TY - JOUR AU - Zhang, Shuiliang AU - Zhao, Hai AU - Zhou, Junru AU - Zhou, Xi AU - Zhou, Xiang PY - 2021/05/18 Y2 - 2024/03/28 TI - Semantics-Aware Inferential Network for Natural Language Understanding JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 35 IS - 16 SE - AAAI Technical Track on Speech and Natural Language Processing III DO - 10.1609/aaai.v35i16.17697 UR - https://ojs.aaai.org/index.php/AAAI/article/view/17697 SP - 14437-14445 AB - For natural language understanding tasks, either machine reading comprehension or natural language inference, both semantics-aware and inference are favorable features of the concerned modeling for better understanding performance. Thus we propose a Semantics-Aware Inferential Network (SAIN) to meet such a motivation. Taking explicit contextualized semantics as a complementary input, the inferential module of SAIN enables a series of reasoning steps over semantic clues through an attention mechanism. By stringing these steps, the inferential network effectively learns to perform iterative reasoning which incorporates both explicit semantics and contextualized representations. In terms of well pre-trained language models as front-end encoder, our model achieves significant improvement on 11 tasks including machine reading comprehension and natural language inference. ER -