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 ≈5% improvement over prior state of the art and that the pretrained DEISTE on SciTail generalizes well on RTE-5.
Highlights
Textual entailment (TE) is a fundamental problem in natural language understanding and has been studied intensively recently using multiple benchmarks – PASCAL RTE challenges (Dagan et al, 2006, 2013), Paragraph-Headline (Burger and Ferro, 2005), SICK (Marelli et al, 2014) and SNLI (Bowman et al, 2015)
– has generated much work based on deep neural networks due to its large size
DEISTE, equipped with a parameter-dynamic convolution and a more advanced position-aware attentive convolution, clearly gets a big plus. (ii) The ablation shows that all three aspects we explore from the inter-sentence interactions contribute; “position” encoding is less important than “dyn-conv” and “representation”
Summary
Textual entailment (TE) is a fundamental problem in natural language understanding and has been studied intensively recently using multiple benchmarks – PASCAL RTE challenges (Dagan et al, 2006, 2013), Paragraph-Headline (Burger and Ferro, 2005), SICK (Marelli et al, 2014) and SNLI (Bowman et al, 2015). – has generated much work based on deep neural networks due to its large size These benchmarks were mostly derived independently of any NLP problems.. We study SCITAIL (Khot et al, 2018), an end-task oriented challenging entailment benchmark. Khot et al (2018) report that SCITAIL challenges neural entailment models that show outstanding performance on SNLI, e.g., Decomposable Attention Model (Parikh et al, 2016) and Enhanced LSTM (Chen et al, 2017). 2 Method pi hj Figure 2: The basic principles of DEISTE in modeling the pair (P , H). The pair (P , H), DEISTE pursues three deep exploration strategies of these interactions. We elaborate DEISTE’s exploration strategies (a), (b) and (c) of the interaction results I
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
