How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks
This addresses the problem of improving NLP model performance for researchers and practitioners by applying text simplification in a novel way, though it is incremental as it builds on existing methods.
The paper investigates using neural text simplification to improve downstream NLP tasks by augmenting training data, showing performance gains of 1.82-1.98% for LSTM and 0.7-1.3% for SpanBERT on TACRED, and up to 0.65% accuracy for BERT on MNLI.
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%) extractors on TACRED, a complex, large-scale, real-world relation extraction task. Further, the same setting yields improvements of up to 0.65% matched and 0.62% mismatched accuracies for a BERT text classifier on MNLI, a practical natural language inference dataset.