mlsanityData to 7 Oct 2026

Learning Semantic Textual Similarity from Conversations

arXiv 1804.07754 ↗First posted 20 Apr 2018cs.CLcited by 41

Not on the map. Why?

Abstract (arXiv)

We present a novel approach to learn representations for sentence-level semantic similarity using conversational data. Our method trains an unsupervised model to predict conversational input-response pairs. The resulting sentence embeddings perform well on the semantic textual similarity (STS) benchmark and SemEval 2017's Community Question Answering (CQA) question similarity subtask. Performance is further improved by introducing multitask training combining the conversational input-response prediction task and a natural language inference task. Extensive experiments show the proposed model achieves the best performance among all neural models on the STS benchmark and is competitive with the state-of-the-art feature engineered and mixed systems in both tasks.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 19; 2022: 9; 2023: 4; 2024: 5; 2025: 4.

41 papers.

Sort:

By area:

  1. 2022MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledgecited by 469
  2. 2021Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Modelscited by 462
  3. 2021Hash Layers For Large Sparse Modelscited by 236
  4. 2021Whitening Sentence Representations for Better Semantics and Faster Retrievalcited by 198
  5. 2022BlenderBot 3: a deployed conversational agent that continually learns to responsibly engagecited by 197
  6. 2022Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completioncited by 102
  7. 2022Same Author or Just Same Topic? Towards Content-Independent Style Representationscited by 83
  8. 2021CoSQA: 20,000+ Web Queries for Code Search and Question Answeringcited by 74
  9. 2024User-LLM: Efficient LLM Contextualization with User Embeddingscited by 74
  10. 2023Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutionscited by 59
  11. 2021Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Taskscited by 32
  12. 2021Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrievalcited by 27
29 more
  1. 2021ConvFiT: Conversational Fine-Tuning of Pretrained Language Modelscited by 25
  2. 2021DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddingscited by 19
  3. 2022Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunitiescited by 14
  4. 2021Telling Stories through Multi-User Dialogue by Modeling Character Relationscited by 13
  5. 2021Staircase Attention for Recurrent Processing of Sequencescited by 13
  6. 2022Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translationcited by 13
  7. 2025Malicious LLM-Based Conversational AI Makes Users Reveal Personal Informationcited by 10
  8. 2021Situated Dialogue Learning through Procedural Environment Generationcited by 9
  9. 2021Aligning Cross-lingual Sentence Representations with Dual Momentum Contrastcited by 7
  10. 2021CheerBots: Chatbots toward Empathy and Emotionusing Reinforcement Learningcited by 7
  11. 2023CrisisTransformers: Pre-trained language models and sentence encoders for crisis-related social media textscited by 7
  12. 2024Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learningcited by 7
  13. 2021Learning Federated Representations and Recommendations with Limited Negativescited by 6
  14. 2021Semantic sentence similarity: size does not always mattercited by 5
  15. 2021Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intentioncited by 4
  16. 2023Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysiscited by 4
  17. 2025Your Agent Can Defend Itself against Backdoor Attackscited by 4
  18. 2024UMBCLU at SemEval-2024 Task 1A and 1C: Semantic Textual Relatedness with and without machine translationcited by 3
  19. 2021Batch-Softmax Contrastive Loss for Pairwise Sentence Scoring Taskscited by 2
  20. 2024A Collection of Pragmatic-Similarity Judgments over Spoken Dialog Utterancescited by 2
  21. 2022EMS: Efficient and Effective Massively Multilingual Sentence Embedding Learningcited by 1
  22. 2022Multimodal Learning for Non-small Cell Lung Cancer Prognosiscited by 1
  23. 2022Conciseness: An Overlooked Language Taskcited by 1
  24. 2024Semantically Enriched Cross-Lingual Sentence Embeddings for Crisis-related Social Media Textscited by 1
  25. 2021SentEmojiBot: Empathising Conversations Generation with Emojiscited by 0
  26. 2021A Case Study to Reveal if an Area of Interest has a Trend in Ongoing Tweets Using Word and Sentence Embeddingscited by 0
  27. 2023KeyGen2Vec: Learning Document Embedding via Multi-label Keyword Generation in Question-Answeringcited by 0
  28. 2025On the Effectiveness of Integration Methods for Multimodal Dialogue Response Retrievalcited by 0
  29. 2025TurkEmbed: Turkish Embedding Model on NLI & STS Taskscited by 0