Universal Sentence Encoder
Explore this paper's citation graph
Summary
It is found that transfer learning using sentence embeddings tends to outperform word level transfer with surprisingly good performance with minimal amounts of supervised training data for a transfer task.
- Type
- preprint
- Published
- 2018-03-29
- Cited by
- 2,107
- References
- 28
- Access
- Open access
- OpenAlex
- https://openalex.org/W2794557536
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:4494896
Keywords
Computer science, Transfer of learning, Sentence, Encoder, Encoding (memory)
References
- Convolutional Neural Networks for Sentence Classification
- A large annotated corpus for learning natural language inference
- Implicit and Explicit Stigmatizing Attitudes and Stereotypes About Depression
- Annotating Expressions of Opinions and Emotions in Language
- Long Short-Term Memory
- Harvesting implicit group attitudes and beliefs from a demonstration web site
- Learning Question Classifiers
- A Sentimental Education: Sentiment Analysis Using Subjectivity Summarization Based on Minimum Cuts
- Measuring individual differences in implicit cognition: the implicit association test.
- Are Emily and Greg More Employable than Lakisha and Jamal? A Field Experiment on Labor Market Discrimination
- Distributed Representations of Words and Phrases and their Compositionality
- Mining and summarizing customer reviews
- Seeing Stars: Exploiting Class Relationships for Sentiment Categorization with Respect to Rating Scales
- Deep Unordered Composition Rivals Syntactic Methods for Text Classification
- GloVe: Global Vectors for Word Representation
- Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
- Efficient Natural Language Response Suggestion for Smart Reply
- Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
- Google Vizier: A Service for Black-Box Optimization
- SemEval-2017 Task 1: Semantic Textual Similarity Multilingual and Crosslingual Focused Evaluation
Cited by
- A Study on Passage Re-ranking in Embedding based Unsupervised Semantic Search
- Multi-Label Transfer Learning for Semantic Similarity
- On Accurate Evaluation of GANs for Language Generation
- Evaluation of sentence embeddings in downstream and linguistic probing tasks
- Neural Machine Translation for Query Construction and Composition
- Large Scale Language Modeling: Converging on 40GB of Text in Four Hours
- Effective Parallel Corpus Mining using Bilingual Sentence Embeddings
- Latent Dirichlet Allocation (LDA) for Topic Modeling of the CFPB Consumer Complaints
- Thou shalt not hate: Countering Online Hate Speech
- Fake Sentence Detection as a Training Task for Sentence Encoding
- Adversarial Decomposition of Text Representation
- Similarity-Based Reconstruction Loss for Meaning Representation
- IEST: WASSA-2018 Implicit Emotions Shared Task
- XNLI: Evaluating Cross-lingual Sentence Representations
- Learning Universal Sentence Representations with Mean-Max Attention Autoencoder
- Learning Robust, Transferable Sentence Representations for Text Classification
- Learning Finer-class Networks for Universal Representations
- Zero-training Sentence Embedding via Orthogonal Basis
- ResumeNet: A Learning-Based Framework for Automatic Resume Quality Assessment
- BioSentVec: creating sentence embeddings for biomedical texts
Related papers
- Embedding as a modeling problem
- Design and Realization of RS Encoder Based on FPGA
- A solution to the reversible embedding problem for finite Markov chains
- Development of an HDTV MPEG-2 encoder based on multiple enhanced SDTV encoding LSIs
- Iterative Machine-Learning-Based Method of Selecting Encoder Parameters for Speed-Bitrate Tradeoff
- An efficient encoder for distributed real-time applications
- A New Encoding Scheme for an Absolute Digital Encoder in Units of Degrees
- A touch sensitive X-Y position encoder for computer input