Conversational Semantic Role Labeling

TL;DR

This paper introduces conversational semantic role labeling (CSRL), a new task designed to handle dialogue-specific phenomena like ellipsis and anaphora, with a new annotated dataset and evidence that dialogue-aware models improve understanding.

Contribution

The paper proposes CSRL as a novel extension of SRL for dialogues, creates a large annotated dataset, and demonstrates the effectiveness of dialogue history modeling for better dialogue understanding.

Findings

Traditional SRL performs poorly on dialogues.

Modeling dialogue history and participants improves SRL performance.

CSRL benefits dialogue response generation and context rewriting tasks.

Abstract

Semantic role labeling (SRL) aims to extract the arguments for each predicate in an input sentence. Traditional SRL can fail to analyze dialogues because it only works on every single sentence, while ellipsis and anaphora frequently occur in dialogues. To address this problem, we propose the conversational SRL task, where an argument can be the dialogue participants, a phrase in the dialogue history or the current sentence. As the existing SRL datasets are in the sentence level, we manually annotate semantic roles for 3,000 chit-chat dialogues (27,198 sentences) to boost the research in this direction. Experiments show that while traditional SRL systems (even with the help of coreference resolution or rewriting) perform poorly for analyzing dialogues, modeling dialogue histories and participants greatly helps the performance, indicating that adapting SRL to conversations is very promising for universal dialogue understanding. Our initial study by applying CSRL to two mainstream conversational tasks, dialogue response generation and dialogue context rewriting, also confirms the usefulness of CSRL.