paper-with-me

Papers Conversational Response Selection

“Conversational Response Selection” 태그가 달린 논문 46편 · 필터 해제

Efficient Dynamic Hard Negative Sampling for Dialogue Selection

2024-08-16 · NLP4ConvAI Association for Computational Linguistics Workshop 2024 8 · Janghoon Han, Dongkyu Lee, Joongbo Shin, Hyunkyung Bae 외

Recent studies have demonstrated significant improvements in selection tasks, and a considerable portion of this success is attributed to incorporating informative negative samples during training. While traditional meth…

Conversational Response Selection

P5: Plug-and-Play Persona Prompting for Personalized Response Selection

2023-10-10 · Joosung Lee, Minsik Oh, Donghun Lee

The use of persona-grounded retrieval-based chatbots is crucial for personalized conversations, but there are several challenges that need to be addressed. 1) In general, collecting persona-grounded corpus is very expens…

ChatbotConversational Response Selection

Knowledge-aware response selection with semantics underlying multi-turn open-domain conversations

2023-07-27 · World Wide Web Journal 2023 7 · Makoto Nakatsuji, Yuka Ozeki, Shuhei Tateishi, Yoshihisa Kano & QingPeng Zhang

Response selection is a critical issue in the AI community, with important applications on the Web. The accuracy of the selected responses, however, tends to be insufficient due to the lack of contextual awareness, espec…

Conversational Response Selection

Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems

2023-06-07 · Zhenpeng Su, Xing Wu, Wei Zhou, Guangyuan Ma 외

Dialogue response selection aims to select an appropriate response from several candidates based on a given user and system utterance history. Most existing works primarily focus on post-training and fine-tuning tailored…

Conversational Response SelectionDecoderLanguage ModelingLanguage Modelling+2

Learning Dialogue Representations from Consecutive Utterances

2022-05-26 · NAACL 2022 7 · Zhihan Zhou, Dejiao Zhang, Wei Xiao, Nicholas Dingwall 외

Learning high-quality dialogue representations is essential for solving a variety of dialogue-oriented tasks, especially considering that dialogue systems often suffer from data scarcity. In this paper, we introduce Dial…

Contrastive LearningConversational Question AnsweringConversational Response SelectionDialogue Act Classification+14

One Agent To Rule Them All: Towards Multi-agent Conversational AI

2022-03-15 · Findings (ACL) 2022 5 · Christopher Clarke, Joseph Joshua Peper, Karthik Krishnamurthy, Walter Talamonti 외

The increasing volume of commercially available conversational agents (CAs) on the market has resulted in users being burdened with learning and adopting multiple agents to accomplish their tasks. Though prior work has e…

AllConversational Response SelectionMulti-agent IntegrationText Classification

Two-Level Supervised Contrastive Learning for Response Selection in Multi-Turn Dialogue

2022-03-01 · Wentao Zhang, Shuang Xu, Haoran Huang

Selecting an appropriate response from many candidates given the utterances in a multi-turn dialogue is the key problem for a retrieval-based dialogue system. Existing work formalizes the task as matching between the utt…

Contrastive LearningConversational Response SelectionRetrievalSentence+1

Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning

2021-11-19 · Yuntao Li, Can Xu, Huang Hu, Lei Sha 외

Retrieve-based dialogue response selection aims to find a proper response from a candidate set given a multi-turn context. Pre-trained language models (PLMs) based methods have yielded significant improvements on this ta…

Contrastive LearningConversational Response Selection

Exploring Dense Retrieval for Dialogue Response Selection

2021-10-13 · Tian Lan, Deng Cai, Yan Wang, Yixuan Su 외

Recent progress in deep learning has continuously improved the accuracy of dialogue response selection. In particular, sophisticated neural network architectures are leveraged to capture the rich interactions between dia…

Conversational Response SelectionRetrieval

Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues

2021-08-17 · ACM Transactions on Information Systems 2021 8 · Ruijian Xu, Chongyang Tao, Jiazhan Feng, Wei Wu 외

Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is challenging in three aspects: (1) the meaning of a context–response pair is built upon language un…

Conversational Response SelectionRetrieval

MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding

2021-06-03 · ACL 2021 5 · Jia-Chen Gu, Chongyang Tao, Zhen-Hua Ling, Can Xu 외

Recently, various neural models for multi-party conversation (MPC) have achieved impressive improvements on a variety of tasks such as addressee recognition, speaker identification and response prediction. However, these…

Conversational Response SelectionLanguage ModelingLanguage ModellingSpeaker Identification

Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems

2021-06-02 · Chiyu Song, Hongliang He, Haofei Yu, Pengfei Fang 외

Sample-and-rank is a key decoding strategy for modern generation-based dialogue systems. It helps achieve diverse and high-quality responses by selecting an answer from a small pool of generated candidates. The current s…

Computational EfficiencyConversational Response Selection

Fine-grained Post-training for Improving Retrieval-based Dialogue Systems

2021-05-24 · NAACL 2021 4 · Janghoon Han, Taesuk Hong, Byoungjae Kim, Youngjoong Ko 외

Retrieval-based dialogue systems display an outstanding performance when pre-trained language models are used, which includes bidirectional encoder representations from transformers (BERT). During the multi-turn response…

Conversational Response SelectionRetrieval

Open-domain question classification and completion in conversational information search

2021-02-26 · Omid Mohammadi Kia, Mahmood Neshati, Mahsa Soudi Alamdari

Searching for new information requires talking to the system. In this research, an Open-domain Conversational information search system has been developed. This system has been implemented using the TREC CAsT 2019 track,…

ClassificationConversational Response SelectionGeneral Classification

Dialogue Response Selection with Hierarchical Curriculum Learning

2020-12-29 · ACL 2021 5 · Yixuan Su, Deng Cai, Qingyu Zhou, Zibo Lin 외

We study the learning of a matching model for dialogue response selection. Motivated by the recent finding that models trained with random negative samples are not ideal in real-world scenarios, we propose a hierarchical…

Conversational Response Selection

Dialogue Response Ranking Training with Large-Scale Human Feedback Data

2020-09-15 · EMNLP 2020 11 · Xiang Gao, Yizhe Zhang, Michel Galley, Chris Brockett 외

Existing open-domain dialog models are generally trained to minimize the perplexity of target human responses. However, some human replies are more engaging than others, spawning more followup interactions. Current conve…

Conversational Response SelectionOpen-Domain Dialog

Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues

2020-09-14 · Ruijian Xu, Chongyang Tao, Daxin Jiang, Xueliang Zhao 외

Building an intelligent dialogue system with the ability to select a proper response according to a multi-turn context is a great challenging task. Existing studies focus on building a context-response matching model wit…

Conversational Response SelectionRetrieval

Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection

2020-09-10 · Taesun Whang, Dongyub Lee, Dongsuk Oh, Chanhee Lee 외

In this paper, we study the task of selecting the optimal response given a user and system utterance history in retrieval-based multi-turn dialog systems. Recently, pre-trained language models (e.g., BERT, RoBERTa, and E…

Binary ClassificationConversational Response SelectionRetrieval

Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots

2020-04-07 · Jia-Chen Gu, Tianda Li, Quan Liu, Zhen-Hua Ling 외

In this paper, we study the problem of employing pre-trained language models for multi-turn response selection in retrieval-based chatbots. A new model, named Speaker-Aware BERT (SA-BERT), is proposed in order to make th…

Conversational Response SelectionDisentanglementDomain AdaptationRetrieval

The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection

2020-04-06 · EMNLP 2020 11 · Zibo Lin, Deng Cai, Yan Wang, Xiaojiang Liu 외

Response selection plays a vital role in building retrieval-based conversation systems. Despite that response selection is naturally a learning-to-rank problem, most prior works take a point-wise view and train binary cl…

Conversational Response SelectionDiversityLearning-To-RankResponse Generation+1
1–20 / 46 다음 →