Enhanced LSTM for Natural Language Inference
This provides a more effective approach for natural language inference tasks, though it appears incremental as it builds on existing LSTM methods.
The paper tackles natural language inference by enhancing LSTM models, achieving state-of-the-art accuracy of 88.6% on the Stanford Natural Language Inference Dataset. It demonstrates that carefully designed sequential inference models with chain LSTMs outperform previous complex architectures, with further gains from recursive architectures and syntactic parsing.
Reasoning and inference are central to human and artificial intelligence. Modeling inference in human language is very challenging. With the availability of large annotated data (Bowman et al., 2015), it has recently become feasible to train neural network based inference models, which have shown to be very effective. In this paper, we present a new state-of-the-art result, achieving the accuracy of 88.6% on the Stanford Natural Language Inference Dataset. Unlike the previous top models that use very complicated network architectures, we first demonstrate that carefully designing sequential inference models based on chain LSTMs can outperform all previous models. Based on this, we further show that by explicitly considering recursive architectures in both local inference modeling and inference composition, we achieve additional improvement. Particularly, incorporating syntactic parsing information contributes to our best result---it further improves the performance even when added to the already very strong model.