Subword Encoding in Lattice LSTM for Chinese Word Segmentation

TL;DR

This paper introduces a lattice LSTM model for Chinese word segmentation that effectively utilizes subword information without external segmentors, achieving competitive results and providing insights into the contributions of lexicon and embeddings.

Contribution

It demonstrates that subword encoding in lattice LSTM performs comparably to word embeddings and offers a more independent approach for Chinese word segmentation.

Findings

Subword encoding achieves similar performance to word embeddings.

Lattice LSTM with subword encoding outperforms previous models on benchmarks.

Lexicon information contributes more than pretrained embeddings.

Abstract

We investigate a lattice LSTM network for Chinese word segmentation (CWS) to utilize words or subwords. It integrates the character sequence features with all subsequences information matched from a lexicon. The matched subsequences serve as information shortcut tunnels which link their start and end characters directly. Gated units are used to control the contribution of multiple input links. Through formula derivation and comparison, we show that the lattice LSTM is an extension of the standard LSTM with the ability to take multiple inputs. Previous lattice LSTM model takes word embeddings as the lexicon input, we prove that subword encoding can give the comparable performance and has the benefit of not relying on any external segmentor. The contribution of lattice LSTM comes from both lexicon and pretrained embeddings information, we find that the lexicon information contributes more than the pretrained embeddings information through controlled experiments. Our experiments show that the lattice structure with subword encoding gives competitive or better results with previous state-of-the-art methods on four segmentation benchmarks. Detailed analyses are conducted to compare the performance of word encoding and subword encoding in lattice LSTM. We also investigate the performance of lattice LSTM structure under different circumstances and when this model works or fails.