Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
Explore this paper's citation graph
Summary
Sentence-BERT (SBERT), a modification of the pretrained BERT network that use siamese and triplet network structures to derive semantically meaningful sentence embeddings that can be compared using cosine-similarity is presented.
- Type
- article
- Published
- 2019-08-14
- Cited by
- 20,101
- References
- 38
- Access
- Open access
- OpenAlex
- https://openalex.org/W2970641574
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:201646309
Keywords
Sentence, Computer science, Artificial intelligence, Natural language processing
References
- A large annotated corpus for learning natural language inference
- Unsupervised Construction of Large Paraphrase Corpora: Exploiting Massively Parallel News Sources
- Annotating Expressions of Opinions and Emotions in Language
- Learning Question Classifiers
- FaceNet: A unified embedding for face recognition and clustering
- A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts
- SemEval-2014 Task 10: Multilingual Semantic Textual Similarity
- SemEval-2015 Task 2: Semantic Textual Similarity, English, Spanish and Pilot on Interpretability
- *SEM 2013 shared task: Semantic Textual Similarity
- Mining and summarizing customer reviews
- Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales
- GloVe: Global Vectors for Word Representation
- A SICK cure for the evaluation of compositional distributional semantic models
- SemEval-2012 Task 6: A Pilot on Semantic Textual Similarity
- Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
- Learning Distributed Representations of Sentences from Unlabelled Data
- SemEval-2016 Task 1: Semantic Textual Similarity, Monolingual and Cross-Lingual Evaluation
- Measuring the Similarity of Sentential Arguments in Dialogue
- Task-Oriented Intrinsic Evaluation of Semantic Textual Similarity
- Billion-Scale Similarity Search with GPUs
Cited by
- Productivity, Portability, Performance: Data-Centric Python
- Deep Learning for Matching in Search and Recommendation
- On the Evaluation of Conditional GANs
- Pairwise learning to rank by neural networks revisited: reconstruction, theoretical analysis and practical performance
- Comprehensive Analysis of Aspect Term Extraction Methods using Various Text Embeddings
- Situating Sentence Embedders with Nearest Neighbor Overlap
- INSET: Sentence Infilling with Inter-sentential Generative Pre-training
- Searching for Legal Clauses by Analogy. Few-shot Semantic Retrieval Shared Task
- Sentence Meta-Embeddings for Unsupervised Semantic Textual Similarity
- A Bilingual Generative Transformer for Semantic Sentence Embedding
- Siamese Networks for Large-Scale Author Identification
- BERT has a Moral Compass: Improvements of ethical and moral values of machines
- Multi-level Head-wise Match and Aggregation in Transformer for Textual Sequence Matching
- Emu: Enhancing Multilingual Sentence Embeddings with Semantic Specialization
- Quo Vadis, Math Information Retrieval
- Learning Entailment-Based Sentence Embeddings from Natural Language Inference
- Improving Sentence Representations via Component Focusing
- Monotonic Cardinality Estimation of Similarity Selection: A Deep Learning Approach
- Hierarchical Transformer Network for Utterance-level Emotion Recognition
- Event sequence metric learning
Related papers
- Using DataGrid Control to Realize DataBase of Querying in VB6.0
- Study and Two Types of Typical Usage of DataGrid Web Server Control
- PACWON: A parallelizing compiler for workstations on a network
- Bidirectional Sort and Choosing a Row to Update or Delete by Click Any Cell in DataGrid
- Flexible Application of VSFlexGrid
- Query Caching Method for Distributed Web Caching
- Export Paging DataGrid files Based on.NET