# Refining Raw Sentence Representations for Textual Entailment Recognition via Attention

arXiv: https://arxiv.org/abs/1707.03103 · HTML: https://mlsanity.com/paper/1707.03103/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Jul 2017.

## Built on by (most cited first, 1 of 1)

- [EDeR: A Dataset for Exploring Dependency Relations Between Events](https://mlsanity.com/paper/2304.01612/) (2023)

## Abstract (arXiv)

In this paper we present the model used by the team Rivercorners for the 2017 RepEval shared task. First, our model separately encodes a pair of sentences into variable-length representations by using a bidirectional LSTM. Later, it creates fixed-length raw representations by means of simple aggregation functions, which are then refined using an attention mechanism. Finally it combines the refined representations of both sentences into a single vector to be used for classification. With this model we obtained test accuracies of 72.057% and 72.055% in the matched and mismatched evaluation tracks respectively, outperforming the LSTM baseline, and obtaining performances similar to a model that relies on shared information between sentences (ESIM). When using an ensemble both accuracies increased to 72.247% and 72.827% respectively.