The Impact of Edge Displacement Vaserstein Distance on UD Parsing Performance
Bibliographic Data
| ID | 12156010 |
|---|---|
| Authors | Mark Anderson (0000-0002-6400-8760, Universidade da Coruña, CITIC. [email protected], corresponding author), Carlos Gómez‐Rodríguez (0000-0003-0752-8812, CITIC Group (China), corresponding author), Carlos Gómez-Rodríguez (Universidade da Coruña, CITIC. [email protected]) |
| Year | 2022 |
| Volume | 48 |
| Issue | 3 |
| Pages | 517-554 |
| Publication date | 2022-01-01 |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Computational Linguistics (JOURNAL) |
| Journal identifiers | ISSN: 0891-2017 • E-ISSN: 1530-9312 |
| Publisher | Association for Computational Linguistics (PUBLISHER • US) |
| DOI | 10.1162/coli_a_00440 |
| OpenAlex | W4225729798 |
| Language | EN |
| References cited | 46 |
We contribute to the discussion on parsing performance in NLP by introducing a measurement that evaluates the differences between the distributions of edge displacement (the directed distance of edges) seen in training and test data. We hypothesize that this measurement will be related to differences observed in parsing performance across treebanks. We motivate this by building upon previous work and then attempt to falsify this hypothesis by using a number of statistical methods. We establish that there is a statistical correlation between this measurement and parsing performance even when controlling for potential covariants. We then use this to establish a sampling technique that gives us an adversarial and complementary split. This gives an idea of the lower and upper bounds of parsing systems for a given treebank in lieu of freshly sampled data. In a broader sense, the methodology presented here can act as a reference for future correlation-based exploratory work in NLP
Adversarial system · Bottom-up parsing · Displacement (psychology · Enhanced Data Rates for GSM Evolution · Natural language processing · Parsing · Top-down parsing · Treebank · Computer Science · Natural Language Processing Techniques · Psychology · Software Engineering Research · Topic Modeling · Artificial Intelligence
An Analysis of Variance Test for Normality (Complete Samples)
Relative Importance for Linear Regression in R
Pingouin
Dependency Distance as a Metric of Language Comprehension Difficulty
Large-scale evidence of dependency length minimization in 37 languages
Dependency distance
A Mathematical Theory of Communication
The risks of mixing dependency lengths from sequences of different length
Multicollinearity in Regression Analysis
Minimizing Syntactic Dependency Lengths
Analyzing and Integrating Dependency Parsers
The effects of sentence length on dependency distance, dependency direction and the implications-Based on a parallel English-Chinese dependency treebank
| Highly cited | No |
|---|