# Chinese NER Using Lattice LSTM

arXiv: https://arxiv.org/abs/1805.02023 · HTML: https://mlsanity.com/paper/1805.02023/

## Key facts

- Cited by 81 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 May 2018.

## Built on by (most cited first, 30 of 81)

- [Unified Named Entity Recognition as Word-Word Relation Classification](https://mlsanity.com/paper/2112.10070/) (2021)
- [A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets](https://mlsanity.com/paper/2204.08997/) (2022)
- [Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs](https://mlsanity.com/paper/2110.01191/) (2021)
- [On the Explainability of Natural Language Processing Deep Models](https://mlsanity.com/paper/2210.06929/) (2022)
- [Lexicon Enhanced Chinese Sequence Labeling Using BERT Adapter](https://mlsanity.com/paper/2105.07148/) (2021)
- [TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning](https://mlsanity.com/paper/2111.04198/) (2021)
- [Pushing the Limits of ChatGPT on NLP Tasks](https://mlsanity.com/paper/2306.09719/) (2023)
- [Better Feature Integration for Named Entity Recognition](https://mlsanity.com/paper/2104.05316/) (2021)
- [Boundary Smoothing for Named Entity Recognition](https://mlsanity.com/paper/2204.12031/) (2022)
- [Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models](https://mlsanity.com/paper/2104.07204/) (2021)
- [Interpreting Deep Learning Models in Natural Language Processing: A Review](https://mlsanity.com/paper/2110.10470/) (2021)
- [AISHELL-NER: Named Entity Recognition from Chinese Speech](https://mlsanity.com/paper/2202.08533/) (2022)
- [SeqGPT: An Out-of-the-box Large Language Model for Open Domain Sequence Understanding](https://mlsanity.com/paper/2308.10529/) (2023)
- [Discontinuous Named Entity Recognition as Maximal Clique Discovery](https://mlsanity.com/paper/2106.00218/) (2021)
- [MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective](https://mlsanity.com/paper/2204.04391/) (2022)
- [ContextASR-Bench: A Massive Contextual Speech Recognition Benchmark](https://mlsanity.com/paper/2507.05727/) (2025)
- [TransLIST: A Transformer-Based Linguistically Informed Sanskrit Tokenizer](https://mlsanity.com/paper/2210.11753/) (2022)
- [A Survey on Deep Learning Event Extraction: Approaches and Applications](https://mlsanity.com/paper/2107.02126/) (2021)
- [Understanding the Failure of Batch Normalization for Transformers in NLP](https://mlsanity.com/paper/2210.05153/) (2022)
- [LinkNER: Linking Local Named Entity Recognition Models to Large Language Models using Uncertainty](https://mlsanity.com/paper/2402.10573/) (2024)
- [MECT: Multi-Metadata Embedding based Cross-Transformer for Chinese Named Entity Recognition](https://mlsanity.com/paper/2107.05418/) (2021)
- [PUnifiedNER: A Prompting-based Unified NER System for Diverse Datasets](https://mlsanity.com/paper/2211.14838/) (2022)
- [Flat Multi-modal Interaction Transformer for Named Entity Recognition](https://mlsanity.com/paper/2208.11039/) (2022)
- [TOE: A Grid-Tagging Discontinuous NER Model Enhanced by Embedding Tag/Word Relations and More Fine-Grained Tags](https://mlsanity.com/paper/2211.00684/) (2022)
- [Delving Deep into Regularity: A Simple but Effective Method for Chinese Named Entity Recognition](https://mlsanity.com/paper/2204.05544/) (2022)
- [Masked Conditional Random Fields for Sequence Labeling](https://mlsanity.com/paper/2103.10682/) (2021)
- [Lattention: Lattice-attention in ASR rescoring](https://mlsanity.com/paper/2111.10157/) (2021)
- [PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition](https://mlsanity.com/paper/2402.04838/) (2024)
- [IEPile: Unearthing Large-Scale Schema-Based Information Extraction Corpus](https://mlsanity.com/paper/2402.14710/) (2024)
- [Medical Dialogue: A Survey of Categories, Methods, Evaluation and Challenges](https://mlsanity.com/paper/2405.10630/) (2024)

## Abstract (arXiv)

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.