Automatic Construction of Sememe Knowledge Bases via Dictionaries
Not on the map. Why?
Abstract (arXiv)
A sememe is defined as the minimum semantic unit in linguistics. Sememe knowledge bases (SKBs), which comprise words annotated with sememes, enable sememes to be applied to natural language processing. So far a large body of research has showcased the unique advantages and effectiveness of SKBs in various tasks. However, most languages have no SKBs, and manual construction of SKBs is time-consuming and labor-intensive. To tackle this challenge, we propose a simple and fully automatic method of building an SKB via an existing dictionary. We use this method to build an English SKB and a French SKB, and conduct comprehensive evaluations from both intrinsic and extrinsic perspectives. Experimental results demonstrate that the automatically built English SKB is even superior to HowNet, the most widely used SKB that takes decades to build manually. And both the English and French SKBs can bring obvious performance enhancement in multiple downstream tasks. All the code and data of this paper (except the copyrighted dictionaries) can be obtained at https://github.com/thunlp/DictSKB.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 27 of its 84 references that are in the map. First posted on arXiv 26 May 2021.
Builds on
27 of 84 references.
References · 27
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
- 2013Intriguing properties of neural networkscited by 5,155
- 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,057
- 2016Pointer Sentinel Mixture Modelscited by 3,096
- 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
- 2015A large annotated corpus for learning natural language inferencecited by 1,847
- 2018XNLI: Evaluating Cross-lingual Sentence Representationscited by 915
- 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 723
- 2018AllenNLP: A Deep Semantic Natural Language Processing Platformcited by 347
- 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 237
- 2017Regularizing and Optimizing LSTM Language Modelscited by 205
- 2014Recurrent Neural Network Regularizationcited by 189
15 more
- 2019FlauBERT: Unsupervised Language Model Pre-training for Frenchcited by 153
- 2020The Multilingual Amazon Reviews Corpuscited by 143
- 2019GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledgecited by 79
- 2020Moving Down the Long Tail of Word Sense Disambiguation with Gloss-Informed Biencoderscited by 61
- 2019Word-level Textual Adversarial Attacking as Combinatorial Optimizationcited by 37
- 2015Learning to Understand Phrases by Embedding the Dictionarycited by 33
- 2019OpenHowNet: An Open Sememe-based Lexical Knowledge Basecited by 21
- 2018Incorporating Glosses into Neural Word Sense Disambiguationcited by 18
- 2019Multi-channel Reverse Dictionary Modelcited by 16
- 2017Learning to Compute Word Embeddings On the Flycited by 12
- 2019Modeling Semantic Compositionality with Sememe Knowledgecited by 8
- 2019Using BERT for Word Sense Disambiguationcited by 7
- 2018Language Modeling with Sparse Product of Sememe Expertscited by 6
- 2019Towards Building a Multilingual Sememe Knowledge Base: Predicting Sememes for BabelNet Synsetscited by 6
- 2018Incorporating Chinese Characters of Words for Lexical Sememe Predictioncited by 3
Built on by
Citing papers per year: 2022: 1.
1 paper.