Neural Models for Sequence Chunking

TL;DR

This paper introduces neural models that treat entire chunks as units for labeling in sequence chunking tasks, achieving state-of-the-art results in text chunking and slot filling.

Contribution

It proposes three neural models that consider chunks as complete units, offering an alternative to traditional word-based sequence labeling methods.

Findings

Achieved state-of-the-art performance on text chunking.

Achieved state-of-the-art performance on slot filling.

Demonstrated effectiveness of chunk-based neural models.

Abstract

Many natural language understanding (NLU) tasks, such as shallow parsing (i.e., text chunking) and semantic slot filling, require the assignment of representative labels to the meaningful chunks in a sentence. Most of the current deep neural network (DNN) based methods consider these tasks as a sequence labeling problem, in which a word, rather than a chunk, is treated as the basic unit for labeling. These chunks are then inferred by the standard IOB (Inside-Outside-Beginning) labels. In this paper, we propose an alternative approach by investigating the use of DNN for sequence chunking, and propose three neural models so that each chunk can be treated as a complete unit for labeling. Experimental results show that the proposed neural sequence chunking models can achieve start-of-the-art performance on both the text chunking and slot filling tasks.