Sentence Embeddings in NLI with Iterative Refinement Encoders

27 Aug 2018  ·  Aarne Talman, Anssi Yli-Jyrä, Jörg Tiedemann ·

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. read more

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Natural Language Inference SciTail Hierarchical BiLSTM Max Pooling Accuracy 86.0 # 7
Natural Language Inference SNLI 600D Hierarchical BiLSTM with Max Pooling (HBMP, code) % Test Accuracy 86.6 # 49
% Train Accuracy 89.9 # 44
Parameters 22m # 3