Unsupervised Deep Structured Semantic Models for Commonsense Reasoning
This addresses the problem of commonsense reasoning for natural language understanding, offering an incremental advance by applying existing frameworks to new tasks.
The paper tackled commonsense reasoning tasks like Winograd Schema challenges and Pronoun Disambiguation by proposing unsupervised neural models based on Deep Structured Semantic Models, achieving significant improvement over previous state-of-the-art approaches.
Commonsense reasoning is fundamental to natural language understanding. While traditional methods rely heavily on human-crafted features and knowledge bases, we explore learning commonsense knowledge from a large amount of raw text via unsupervised learning. We propose two neural network models based on the Deep Structured Semantic Models (DSSM) framework to tackle two classic commonsense reasoning tasks, Winograd Schema challenges (WSC) and Pronoun Disambiguation (PDP). Evaluation shows that the proposed models effectively capture contextual information in the sentence and co-reference information between pronouns and nouns, and achieve significant improvement over previous state-of-the-art approaches.