English

Causal Document-Grounded Dialogue Pre-training

Computation and Language 2023-11-07 v3

Abstract

The goal of document-grounded dialogue (DocGD) is to generate a response by grounding the evidence in a supporting document in accordance with the dialogue context. This process involves four variables that are causally connected. Recently, task-specific pre-training has greatly boosted performances on many downstream tasks. Existing DocGD methods, however, continue to rely on general pre-trained language models without a specifically tailored pre-training approach that explicitly captures the causal relationships. To tackle this issue, we are the first to present a causally-complete dataset construction strategy for building million-level DocGD pre-training corpora. To better capture causality, we further propose a causally-perturbed pre-training strategy, which introduces causal perturbations on the variables and optimizes the overall causal effect. Experiments on three benchmark datasets demonstrate that our causal pre-training achieves considerable and consistent improvements under fully-supervised, low-resource, few-shot, and zero-shot settings.

Keywords

Cite

@article{arxiv.2305.10927,
  title  = {Causal Document-Grounded Dialogue Pre-training},
  author = {Yingxiu Zhao and Bowen Yu and Haiyang Yu and Bowen Li and Jinyang Li and Chao Wang and Fei Huang and Yongbin Li and Nevin L. Zhang},
  journal= {arXiv preprint arXiv:2305.10927},
  year   = {2023}
}

Comments

EMNLP 2023 main

R2 v1 2026-06-28T10:38:10.736Z