References & Citations
Computer Science > Computation and Language
Title: Empirical Analysis for Unsupervised Universal Dependency Parse Tree Aggregation
(Submitted on 28 Mar 2024 (v1), last revised 3 Apr 2024 (this version, v2))
Abstract: Dependency parsing is an essential task in NLP, and the quality of dependency parsers is crucial for many downstream tasks. Parsers' quality often varies depending on the domain and the language involved. Therefore, it is essential to combat the issue of varying quality to achieve stable performance. In various NLP tasks, aggregation methods are used for post-processing aggregation and have been shown to combat the issue of varying quality. However, aggregation methods for post-processing aggregation have not been sufficiently studied in dependency parsing tasks. In an extensive empirical study, we compare different unsupervised post-processing aggregation methods to identify the most suitable dependency tree structure aggregation method.
Submission history
From: Adithya Kulkarni [view email][v1] Thu, 28 Mar 2024 07:27:10 GMT (6658kb,D)
[v2] Wed, 3 Apr 2024 05:53:38 GMT (6658kb,D)
Link back to: arXiv, form interface, contact.