Publishing Partner: Cambridge University Press CUP Extra Wiley-Blackwell Publisher Login
amazon logo
More Info


New from Oxford University Press!

ad

The Social Origins of Language

By Daniel Dor

Presents a new theoretical framework for the origins of human language and sets key issues in language evolution in their wider context within biological and cultural evolution


New from Cambridge University Press!

ad

Preposition Placement in English: A Usage-Based Approach

By Thomas Hoffmann

This is the first study that empirically investigates preposition placement across all clause types. The study compares first-language (British English) and second-language (Kenyan English) data and will therefore appeal to readers interested in world Englishes. Over 100 authentic corpus examples are discussed in the text, which will appeal to those who want to see 'real data'


New from Brill!

ad

Free Access 4 You

Free access to several Brill linguistics journals, such as Journal of Jewish Languages, Language Dynamics and Change, and Brill’s Annual of Afroasiatic Languages and Linguistics.


Academic Paper


Title: Using Machine-Learning to Assign Function Labels to Parser Output for Spanish
Paper URL: http://acl.ldc.upenn.edu/P/P06/P06-2018.pdf
Author: Grzegorz Chrupała
Email: click here to access email
Homepage: http://www.lsv.uni-saarland.de/personalPages/gchrupala/index.html
Institution: Saarland University
Author: Josef Van Genabith
Email: click here to access email
Institution: Dublin City University
Linguistic Field: Computational Linguistics
Subject Language: Spanish
Spanish
Abstract: Data-driven grammatical function tag assignment has been studied for English using the Penn-II Treebank data. In this paper we address the question of whether such methods can be applied successfully to other languages and treebank resources. In addition to tag assignment accuracy and f-scores we also present results of a task-based evaluation. We use three machine-learning methods to assign Cast3LB function tags to sentences parsed with Bikel's parser trained on the Cast3LB treebank. The best performing method, SVM, achieves an f-score of 86.87% on gold-standard trees and 66.67% on parser output - a statistically significant improvement of 6.74% over the baseline. In a task-based evaluation we generate LFG functional-structures from the function-tag-enriched trees. On this task we achieve an f-score of 75.67%, a statistically significant 3.4% improvement over the baseline.
Type: Individual Paper
Status: Completed
Publication Info: Proceedings of the COLING/ACL 2006 Main Conference Poster Sessions
URL: http://acl.ldc.upenn.edu/P/P06/P06-2018.pdf


Back
Add a new paper
Return to Academic Papers main page
Return to Directory of Linguists main page