Sentence Embeddings in NLI with Iterative Refinement Encoders
This work addresses the need for effective sentence embeddings in NLP, offering incremental improvements over existing models for tasks like natural language inference and transfer learning.
The paper tackled the problem of learning sentence embeddings for NLP tasks by proposing a hierarchical BiLSTM and max pooling model with iterative refinement, achieving state-of-the-art results on the SciTail dataset and strong performance on SNLI and MultiNLI, with concrete improvements such as outperforming InferSent on 7 out of 10 and SkipThought on 8 out of 9 SentEval tasks.
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.