English

Nightmare at test time: How punctuation prevents parsers from generalizing

Computation and Language 2018-09-05 v1

Abstract

Punctuation is a strong indicator of syntactic structure, and parsers trained on text with punctuation often rely heavily on this signal. Punctuation is a diversion, however, since human language processing does not rely on punctuation to the same extent, and in informal texts, we therefore often leave out punctuation. We also use punctuation ungrammatically for emphatic or creative purposes, or simply by mistake. We show that (a) dependency parsers are sensitive to both absence of punctuation and to alternative uses; (b) neural parsers tend to be more sensitive than vintage parsers; (c) training neural parsers without punctuation outperforms all out-of-the-box parsers across all scenarios where punctuation departs from standard punctuation. Our main experiments are on synthetically corrupted data to study the effect of punctuation in isolation and avoid potential confounds, but we also show effects on out-of-domain data.

Keywords

Cite

@article{arxiv.1809.00070,
  title  = {Nightmare at test time: How punctuation prevents parsers from generalizing},
  author = {Anders Søgaard and Miryam de Lhoneux and Isabelle Augenstein},
  journal= {arXiv preprint arXiv:1809.00070},
  year   = {2018}
}

Comments

Analyzing and interpreting neural networks for NLP, EMNLP 2018 workshop

R2 v1 2026-06-23T03:51:12.526Z