Saved in:
Bibliographic Details
Main Authors: Su, Zhenpeng, Wu, Xing, Zhou, Wei, Ma, Guangyuan, Hu, Songlin
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2306.04357
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910385036066816
author Su, Zhenpeng
Wu, Xing
Zhou, Wei
Ma, Guangyuan
Hu, Songlin
author_facet Su, Zhenpeng
Wu, Xing
Zhou, Wei
Ma, Guangyuan
Hu, Songlin
contents 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 for cross-encoders. However, there are no post-training methods tailored for dense encoders in dialogue response selection. We argue that when the current language model, based on dense dialogue systems (such as BERT), is employed as a dense encoder, it separately encodes dialogue context and response, leading to a struggle to achieve the alignment of both representations. Thus, we propose Dial-MAE (Dialogue Contextual Masking Auto-Encoder), a straightforward yet effective post-training technique tailored for dense encoders in dialogue response selection. Dial-MAE uses an asymmetric encoder-decoder architecture to compress the dialogue semantics into dense vectors, which achieves better alignment between the features of the dialogue context and response. Our experiments have demonstrated that Dial-MAE is highly effective, achieving state-of-the-art performance on two commonly evaluated benchmarks.
format Preprint
id arxiv_https___arxiv_org_abs_2306_04357
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems
Su, Zhenpeng
Wu, Xing
Zhou, Wei
Ma, Guangyuan
Hu, Songlin
Computation and Language
Artificial Intelligence
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 for cross-encoders. However, there are no post-training methods tailored for dense encoders in dialogue response selection. We argue that when the current language model, based on dense dialogue systems (such as BERT), is employed as a dense encoder, it separately encodes dialogue context and response, leading to a struggle to achieve the alignment of both representations. Thus, we propose Dial-MAE (Dialogue Contextual Masking Auto-Encoder), a straightforward yet effective post-training technique tailored for dense encoders in dialogue response selection. Dial-MAE uses an asymmetric encoder-decoder architecture to compress the dialogue semantics into dense vectors, which achieves better alignment between the features of the dialogue context and response. Our experiments have demonstrated that Dial-MAE is highly effective, achieving state-of-the-art performance on two commonly evaluated benchmarks.
title Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2306.04357