Unsupervised Deep Structured Semantic Models for Commonsense Reasoning
Shuohang Wang, Sheng Zhang, Yelong Shen, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Jing Jiang
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
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.
Tasks
Benchmark Results
| Dataset | Model | Metric | Claimed | Verified | Status |
|---|---|---|---|---|---|
| Winograd Schema Challenge | DSSM | Accuracy | 63 | — | Unverified |
| Winograd Schema Challenge | UDSSM-II (ensemble) | Accuracy | 62.4 | — | Unverified |
| Winograd Schema Challenge | UDSSM-II | Accuracy | 59.2 | — | Unverified |
| Winograd Schema Challenge | UDSSM-I (ensemble) | Accuracy | 57.1 | — | Unverified |
| Winograd Schema Challenge | UDSSM-I | Accuracy | 54.5 | — | Unverified |