# End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions

Source: [End-Task Oriented Textual Entailment via Deep Explorations of Inter-Sentence Interactions](<https://www.sota2.com/research/paper/68fa64641e209131cea044df>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T21:03:11.991Z

Authors: Wenpeng Yin, Hinrich Sch\\"utze, Dan Roth

Published: 2018-04-24T02:29:14.000Z

## Abstract

This work deals with SciTail, a natural entailment challenge derived from a multi-choice question answering problem. The premises and hypotheses in SciTail were generated with no awareness of each other, and did not specifically aim at the entailment task. This makes it more challenging than other entailment data sets and more directly useful to the end-task -- question answering. We propose DEISTE (deep explorations of inter-sentence interactions for textual entailment) for this entailment task. Given word-to-word interactions between the premise-hypothesis pair ($P$, $H$), DEISTE consists of: (i) a parameter-dynamic convolution to make important words in $P$ and $H$ play a dominant role in learnt representations; and (ii) a position-aware attentive convolution to encode the representation and position information of the aligned word pairs. Experiments show that DEISTE gets $\\approx$5\\% improvement over prior state of the art and that the pretrained DEISTE on SciTail generalizes well on RTE-5.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1804.08813>)

[PDF](<https://arxiv.org/pdf/1804.08813.pdf>)