Auxiliary Sequence Labeling Tasks for Disfluency Detection

TL;DR

This paper introduces a novel approach for disfluency detection in speech transcripts by incorporating auxiliary sequence labeling tasks like NER and POS, leading to improved accuracy over previous methods.

Contribution

It proposes using linguistic auxiliary tasks such as NER and POS for disfluency detection, enhancing model performance and understanding of disfluency patterns.

Findings

Auxiliary SL tasks improve disfluency detection accuracy.

The method outperforms previous state-of-the-art on English Switchboard.

Certain auxiliary tasks are more influential depending on the baseline model.

Abstract

Detecting disfluencies in spontaneous speech is an important preprocessing step in natural language processing and speech recognition applications. Existing works for disfluency detection have focused on designing a single objective only for disfluency detection, while auxiliary objectives utilizing linguistic information of a word such as named entity or part-of-speech information can be effective. In this paper, we focus on detecting disfluencies on spoken transcripts and propose a method utilizing named entity recognition (NER) and part-of-speech (POS) as auxiliary sequence labeling (SL) tasks for disfluency detection. First, we investigate cases that utilizing linguistic information of a word can prevent mispredicting important words and can be helpful for the correct detection of disfluencies. Second, we show that training a disfluency detection model with auxiliary SL tasks can improve its F-score in disfluency detection. Then, we analyze which auxiliary SL tasks are influential depending on baseline models. Experimental results on the widely used English Switchboard dataset show that our method outperforms the previous state-of-the-art in disfluency detection.