A Hybrid Neural Network Model for Commonsense Reasoning
This addresses commonsense reasoning for AI systems, representing an incremental improvement by combining existing methods.
The paper tackled commonsense reasoning by proposing a hybrid neural network model, achieving new state-of-the-art results with 89% on WNLI, 75.1% on WSC, and 90.0% on PDP60.
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.