Token-Level Supervised Contrastive Learning for Punctuation Restoration

Abstract

Punctuation is critical in understanding natural language text. Currently, most automatic speech recognition (ASR) systems do not generate punctuation, which affects the performance of downstream tasks, such as intent detection and slot filling. This gives rise to the need for punctuation restoration. Recent work in punctuation restoration heavily utilizes pre-trained language models without considering data imbalance when predicting punctuation classes. In this work, we address this problem by proposing a token-level supervised contrastive learning method that aims at maximizing the distance of representation of different punctuation marks in the embedding space. The result shows that training with token-level supervised contrastive learning obtains up to 3.2% absolute F1 improvement on the test set.

5 pages, 3 figures, Accepted by INTERSPEECH 2021

References in corpus (1)

• Automatic punctuation restoration with BERT models

Cited by in corpus (6)

• Superficial White Matter Analysis: An Efficient Point-cloud-based Deep Learning Framework with Supervised Contrastive Learning for Consistent Tractography Parcellation across Populations and dMRI Acquisitions
• CL4AC: A Contrastive Loss for Audio Captioning
• Supervised Graph Contrastive Pretraining for Text Classification
• Efficient Ensemble for Multimodal Punctuation Restoration using Time-Delay Neural Network
• Improving Punctuation Restoration for Speech Transcripts via External Data
• End-to-end Joint Punctuated and Normalized ASR with a Limited Amount of Punctuated Training Data