# LET: Linguistic Knowledge Enhanced Graph Transformer for Chinese Short Text Matching

arXiv: https://arxiv.org/abs/2102.12671 · HTML: https://mlsanity.com/paper/2102.12671/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 43 references that are in the map.
- First posted on arXiv 25 Feb 2021.

## Builds on (most cited first, 22 of 22)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation](https://mlsanity.com/paper/1406.1078/) (2014)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [K-BERT: Enabling Language Representation with Knowledge Graph](https://mlsanity.com/paper/1909.07606/) (2019)
- [ERNIE: Enhanced Representation through Knowledge Integration](https://mlsanity.com/paper/1904.09223/) (2019)
- [Enhanced LSTM for Natural Language Inference](https://mlsanity.com/paper/1609.06038/) (2016)
- [Neural Approaches to Conversational AI](https://mlsanity.com/paper/1809.08267/) (2018)
- [Bilateral Multi-Perspective Matching for Natural Language Sentences](https://mlsanity.com/paper/1702.03814/) (2017)
- [DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understanding](https://mlsanity.com/paper/1709.04696/) (2017)
- [FLAT: Chinese NER Using Flat-Lattice Transformer](https://mlsanity.com/paper/2004.11795/) (2020)
- [Natural Language Inference over Interaction Space](https://mlsanity.com/paper/1709.04348/) (2017)
- [Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Tracking](https://mlsanity.com/paper/2004.03386/) (2020)
- [Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering](https://mlsanity.com/paper/1806.04330/) (2018)
- [OpenHowNet: An Open Sememe-based Lexical Knowledge Base](https://mlsanity.com/paper/1901.09957/) (2019)
- [Is Word Segmentation Necessary for Deep Learning of Chinese Representations?](https://mlsanity.com/paper/1905.05526/) (2019)
- [PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentation](https://mlsanity.com/paper/1906.11455/) (2019)
- [Text-Attentional Convolutional Neural Networks for Scene Text Detection](https://mlsanity.com/paper/1510.03283/) (2015)
- [AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learning](https://mlsanity.com/paper/1905.11259/) (2019)
- [Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management](https://mlsanity.com/paper/2009.10326/) (2020)
- [Enhancing Pre-trained Chinese Character Representation with Word-aligned Attention](https://mlsanity.com/paper/1911.02821/) (2019)
- [Language Modeling with Sparse Product of Sememe Experts](https://mlsanity.com/paper/1810.12387/) (2018)
- [Lattice CNNs for Matching Based Chinese Question Answering](https://mlsanity.com/paper/1902.09087/) (2019)

## Built on by (most cited first, 15 of 15)

- [LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relations](https://mlsanity.com/paper/2106.01093/) (2021)
- [A Survey of Knowledge Enhanced Pre-trained Language Models](https://mlsanity.com/paper/2211.05994/) (2022)
- [ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parser](https://mlsanity.com/paper/2104.04689/) (2021)
- [Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Models](https://mlsanity.com/paper/2104.07204/) (2021)
- [A Hierarchical N-Gram Framework for Zero-Shot Link Prediction](https://mlsanity.com/paper/2204.10293/) (2022)
- [TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pages](https://mlsanity.com/paper/2205.06435/) (2022)
- [Enhancing Text-to-SQL Capabilities of Large Language Models via Domain Database Knowledge Injection](https://mlsanity.com/paper/2409.15907/) (2024)
- [Context Enhanced Short Text Matching using Clickthrough Data](https://mlsanity.com/paper/2203.01849/) (2022)
- [Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Information](https://mlsanity.com/paper/2203.07426/) (2022)
- [Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processing](https://mlsanity.com/paper/2211.02899/) (2022)
- [Shuo Wen Jie Zi: Rethinking Dictionaries and Glyphs for Chinese Language Pre-training](https://mlsanity.com/paper/2305.18760/) (2023)
- [Co-Driven Recognition of Semantic Consistency via the Fusion of Transformer and HowNet Sememes Knowledge](https://mlsanity.com/paper/2302.10570/) (2023)
- [The Short Text Matching Model Enhanced with Knowledge via Contrastive Learning](https://mlsanity.com/paper/2304.03898/) (2023)
- [HICL: Hashtag-Driven In-Context Learning for Social Media Natural Language Understanding](https://mlsanity.com/paper/2308.09985/) (2023)
- [SememeLM: A Sememe Knowledge Enhanced Method for Long-tail Relation Representation](https://mlsanity.com/paper/2406.10297/) (2024)

## Abstract (arXiv)

Chinese short text matching is a fundamental task in natural language processing. Existing approaches usually take Chinese characters or words as input tokens. They have two limitations: 1) Some Chinese words are polysemous, and semantic information is not fully utilized. 2) Some models suffer potential issues caused by word segmentation. Here we introduce HowNet as an external knowledge base and propose a Linguistic knowledge Enhanced graph Transformer (LET) to deal with word ambiguity. Additionally, we adopt the word lattice graph as input to maintain multi-granularity information. Our model is also complementary to pre-trained language models. Experimental results on two Chinese datasets show that our models outperform various typical text matching approaches. Ablation study also indicates that both semantic information and multi-granularity information are important for text matching modeling.