CLFeb 12, 2023

Discourse Structure Extraction from Pre-Trained and Fine-Tuned Language Models in Dialogues

arXiv:2302.05895v2272 citationsh-index: 49
Originality Incremental advance
AI Analysis

This addresses data sparsity in discourse processing for dialogues, offering incremental improvements in a domain-specific task.

The paper tackled discourse structure extraction in dialogues by using attention matrices from pre-trained language models, proposing unsupervised and semi-supervised methods that achieved F1 scores up to 68.1 on the STAC corpus.

Discourse processing suffers from data sparsity, especially for dialogues. As a result, we explore approaches to build discourse structures for dialogues, based on attention matrices from Pre-trained Language Models (PLMs). We investigate multiple tasks for fine-tuning and show that the dialogue-tailored Sentence Ordering task performs best. To locate and exploit discourse information in PLMs, we propose an unsupervised and a semi-supervised method. Our proposals achieve encouraging results on the STAC corpus, with F1 scores of 57.2 and 59.3 for unsupervised and semi-supervised methods, respectively. When restricted to projective trees, our scores improved to 63.3 and 68.1.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes