A Hybrid Neural Network Model for Commonsense Reasoning

This paper proposes a hybrid neural network (HNN) model for commonsense reasoning. An HNN consists of two component models, a masked language model and a semantic similarity model, which share a BERT-based contextual encoder but use different model-specific input and output layers. HNN obtains new state-of-the-art results on three classic commonsense reasoning tasks, pushing the WNLI benchmark to 89%, the Winograd Schema Challenge (WSC) benchmark to 75.1%, and the PDP60 benchmark to 90.0%. An ablation study shows that language models and semantic similarity models are complementary approaches to commonsense reasoning, and HNN effectively combines the strengths of both. The code and pre-trained models will be publicly available at https://github.com/namisan/mt-dnn.

PDF Abstract WS 2019 PDF WS 2019 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Natural Language Understanding PDP60 HNN Accuracy 90 # 1
Common Sense Reasoning Winograd Schema Challenge HNN Score 75.1 # 1
Natural Language Understanding WNLI HNN Accuracy 83.6 # 1

Methods


No methods listed for this paper. Add relevant methods here