Year: 2017
Type: conference-paper
Abstract: We present a simple sequential sentence encoder for multi-domain natural language inference.Our encoder is based on stacked bidirectional LSTM-RNNs with shortcut connections and fine-tuning of word embeddings.The overall supervised model uses the above encoder to encode two input sentences into two vectors, and then uses a classifier over the vector combination to label the relationship between these two sentences as that of entailment, contradiction, or neural.Our Shortcut-Stacked sentence encoders achieve strong improvements over existing encoders on matched and mismatched multi-domain natural language inference (top singlemodel result in the EMNLP RepEval 2017 Shared Task (Nangia et al., 2017)).Moreover, they achieve the new state-of-theart encoding result on the original SNLI dataset (Bowman et al., 2015).
DOI: 10.18653/v1/w17-5308
Authors: Yixin Nie, Mohit Bansal
Institution: University of North Carolina at Chapel Hill
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Nvidia
OpenAlex ID: W2962685628
