Results 11 to 20 of about 562,698 (308)
SimCSE: Simple Contrastive Learning of Sentence Embeddings [PDF]
Conference on Empirical Methods in Natural Language Processing, 2021 This paper presents SimCSE, a simple contrastive learning framework that greatly advances the state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive objective ...
Tianyu Gao, Xingcheng Yao, Danqi Chen
semanticscholar +1 more source
Sentence-T5: Scalable Sentence Encoders from Pre-trained Text-to-Text Models [PDF]
Findings, 2021 We provide the first exploration of sentence embeddings from text-to-text transformers (T5) including the effects of scaling up sentence encoders to 11B parameters. Sentence embeddings are broadly useful for language processing tasks.
Jianmo Ni +6 more
semanticscholar +1 more source
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer [PDF]
Annual Meeting of the Association for Computational Linguistics, 2021 Learning high-quality sentence representations benefits a wide range of natural language processing tasks. Though BERT-based pre-trained language models achieve high performance on many downstream tasks, the native derived sentence representations are ...
Yuanmeng Yan +5 more
semanticscholar +1 more source
Language-agnostic BERT Sentence Embedding [PDF]
Annual Meeting of the Association for Computational Linguistics, 2020 While BERT is an effective method for learning monolingual sentence embeddings for semantic similarity and embedding based transfer learning BERT based cross-lingual sentence embeddings have yet to be explored.
Fangxiaoyu Feng +4 more
semanticscholar +1 more source
DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings [PDF]
North American Chapter of the Association for Computational Linguistics, 2022 We propose DiffCSE, an unsupervised contrastive learning framework for learning sentence embeddings. DiffCSE learns sentence embeddings that are sensitive to the difference between the original sentence and an edited sentence, where the edited sentence ...
Yung-Sung Chuang +9 more
semanticscholar +1 more source
Making Monolingual Sentence Embeddings Multilingual Using Knowledge Distillation [PDF]
Conference on Empirical Methods in Natural Language Processing, 2020 We present an easy and efficient method to extend existing sentence embedding models to new languages. This allows to create multilingual versions from previously monolingual models.
Nils Reimers, Iryna Gurevych
semanticscholar +1 more source
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks [PDF]
Conference on Empirical Methods in Natural Language Processing, 2019 BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are fed into the network, which causes
Nils Reimers, Iryna Gurevych
semanticscholar +1 more source
A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference [PDF]
North American Chapter of the Association for Computational Linguistics, 2017 This paper introduces the Multi-Genre Natural Language Inference (MultiNLI) corpus, a dataset designed for use in the development and evaluation of machine learning models for sentence understanding.
Adina Williams +2 more
semanticscholar +1 more source
HellaSwag: Can a Machine Really Finish Your Sentence? [PDF]
Annual Meeting of the Association for Computational Linguistics, 2019 Recent work by Zellers et al. (2018) introduced a new task of commonsense natural language inference: given an event description such as “A woman sits at a piano,” a machine must select the most likely followup: “She sets her fingers on the keys.” With ...
Rowan Zellers +4 more
semanticscholar +1 more source
Convolutional Neural Networks for Sentence Classification [PDF]
Conference on Empirical Methods in Natural Language Processing, 2014 We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vectors for sentence-level classification tasks.
Yoon Kim
semanticscholar +1 more source