How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks. Van, H., Tang, Z., & Surdeanu, M. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 4074–4080, Punta Cana, Dominican Republic, November, 2021. Association for Computational Linguistics.
How May I Help You? Using Neural Text Simplification to Improve Downstream NLP Tasks [link]Paper  abstract   bibtex   
The general goal of text simplification (TS) is to reduce text complexity for human consumption. In this paper, we investigate 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.
@inproceedings{van-etal-2021-may-help,
    title = "How May {I} Help You? Using Neural Text Simplification to Improve Downstream {NLP} Tasks",
    author = "Van, Hoang  and
      Tang, Zheng  and
      Surdeanu, Mihai",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
    month = nov,
    year = "2021",
    address = "Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.findings-emnlp.343",
    pages = "4074--4080",
    abstract = "The general goal of text simplification (TS) is to reduce text complexity for human consumption. In this paper, we investigate 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.",
}

Downloads: 0