Growing Trees on Sounds: Assessing Strategies for End-to-End Dependency Parsing of Speech

Anonymous

Abstract: Direct dependency parsing of the speech signal --as opposed to parsing speech transcriptions-- has recently been proposed as a task $\citep{pupier22_interspeech}$, as a way of incorporating prosodic information in the parsing system and bypassing the limitations of a pipeline approach that would consist of using first an Automatic Speech Recognition (ASR) system and then a syntactic parser.In this article, we report on a set of experiments aiming at assessing the performance of two parsing paradigms (graph-based parsing and sequence labeling based parsing) on speech parsing.We perform this evaluation on a large treebank of spoken French, featuringrealistic spontaneous conversations.Our findings show that (i) the graph based approach obtain better results across the board (ii) parsing directly from speech outperforms a pipeline approach, despite having 30% fewer parameters.

Paper Type: short

Research Area: Syntax: Tagging, Chunking and Parsing / ML

Contribution Types: NLP engineering experiment

Languages Studied: French