Towards Relation Extraction From Speech

TL;DR

This paper introduces speech relation extraction, a new task that aims to extract semantic relationships from spoken language, addressing challenges caused by ASR errors and proposing both pipeline and end-to-end models.

Contribution

It presents the first dataset and models for speech relation extraction, including a novel end-to-end SpeechRE model, and explores challenges in speech-based semantic relation extraction.

Findings

Speech relation extraction is feasible with current models.

End-to-end SpeechRE outperforms pipeline approaches in certain scenarios.

ASR errors significantly impact relation extraction accuracy.

Abstract

Relation extraction typically aims to extract semantic relationships between entities from the unstructured text. One of the most essential data sources for relation extraction is the spoken language, such as interviews and dialogues. However, the error propagation introduced in automatic speech recognition (ASR) has been ignored in relation extraction, and the end-to-end speech-based relation extraction method has been rarely explored. In this paper, we propose a new listening information extraction task, i.e., speech relation extraction. We construct the training dataset for speech relation extraction via text-to-speech systems, and we construct the testing dataset via crowd-sourcing with native English speakers. We explore speech relation extraction via two approaches: the pipeline approach conducting text-based extraction with a pretrained ASR module, and the end2end approach via a new proposed encoder-decoder model, or what we called SpeechRE. We conduct comprehensive experiments to distinguish the challenges in speech relation extraction, which may shed light on future explorations. We share the code and data on https://github.com/wutong8023/SpeechRE.