mlsanityData to 14 Oct 2026

DefSent: Sentence Embeddings using Definition Sentences

arXiv 2105.04339 ↗First posted 10 May 2021cs.CLcited by 20

Not on the map. Why?

Abstract (arXiv)

Sentence embedding methods using natural language inference (NLI) datasets have been successfully applied to various tasks. However, these methods are only available for limited languages due to relying heavily on the large NLI datasets. In this paper, we propose DefSent, a sentence embedding method that uses definition sentences from a word dictionary, which performs comparably on unsupervised semantics textual similarity (STS) tasks and slightly better on SentEval tasks than conventional methods. Since dictionaries are available for many languages, DefSent is more broadly applicable than methods using NLI datasets without constructing additional datasets. We demonstrate that DefSent performs comparably on unsupervised semantics textual similarity (STS) tasks and slightly better on SentEval tasks to the methods using large NLI datasets. Our code is publicly available at https://github.com/hpprc/defsent .

Key facts. Cited by 20 papers in the map (data through 14 Oct 2026). Builds on 12 of its 26 references that are in the map. First posted on arXiv 10 May 2021.

Builds on

12 of 26 references.

References · 12

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,372
  5. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  6. 2017A Broad-Coverage Challenge Corpus for Sentence Understanding through Inferencecited by 2,682
  7. 2015A large annotated corpus for learning natural language inferencecited by 1,847
  8. 2017SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluationcited by 1,001
  9. 2018Universal Sentence Encodercited by 489
  10. 2017Supervised Learning of Universal Sentence Representations from Natural Language Inference Datacited by 432
  11. 2018SentEval: An Evaluation Toolkit for Universal Sentence Representationscited by 294
  12. 2015Learning to Understand Phrases by Embedding the Dictionarycited by 33

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 6; 2023: 5; 2024: 4; 2025: 3; 2026: 2.

20 papers.

Sort:

By area:

  1. 2023Scaling Sentence Embeddings with Large Language Modelscited by 85
  2. 2022PromptBERT: Improving BERT Sentence Embeddings with Promptscited by 75
  3. 2024LLMs are Also Effective Embedding Models: An In-depth Overviewcited by 32
  4. 2022DR.BENCH: Diagnostic Reasoning Benchmark for Clinical Natural Language Processingcited by 14
  5. 2022Learning Disentangled Representations for Natural Language Definitionscited by 12
  6. 2022DictBERT: Dictionary Description Knowledge Enhanced Language Model Pre-training via Contrastive Learningcited by 11
  7. 2025Redundancy, Isotropy, and Intrinsic Dimensionality of Prompt-based Text Embeddingscited by 11
  8. 2022Non-Linguistic Supervision for Contrastive Learning of Sentence Embeddingscited by 10
  9. 2025Pool Me Wisely: On the Effect of Pooling in Transformer-Based Modelscited by 6
  10. 2023Multi-Relational Hyperbolic Word Embeddings from Natural Language Definitionscited by 4
  11. 2022Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signalscited by 3
  12. 2023Unsupervised Sentence Representation Learning with Frequency-induced Adversarial Tuning and Incomplete Sentence Filteringcited by 3
8 more
  1. 2024Improving Sentence Embeddings with Automatic Generation of Training Data Using Few-shot Examplescited by 3
  2. 2024S~onajaht: Definition Embeddings and Semantic Search for Reverse Dictionary Creationcited by 2
  3. 2023Sentence Representations via Gaussian Embeddingcited by 1
  4. 2023Machine Learning and Statistical Approaches to Measuring Similarity of Political Partiescited by 0
  5. 2024DefSent+: Improving sentence embeddings of language models by projecting definition sentences into a quasi-isotropic or isotropic vector space of unlimited dictionary entriescited by 0
  6. 2025FrameEOL: Semantic Frame Induction using Causal Language Modelscited by 0
  7. 2026A Good Talk Does not Look Like a Summary, It Teaches You! Measuring Takeaways from Paper-to-Video Talkscited by 0
  8. 2026Predicting Multilingual Classification and Translation Performance of LLMs with Cross-Lingual Alignment -- Is English Enough?cited by 0