Adapting a FrameNet Semantic Parser for Spoken Language Understanding Using Adversarial Learning

TL;DR

This paper adapts a FrameNet-based semantic parser for spoken language understanding using adversarial learning to improve robustness across different speech and text domains.

Contribution

It extends adversarial learning for semantic parsing to spoken language, enhancing model robustness to lexical, stylistic, and ASR errors.

Findings

Adversarial learning improves domain generalization in semantic parsing.

Models perform better on both manual and automatic transcriptions.

Robustness increases across spoken and written language datasets.

Abstract

This paper presents a new semantic frame parsing model, based on Berkeley FrameNet, adapted to process spoken documents in order to perform information extraction from broadcast contents. Building upon previous work that had shown the effectiveness of adversarial learning for domain generalization in the context of semantic parsing of encyclopedic written documents, we propose to extend this approach to elocutionary style generalization. The underlying question throughout this study is whether adversarial learning can be used to combine data from different sources and train models on a higher level of abstraction in order to increase their robustness to lexical and stylistic variations as well as automatic speech recognition errors. The proposed strategy is evaluated on a French corpus of encyclopedic written documents and a smaller corpus of radio podcast transcriptions, both annotated with a FrameNet paradigm. We show that adversarial learning increases all models generalization capabilities both on manual and automatic speech transcription as well as on encyclopedic data.