Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Retrieval-Augmented Response Generation for Knowledge-Grounded Conversation in the Wildopen access

Authors
Ahn, YeonchanLee, Sang-GooShim, JunhoPark, Jaehui
Issue Date
Dec-2022
Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Keywords
Oral communication; Context modeling; Document handling; History; Information retrieval; Knowledge engineering; Information quality; Conversation; knowledge-grounded conversation; knowledge retrieval
Citation
IEEE ACCESS, v.10, pp 131374 - 131385
Pages
12
Journal Title
IEEE ACCESS
Volume
10
Start Page
131374
End Page
131385
URI
https://scholarworks.sookmyung.ac.kr/handle/2020.sw.sookmyung/152263
DOI
10.1109/ACCESS.2022.3228964
ISSN
2169-3536
Abstract
Users on the internet usually have conversations on interesting facts or topics along with diverse knowledge from the web. However, most existing knowledge-grounded conversation models consider only a single document regarding the topic of a conversation. The recently proposed retrieval-augmented models generate a response based on multiple documents; however, they ignore the given topic and use only the local context of the conversation. To this end, we introduce a novel retrieval-augmented response generation model that retrieves an appropriate range of documents relevant to both the topic and local context of a conversation and uses them for generating a knowledge-grounded response. Our model first accepts both topic words extracted from the whole conversation and the tokens before the response to yield multiple representations. It then chooses representations of the first N token and ones of keywords from the conversation and document encoders and compares the two groups of representation from the conversation with those groups of the document, respectively. For training, we introduce a new data-weighting scheme to encourage the model to produce knowledge-grounded responses without ground truth knowledge. Both automatic and human evaluation results with a large-scale dataset show that our models can generate more knowledgeable, diverse, and relevant responses compared to the state-of-the-art models.
Files in This Item
There are no files associated with this item.
Appears in
Collections
ETC > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Related Researcher

Researcher Shim, Junho photo

Shim, Junho
공과대학 (소프트웨어학부(첨단))
Read more

Altmetrics

Total Views & Downloads

BROWSE