机科学 2023-10-18 Heng Gu , Chadha Degachi , Uğur Genç , Senthil Chandrasegaran , Himanshu Verma
‹ 上一页 1 2 3 10 下一页 ›