Year: 2018
Type: conference-paper
Abstract: We investigate a lattice-structured LSTM model for Chinese NER, which encodes a sequence of input characters as well as all potential words that match a lexicon.Compared with character-based methods, our model explicitly leverages word and word sequence information.Compared with word-based methods, lattice LSTM does not suffer from segmentation errors.Gated recurrent cells allow our model to choose the most relevant characters and words from a sentence for better NER results.Experiments on various datasets show that lattice LSTM outperforms both word-based and character-based LSTM baselines, achieving the best results.
DOI: 10.18653/v1/p18-1144
Authors: Yue Zhang, Jie Yang
Institution: Singapore University of Technology and Design
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2962904552