Papers › Chinese Lexical Analysis with Deep Bi-GRU-CRF Network

Chinese Lexical Analysis with Deep Bi-GRU-CRF Network

5 Jul 2018arXiv:1807.01882archive 2025-07-28

Zhenyu Jiao, Shuqi Sun, Ke Sun

Lexical analysis is believed to be a crucial step towards natural language understanding and has been widely studied. Recent years, end-to-end lexical analysis models with recurrent neural networks have gained increasing attention. In this report, we introduce a deep Bi-GRU-CRF network that jointly models word segmentation, part-of-speech tagging and named entity recognition tasks. We trained the model using several massive corpus pre-tagged by our best Chinese lexical analysis tool, together with a small, yet high-quality human annotated corpus. We conducted balanced sampling between different corpora to guarantee the influence of human annotations, and fine-tune the CRF decoding layer regularly during the training progress. As evaluated by linguistic experts, the model achieved a 95.5% accuracy on the test set, roughly 13% relative error reduction over our (previously) best Chinese lexical analysis tool. The model is computationally efficient, achieving the speed of 2.3K characters per second with one thread.

PaperPDFCode

In Syntology View this paper on Syntology: its page in Syntology's graph, with its repositories and citations.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

baidu/lac officialmentioned in papermentioned on GitHubpaddleApache-2.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Lexical AnalysisNamed Entity RecognitionNamed Entity Recognition (NER)Natural Language UnderstandingPart-Of-Speech Taggingnamed-entity-recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

CRFSPEED

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections