Research breakthrough possible @S-Logix pro@slogix.in

Office Address

  • 2nd Floor, #7a, High School Road, Secretariat Colony Ambattur, Chennai-600053 (Landmark: SRM School) Tamil Nadu, India
  • pro@slogix.in
  • +91- 81240 01111

Social List

Semantics-Aware BERT for Language Understanding - 2020

Semantics-Aware Bert For Language Understanding

Research Area:  Machine Learning

Abstract:

The latest work on language representations carefully integrates contextualized features into language model training, which enables a series of success especially in various machine reading comprehension and natural language inference tasks. However, the existing language representation models including ELMo, GPT and BERT only exploit plain context-sensitive features such as character or word embeddings. They rarely consider incorporating structured semantic information which can provide rich semantics for language representation. To promote natural language understanding, we propose to incorporate explicit contextual semantics from pre-trained semantic role labeling, and introduce an improved language representation model, Semantics-aware BERT (SemBERT), which is capable of explicitly absorbing contextual semantics over a BERT backbone. SemBERT keeps the convenient usability of its BERT precursor in a light fine-tuning way without substantial task-specific modifications. Compared with BERT, semantics-aware BERT is as simple in concept but more powerful. It obtains new state-of-the-art or substantially improves results on ten reading comprehension and language inference tasks.

Keywords:  

Author(s) Name:  Zhuosheng Zhang ,Yuwei Wu Shanghai , Hai Zhao ,Zuchao Li ,Shuailiang Zhang , Xi Zhou , Xiang Zhou

Journal name:  

Conferrence name:  Proceedings of the AAAI Conference on Artificial Intelligence

Publisher name:  Association for the Advancement of Artificial Intelligence

DOI:  10.1609/aaai.v34i05.6510

Volume Information: