activity
20162023
most citedKnowledge as a Teacher: Knowledge-Guided Structural Attention Networks

29 citations · 125 across the 22 of their papers we have counts for

collaborators

46 papers

cs.CL2023★ 1 cited

CONVERSER: Few-Shot Conversational Dense Retrieval with Synthetic Data Generation

Chao-Wei Huang, Chen-Yu Hsu, Tsu-Yuan Hsu +2

Conversational search provides a natural interface for information retrieval (IR). Recent approaches have demonstrated promising results in applying dense retrieval to conversation…

cs.CL2023

SalesBot 2.0: A Human-Like Intent-Guided Chit-Chat Dataset

Wen-Yu Chang, Yun-Nung Chen

In recent research on dialogue systems and corpora, there has been a significant focus on two distinct categories: task-oriented (TOD) and open-domain (chit-chat) dialogues. TOD sy…

cs.CL2023★ 13 cited

LLM-Eval: Unified Multi-Dimensional Automatic Evaluation for Open-Domain Conversations with Large Language Models

Yen-Ting Lin, Yun-Nung Chen

We propose LLM-Eval, a unified multi-dimensional automatic evaluation method for open-domain conversations with large language models (LLMs). Existing evaluation methods often rely…

cs.CL2022★ 4 cited

Open-Domain Conversational Question Answering with Historical Answers

Hung-Chieh Fang, Kuo-Han Hung, Chao-Wei Huang +1

Open-domain conversational question answering can be viewed as two tasks: passage retrieval and conversational question answering, where the former relies on selecting candidate pa…

cs.CL2022★ 1 cited

Zero-Shot Prompting for Implicit Intent Prediction and Recommendation with Commonsense Reasoning

Hui-Chi Kuo, Yun-Nung Chen

Intelligent virtual assistants are currently designed to perform tasks or services explicitly mentioned by users, so multiple related domains or tasks need to be performed one by o…

cs.CL2022

Controllable User Dialogue Act Augmentation for Dialogue State Tracking

Chun-Mao Lai, Ming-Hao Hsu, Chao-Wei Huang +1

Prior work has demonstrated that data augmentation is useful for improving dialogue state tracking. However, there are many types of user utterances, while the prior method only co…