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

Authors

  • Taesun Whang Wisenut Inc.
  • Dongyub Lee Kakao Corp.
  • Dongsuk Oh Korea University
  • Chanhee Lee Korea University
  • Kijong Han Kakao Enterprise Corp.
  • Dong-hun Lee Kakao Enterprise Corp.
  • Saebyeok Lee Wisenut Inc. Korea University

DOI:

https://doi.org/10.1609/aaai.v35i16.17653

Keywords:

Conversational AI/Dialog Systems

Abstract

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 ELECTRA) showed significant improvements in various natural language processing tasks. This and similar response selection tasks can also be solved using such language models by formulating the tasks as dialog--response binary classification tasks. Although existing works using this approach successfully obtained state-of-the-art results, we observe that language models trained in this manner tend to make predictions based on the relatedness of history and candidates, ignoring the sequential nature of multi-turn dialog systems. This suggests that the response selection task alone is insufficient for learning temporal dependencies between utterances. To this end, we propose utterance manipulation strategies (UMS) to address this problem. Specifically, UMS consist of several strategies (i.e., insertion, deletion, and search), which aid the response selection model towards maintaining dialog coherence. Further, UMS are self-supervised methods that do not require additional annotation and thus can be easily incorporated into existing approaches. Extensive evaluation across multiple languages and models shows that UMS are highly effective in teaching dialog consistency, which leads to models pushing the state-of-the-art with significant margins on multiple public benchmark datasets.

Downloads

Published

2021-05-18

How to Cite

Whang, T., Lee, D., Oh, D., Lee, C., Han, K., Lee, D.- hun, & Lee, S. (2021). Do Response Selection Models Really Know What’s Next? Utterance Manipulation Strategies for Multi-turn Response Selection. Proceedings of the AAAI Conference on Artificial Intelligence, 35(16), 14041-14049. https://doi.org/10.1609/aaai.v35i16.17653

Issue

Section

AAAI Technical Track on Speech and Natural Language Processing III