Corpus ID: 52012412

Convolutional Neural Network for Universal Sentence Embeddings

@inproceedings{Jiao2018ConvolutionalNN,
  title={Convolutional Neural Network for Universal Sentence Embeddings},
  author={Xiaoqi Jiao and F. Wang and D. Feng},
  booktitle={COLING},
  year={2018}
}
This paper proposes a simple CNN model for creating general-purpose sentence embeddings that can transfer easily across domains and can also act as effective initialization for downstream tasks. [...] Key Method In contrast, our model (CSE) utilizes both features of words and n-grams to encode sentences, which is actually a generalization of these bag-of-words models. The extensive experiments demonstrate that CSE performs better than average models in transfer learning setting and exceeds the state of the art…Expand
6 Citations
A MULTI-LAYER SYSTEM FOR SEMANTIC RELATEDNESS EVALUATION
  • 1
  • PDF
Contract Discovery: Dataset and a Few-shot Semantic Retrieval Challenge with Competitive Baselines
  • 3
  • PDF
Searching for Legal Clauses by Analogy. Few-shot Semantic Retrieval Shared Task
  • PDF
Ans2vec: A Scoring System for Short Answers
  • 6
Learning to Ask Screening Questions for Job Postings
  • 2
  • Highly Influenced
  • PDF

References

SHOWING 1-10 OF 40 REFERENCES
A Convolutional Neural Network for Modelling Sentences
  • 2,621
  • Highly Influential
  • PDF
Skip-Thought Vectors
  • 1,676
  • PDF
Towards Universal Paraphrastic Sentence Embeddings
  • 433
  • Highly Influential
  • PDF
Revisiting Recurrent Networks for Paraphrastic Sentence Embeddings
  • 64
  • Highly Influential
  • PDF
Unsupervised Learning of Sentence Embeddings Using Compositional n-Gram Features
  • 370
  • PDF
Convolutional Neural Networks for Sentence Classification
  • 8,058
  • PDF
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
  • 4,317
  • PDF
Convolutional Neural Network for Paraphrase Identification
  • 184
  • PDF
A Structured Self-attentive Sentence Embedding
  • 1,174
  • PDF
...
1
2
3
4
...