Skip to content
conftrace_
2022 NAACL NAACL 2022

A Dependency Treebank of Spoken Second Language English

Abstract

AbstractIn this paper, we introduce a dependency treebank of spoken second language (L2) English that is annotated with part of speech (Penn POS) tags and syntactic dependencies (Universal Dependencies). We then evaluate the degree to which the use of this treebank as training data affects POS and UD annotation accuracy for L1 web texts, L2 written texts, and L2 spoken texts as compared to models trained on L1 texts only.

Authors

Kristopher Kyle, Masaki Eguchi, Aaron Miller, Theodore Sither

Topics

Natural Language Processing > Understanding > Part-of-Speech Tagging Natural Language Processing > Understanding > Parsing

Keywords

universal dependencies part-of-speech tagging syntactic dependency second language acquisition dependency treebank
Download PDF

More from NAACL 2022

All NAACL 2022 papers →
Automatically Detecting Reduced-formed English Pronunciations by Using Deep Learning
A Baseline Readability Model for Cebuano
Generation of Synthetic Error Data of Verb Order Errors for Swedish
Starting from “Zero”: An Incremental Zero-shot Learning Approach for Assessing Peer Feedback Comments
On Assessing and Developing Spoken ’Grammatical Error Correction’ Systems
Automatic True/False Question Generation for Educational Purpose