Explicit Contextual Semantics for Text Comprehension

8 Sep 2018  ·  Zhuosheng Zhang, Yuwei Wu, Zuchao Li, Hai Zhao ·

Who did what to whom is a major focus in natural language understanding, which is right the aim of semantic role labeling (SRL) task. Despite of sharing a lot of processing characteristics and even task purpose, it is surprisingly that jointly considering these two related tasks was never formally reported in previous work. Thus this paper makes the first attempt to let SRL enhance text comprehension and inference through specifying verbal predicates and their corresponding semantic roles. In terms of deep learning models, our embeddings are enhanced by explicit contextual semantic role labels for more fine-grained semantics. We show that the salient labels can be conveniently added to existing models and significantly improve deep learning models in challenging text comprehension tasks. Extensive experiments on benchmark machine reading comprehension and inference datasets verify that the proposed semantic learning helps our system reach new state-of-the-art over strong baselines which have been enhanced by well pretrained language models from the latest progress.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Natural Language Inference SNLI SJRC (BERT-Large +SRL) % Test Accuracy 91.3 # 9
% Train Accuracy 95.7 # 8
Parameters 308m # 5
Natural Language Inference SNLI SLRC % Test Accuracy 89.1 # 20
% Train Accuracy 89.1 # 52
Parameters 6.1m # 5


No methods listed for this paper. Add relevant methods here