How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks
share
The general goal of text simplification (TS) is to reduce text complexity for human consumption. This paper investigates another potential use of neural TS: assisting machines performing natural language processing (NLP) tasks. We evaluate the use of neural TS in two ways: simplifying input texts at prediction time and augmenting data to provide machines with additional information during training. We demonstrate that the latter scenario provides positive effects on machine performance on two separate datasets. In particular, the latter use of TS improves the performances of LSTM (1.82-1.98 and SpanBERT (0.7-1.3 real-world relation extraction task. Further, the same setting yields improvements of up to 0.65 text classifier on MNLI, a practical natural language inference dataset.
READ FULL TEXT