Paper

What\'s in a Span? Evaluating the Creativity of a Span-Based Neural Constituency Parser

---

Abstract

Constituency parsing is generally evaluated superficially, particularly in a multiple language setting, with only F-scores being re-ported. As new state-of-the-art chart-based parsers have resulted in a transition from traditional PCFG-based grammars to span-based approaches (Stern et al., 2017; Gaddy et al.,2018), we do not have a good understanding of how such fundamentally different approaches interact with various treebanks as results show improvements across treebanks (Kitaev and Klein, 2018), but it is unclear what influence annotation schemes have on various treebank performance (Kitaev et al., 2019). In particular, a span-based parser’s capability of creating novel rules is an unknown factor. We perform an analysis of how span-based parsing performs across 11 treebanks in order to examine the overall behavior of this parsing approach and the effect of the treebanks’ specific annotations on results. We find that the parser tends to prefer flatter trees, but the approach works well because it is robust enough to adapt to differences in annotation schemes across treebanks and languages.

Keywords: span-based parsing, neural constituency parsing, evaluation, error analysis, multilingual setting

How to Cite:

Dakota, D. & Kübler, S., (2021) “What\'s in a Span? Evaluating the Creativity of a Span-Based Neural Constituency Parser”, Society for Computation in Linguistics 4(1), 323-333. doi: https://doi.org/10.7275/x3dp-hn26