Chinese NER Using Lattice LSTM

By Jie Yang. Annual Meeting of the Association for Computational Linguistics, 2018

772 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/8fb5a6fe93a3d19ffee50677c0ae563e3377d2d4

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Xipeng Qiu
2. Xuanjing Huang
3. Rui Wang
4. Fei Wu
5. Jiwei Li
6. Hang Yan
7. Yonatan Belinkov
8. Chenliang Li

Citations in the corpus

• A Chapter-Wise Understanding System for Text-To-Speech in Chinese Novels (2021, methodology): “Sequential labeling work has been conducted in Chinese NER [4, 5, 6, 7].”
• A Survey on Deep Learning for Named Entity Recognition (2018, background): “Zhang and Yang [149] proposed 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.”
• Dice Loss for Data-imbalanced NLP Tasks (2019, background): “• Lattice-LSTM: Zhang and Yang (2018) constructs a word-character lattice.”
• FLAT: Chinese NER Using Flat-Lattice Transformer (2020, background): “(1) One line is to design a model to be compatible with lattice input, such as lattice LSTM (Zhang and Yang, 2018) and LR-CNN (Gui et al., 2019a).”
• Simplify the Usage of Lexicon in Chinese NER (2019, methodology): “As a representative, Lattice-LSTM (Zhang and Yang, 2018) has achieved new benchmark results on several public Chinese NER datasets.”
• Lattice-Based Transformer Encoder for Neural Machine Translation (2019, methodology): “To enhance the representaions of the input, lattice has also been applied in many other NLP tasks such as named entity recognition (Zhang and Yang, 2018), Chinese word segmentation (Yang et al., 2019) and part-of-speech tagging (Jiang et al., 2008; Wang et al., 2013).”
• Unified Named Entity Recognition as Word-Word Relation Classification (2021, background): “In Table 9, we present the detailed statistics of 14 datasets, including CoNLL-2003 and OntoNotes 5.0 for English flat NER, OntoNotes 4.0, MSRA, Weibo, and Resume for Chinese flat NER, ACE 2004, ACE2005, and GENIA for English overlapped NER, ACE 2004 and ACE 2005 for Chinese overlapped NER, CADEC, ShA”
• TENER: Adapting Transformer Encoder for Named Entity Recognition (2019, methodology): “♣,♠ are results reported in (Zhang and Yang, 2018) and (Gui et al.”
• A Unified MRC Framework for Named Entity Recognition (2019, methodology): “Other works (Muis and Lu, 2017; Sohrab and Miwa, 2018; Zheng et al., 2019) also proposed various methods to tackle the nested NER problem.”