Exploring Segment Representations for Neural Segmentation Models

TL;DR

This paper introduces a neural semi-CRF model for NLP segmentation tasks that effectively represents segments and achieves state-of-the-art results on Chinese word segmentation and competitive performance on NER.

Contribution

It combines semi-CRF with neural networks to explore segment representations, including composition functions and segment embeddings, for improved segmentation performance.

Findings

Achieves state-of-the-art on Chinese word segmentation

Provides competitive results on NER

Demonstrates benefits of segment representation techniques

Abstract

Many natural language processing (NLP) tasks can be generalized into segmentation problem. In this paper, we combine semi-CRF with neural network to solve NLP segmentation tasks. Our model represents a segment both by composing the input units and embedding the entire segment. We thoroughly study different composition functions and different segment embeddings. We conduct extensive experiments on two typical segmentation tasks: named entity recognition (NER) and Chinese word segmentation (CWS). Experimental results show that our neural semi-CRF model benefits from representing the entire segment and achieves the state-of-the-art performance on CWS benchmark dataset and competitive results on the CoNLL03 dataset.