# Learning Semantic Textual Similarity from Conversations

arXiv: https://arxiv.org/abs/1804.07754 · HTML: https://mlsanity.com/paper/1804.07754/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Apr 2018.

## Built on by (most cited first, 30 of 41)

- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models](https://mlsanity.com/paper/2108.08877/) (2021)
- [Hash Layers For Large Sparse Models](https://mlsanity.com/paper/2106.04426/) (2021)
- [Whitening Sentence Representations for Better Semantics and Faster Retrieval](https://mlsanity.com/paper/2103.15316/) (2021)
- [BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage](https://mlsanity.com/paper/2208.03188/) (2022)
- [Language Models that Seek for Knowledge: Modular Search & Generation for Dialogue and Prompt Completion](https://mlsanity.com/paper/2203.13224/) (2022)
- [Same Author or Just Same Topic? Towards Content-Independent Style Representations](https://mlsanity.com/paper/2204.04907/) (2022)
- [User-LLM: Efficient LLM Contextualization with User Embeddings](https://mlsanity.com/paper/2402.13598/) (2024)
- [CoSQA: 20,000+ Web Queries for Code Search and Question Answering](https://mlsanity.com/paper/2105.13239/) (2021)
- [Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions](https://mlsanity.com/paper/2307.03941/) (2023)
- [Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks](https://mlsanity.com/paper/2101.10642/) (2021)
- [Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for Improved Cross-Modal Retrieval](https://mlsanity.com/paper/2103.11920/) (2021)
- [ConvFiT: Conversational Fine-Tuning of Pretrained Language Models](https://mlsanity.com/paper/2109.10126/) (2021)
- [DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings](https://mlsanity.com/paper/2109.12599/) (2021)
- [Staircase Attention for Recurrent Processing of Sequences](https://mlsanity.com/paper/2106.04279/) (2021)
- [Empathetic Conversational Systems: A Review of Current Advances, Gaps, and Opportunities](https://mlsanity.com/paper/2206.05017/) (2022)
- [Telling Stories through Multi-User Dialogue by Modeling Character Relations](https://mlsanity.com/paper/2105.15054/) (2021)
- [Learning to Generalize to More: Continuous Semantic Augmentation for Neural Machine Translation](https://mlsanity.com/paper/2204.06812/) (2022)
- [Malicious LLM-Based Conversational AI Makes Users Reveal Personal Information](https://mlsanity.com/paper/2506.11680/) (2025)
- [Situated Dialogue Learning through Procedural Environment Generation](https://mlsanity.com/paper/2110.03262/) (2021)
- [Aligning Cross-lingual Sentence Representations with Dual Momentum Contrast](https://mlsanity.com/paper/2109.00253/) (2021)
- [CheerBots: Chatbots toward Empathy and Emotionusing Reinforcement Learning](https://mlsanity.com/paper/2110.03949/) (2021)
- [CrisisTransformers: Pre-trained language models and sentence encoders for crisis-related social media texts](https://mlsanity.com/paper/2309.05494/) (2023)
- [Enhancing Semantic Similarity Understanding in Arabic NLP with Nested Embedding Learning](https://mlsanity.com/paper/2407.21139/) (2024)
- [Learning Federated Representations and Recommendations with Limited Negatives](https://mlsanity.com/paper/2108.07931/) (2021)
- [Semantic sentence similarity: size does not always matter](https://mlsanity.com/paper/2106.08648/) (2021)
- [Your Agent Can Defend Itself against Backdoor Attacks](https://mlsanity.com/paper/2506.08336/) (2025)
- [Put Chatbot into Its Interlocutor's Shoes: New Framework to Learn Chatbot Responding with Intention](https://mlsanity.com/paper/2103.16429/) (2021)
- [Unlocking Bias Detection: Leveraging Transformer-Based Models for Content Analysis](https://mlsanity.com/paper/2310.00347/) (2023)
- [UMBCLU at SemEval-2024 Task 1A and 1C: Semantic Textual Relatedness with and without machine translation](https://mlsanity.com/paper/2402.12730/) (2024)

## 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.