Word Sense Induction with Neural biLM and Symmetric Patterns
Not on the map. Why?
Abstract (arXiv)
An established method for Word Sense Induction (WSI) uses a language model to predict probable substitutes for target words, and induces senses by clustering these resulting substitute vectors. We replace the ngram-based language model (LM) with a recurrent one. Beyond being more accurate, the use of the recurrent LM allows us to effectively query it in a creative way, using what we call dynamic symmetric patterns. The combination of the RNN-LM and the dynamic symmetric patterns results in strong substitute vectors for WSI, allowing to surpass the current state-of-the-art on the SemEval 2013 WSI shared task by a large margin.
Key facts. Cited by 18 papers in the map (data through 14 Oct 2026). First posted on arXiv 26 Aug 2018.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 7; 2022: 5; 2023: 0; 2024: 4; 2025: 2.
18 papers.
Sort:
By area:
- 2022Leveraging Large Language Models for Multiple Choice Question Answeringcited by 203
- 2022An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labelscited by 89
- 2021Characterizing English Variation across Social Media Communities with BERTcited by 20
- 2021Corpus-based Open-Domain Event Type Inductioncited by 18
- 2022Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitutioncited by 12
- 2021Language Models for Lexical Inference in Contextcited by 9
- 2021Large Scale Substitution-based Word Sense Inductioncited by 9
- 2021PolyLM: Learning about Polysemy through Language Modelingcited by 5
- 2025Multi-Sense Embeddings for Language Models and Knowledge Distillationcited by 3
- 2022BOS at LSCDiscovery: Lexical Substitution for Interpretable Lexical Semantic Change Detectioncited by 2
- 2021Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Inductioncited by 1
- 2024Multilingual Substitution-based Word Sense Inductioncited by 1
6 more
- 2021Language models in word sense disambiguation for Polishcited by 0
- 2022Word Sense Induction with Hierarchical Clustering and Mutual Information Maximizationcited by 0
- 2024Semantic Cells: Evolutional Process to Acquire Sense Diversity of Itemscited by 0
- 2024Analyzing Polysemy Evolution Using Semantic Cellscited by 0
- 2024Deep-change at AXOLOTL-24: Orchestrating WSD and WSI Models for Semantic Change Modelingcited by 0
- 2025Emergent Lexical Semantics in Neural Language Models: Testing Martin's Law on LLM-Generated Textcited by 0
- 2025Emergent Lexical Semantics in Neural Language Models: Testing Martin's Law on LLM-Generated Text26 Nov 2025
- 2025Multi-Sense Embeddings for Language Models and Knowledge Distillation8 Apr 2025
- 2024Deep-change at AXOLOTL-24: Orchestrating WSD and WSI Models for Semantic Change Modeling9 Aug 2024
- 2024Analyzing Polysemy Evolution Using Semantic Cells23 Jul 2024
- 2024Multilingual Substitution-based Word Sense Induction17 May 2024
- 2024Semantic Cells: Evolutional Process to Acquire Sense Diversity of Items23 Apr 2024
- 2022Leveraging Large Language Models for Multiple Choice Question Answering22 Oct 2022
- 2022Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization11 Oct 2022
- 2022BOS at LSCDiscovery: Lexical Substitution for Interpretable Lexical Semantic Change Detection7 Jun 2022
- 2022Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution7 Jun 2022
- 2022An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels21 Mar 2022
- 2021Language models in word sense disambiguation for Polish27 Nov 2021
6 more
- 2021Large Scale Substitution-based Word Sense Induction14 Oct 2021
- 2021Corpus-based Open-Domain Event Type Induction7 Sep 2021
- 2021Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Induction27 May 2021
- 2021Characterizing English Variation across Social Media Communities with BERT12 Feb 2021
- 2021Language Models for Lexical Inference in Context10 Feb 2021
- 2021PolyLM: Learning about Polysemy through Language Modeling25 Jan 2021
- 2022Leveraging Large Language Models for Multiple Choice Question Answeringcited by 203
- 2022An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labelscited by 89
- 2021Characterizing English Variation across Social Media Communities with BERTcited by 20
- 2021Corpus-based Open-Domain Event Type Inductioncited by 18
- 2022Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitutioncited by 12
- 2021Language Models for Lexical Inference in Contextcited by 9
- 2021Large Scale Substitution-based Word Sense Inductioncited by 9
- 2021PolyLM: Learning about Polysemy through Language Modelingcited by 5
- 2022BOS at LSCDiscovery: Lexical Substitution for Interpretable Lexical Semantic Change Detectioncited by 2
- 2021Verb Sense Clustering using Contextualized Word Representations for Semantic Frame Inductioncited by 1
- 2024Multilingual Substitution-based Word Sense Inductioncited by 1
- 2021Language models in word sense disambiguation for Polishcited by 0
12 most cited of 17 All 17 (JSON)
- 2025Emergent Lexical Semantics in Neural Language Models: Testing Martin's Law on LLM-Generated Text26 Nov 2025
- 2024Deep-change at AXOLOTL-24: Orchestrating WSD and WSI Models for Semantic Change Modeling9 Aug 2024
- 2024Analyzing Polysemy Evolution Using Semantic Cells23 Jul 2024
- 2024Multilingual Substitution-based Word Sense Induction17 May 2024
- 2024Semantic Cells: Evolutional Process to Acquire Sense Diversity of Items23 Apr 2024
- 2022Leveraging Large Language Models for Multiple Choice Question Answering22 Oct 2022
- 2022Word Sense Induction with Hierarchical Clustering and Mutual Information Maximization11 Oct 2022
- 2022BOS at LSCDiscovery: Lexical Substitution for Interpretable Lexical Semantic Change Detection7 Jun 2022
- 2022Always Keep your Target in Mind: Studying Semantics and Improving Performance of Neural Lexical Substitution7 Jun 2022
- 2022An Information-theoretic Approach to Prompt Engineering Without Ground Truth Labels21 Mar 2022
- 2021Language models in word sense disambiguation for Polish27 Nov 2021
- 2021Large Scale Substitution-based Word Sense Induction14 Oct 2021
12 newest of 17 All 17 (JSON)