LCT-MALTA's Submission to RepEval 2017 Shared Task

Vu, Hoa Trong; Pham, Thuong-Hai; Bai, Xiaoyu; Tanti, Marc; Plas, Lonneke van der; Gatt, Albert

doi:10.18653/v1/w17-5311

Cited by 3 publications

References 13 publications

(15 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

Sentence embeddings in NLI with iterative refinement encoders

2019

View full text Add to dashboard Cite

Sentence-level representations are necessary for various NLP tasks. Recurrent neural networks have proven to be very effective in learning distributed representations and can be trained efficiently on natural language inference tasks. We build on top of one such model and propose a hierarchy of BiLSTM and max pooling layers that implements an iterative refinement strategy and yields state of the art results on the SciTail dataset as well as strong results for SNLI and MultiNLI. We can show that the sentence embeddings learned in this way can be utilized in a wide variety of transfer learning tasks, outperforming InferSent on 7 out of 10 and SkipThought on 8 out of 9 SentEval sentence embedding evaluation tasks. Furthermore, our model beats the InferSent model in 8 out of 10 recently published SentEval probing tasks designed to evaluate sentence embeddings' ability to capture some of the important linguistic properties of sentences.

show abstract

Sentence embeddings in NLI with iterative refinement encoders

2019

View full text Add to dashboard Cite

show abstract

Clustering and Network Analysis for the Embedding Spaces of Sentences and Sub-Sentences

Kalinowski

Greenberg

2021

2021 Second International Conference on Intelligent Data Science Technologies and Applications (IDSTA)

View full text Add to dashboard Cite

The RepEval 2017 Shared Task: Multi-Genre Natural Language Inference with Sentence Representations

Nangia

Williams

Lazaridou

et al. 2017

Proceedings of the 2nd Workshop on Evaluating Vector Space Representations for NLP

View full text Add to dashboard Cite

This paper presents the results of the RepEval 2017 Shared Task, which evaluated neural network sentence representation learning models on the MultiGenre Natural Language Inference corpus (MultiNLI) recently introduced by Williams et al. (2017). All of the five participating teams beat the bidirectional LSTM (BiLSTM) and continuous bag of words baselines reported in Williams et al.. The best single model used stacked BiLSTMs with residual connections to extract sentence features and reached 74.5% accuracy on the genre-matched test set. Surprisingly, the results of the competition were fairly consistent across the genrematched and genre-mismatched test sets, and across subsets of the test data representing a variety of linguistic phenomena, suggesting that all of the submitted systems learned reasonably domainindependent representations for sentence meaning.

show abstract

LCT-MALTA's Submission to RepEval 2017 Shared Task

Cited by 3 publications

References 13 publications

Sentence embeddings in NLI with iterative refinement encoders

Sentence embeddings in NLI with iterative refinement encoders

Clustering and Network Analysis for the Embedding Spaces of Sentences and Sub-Sentences

The RepEval 2017 Shared Task: Multi-Genre Natural Language Inference with Sentence Representations

Contact Info

Product

Resources

About