mlsanityData to 7 Oct 2026

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

arXiv 2102.12671 ↗First posted 25 Feb 2021cs.CL cs.AIcited by 15

Not on the map. Why?

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.

Key facts. Cited by 15 papers in the map (data through 7 Oct 2026). Builds on 22 of its 43 references that are in the map. First posted on arXiv 25 Feb 2021.

Builds on

22 of 43 references.

References · 22

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2018Graph Convolutional Networks for Text Classificationcited by 345
  4. 2019K-BERT: Enabling Language Representation with Knowledge Graphcited by 303
  5. 2019ERNIE: Enhanced Representation through Knowledge Integrationcited by 301
  6. 2016Enhanced LSTM for Natural Language Inferencecited by 199
  7. 2018Neural Approaches to Conversational AIcited by 164
  8. 2017Bilateral Multi-Perspective Matching for Natural Language Sentencescited by 120
  9. 2017DiSAN: Directional Self-Attention Network for RNN/CNN-Free Language Understandingcited by 71
  10. 2020FLAT: Chinese NER Using Flat-Lattice Transformercited by 67
  11. 2017Natural Language Inference over Interaction Spacecited by 34
  12. 2020Efficient Context and Schema Fusion Networks for Multi-Domain Dialogue State Trackingcited by 27
10 more
  1. 2018Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answeringcited by 23
  2. 2019OpenHowNet: An Open Sememe-based Lexical Knowledge Basecited by 21
  3. 2019Is Word Segmentation Necessary for Deep Learning of Chinese Representations?cited by 18
  4. 2019PKUSEG: A Toolkit for Multi-Domain Chinese Word Segmentationcited by 17
  5. 2015Text-Attentional Convolutional Neural Networks for Scene Text Detectioncited by 12
  6. 2019AgentGraph: Towards Universal Dialogue Management with Structured Deep Reinforcement Learningcited by 12
  7. 2020Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Managementcited by 12
  8. 2019Enhancing Pre-trained Chinese Character Representation with Word-aligned Attentioncited by 7
  9. 2018Language Modeling with Sparse Product of Sememe Expertscited by 6
  10. 2019Lattice CNNs for Matching Based Chinese Question Answeringcited by 5

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 6; 2023: 4; 2024: 2.

15 papers.

Sort:

  1. 2021LGESQL: Line Graph Enhanced Text-to-SQL Model with Mixed Local and Non-Local Relationscited by 119
  2. 2022A Survey of Knowledge Enhanced Pre-trained Language Modelscited by 76
  3. 2021ShadowGNN: Graph Projection Neural Network for Text-to-SQL Parsercited by 35
  4. 2021Lattice-BERT: Leveraging Multi-Granularity Representations in Chinese Pre-trained Language Modelscited by 19
  5. 2022A Hierarchical N-Gram Framework for Zero-Shot Link Predictioncited by 9
  6. 2022TIE: Topological Information Enhanced Structural Reading Comprehension on Web Pagescited by 4
  7. 2024Enhancing Text-to-SQL Capabilities of Large Language Models via Domain Database Knowledge Injectioncited by 2
  8. 2022Context Enhanced Short Text Matching using Clickthrough Datacited by 1
  9. 2022Sememe Prediction for BabelNet Synsets using Multilingual and Multimodal Informationcited by 1
  10. 2022Tri-Attention: Explicit Context-Aware Attention Mechanism for Natural Language Processingcited by 1
  11. 2023Shuo Wen Jie Zi: Rethinking Dictionaries and Glyphs for Chinese Language Pre-trainingcited by 1
  12. 2023Co-Driven Recognition of Semantic Consistency via the Fusion of Transformer and HowNet Sememes Knowledgecited by 0
3 more
  1. 2023The Short Text Matching Model Enhanced with Knowledge via Contrastive Learningcited by 0
  2. 2023HICL: Hashtag-Driven In-Context Learning for Social Media Natural Language Understandingcited by 0
  3. 2024SememeLM: A Sememe Knowledge Enhanced Method for Long-tail Relation Representationcited by 0