Robust VPE Detection using Automatically Parsed Text
نویسنده
چکیده
This paper describes a Verb Phrase Ellipsis (VPE) detection system, built for robustness, accuracy and domain independence. The system is corpus-based, and uses machine learning techniques on free text that has been automatically parsed. Tested on a mixed corpus comprising a range of genres, the system achieves a 70% F1-score. This system is designed as the first stage of a complete VPE resolution system that is input free text, detects VPEs, and proceeds to find the antecedents and resolve them.
منابع مشابه
Verb Phrase Ellipsis detection using Automatically Parsed Text
This paper describes a Verb Phrase Ellipsis (VPE) detection system, built for robustness, accuracy and domain independence. The system is corpus-based, and uses a variety of machine learning techniques on free text that has been automatically parsed using two different parsers. Tested on a mixed corpus comprising a range of genres, the system achieves a 72% F1-score. It is designed as the first...
متن کاملVerb Phrase Ellipsis Resolution Using Discriminative and Margin-Infused Algorithms
Verb Phrase Ellipsis (VPE) is an anaphoric construction in which a verb phrase has been elided. It occurs frequently in dialogue and informal conversational settings, but despite its evident impact on event coreference resolution and extraction, there has been relatively little work on computational methods for identifying and resolving VPE. Here, we present a novel approach to detecting and re...
متن کاملAn annotated corpus for the analysis of VP ellipsis
Verb Phrase Ellipsis (VPE) has been studied in great depth in theoretical linguistics, but empirical studies of VPE are rare. We extend the few previous corpus studies with an annotated corpus of VPE in all 25 sections of the Wall Street Journal corpus (WSJ) distributed with the Penn Treebank. We annotated the raw files using a stand-off annotation scheme that codes the auxiliary verb triggerin...
متن کاملParsed Corpora for Linguistics
Knowledge-based parsers are now accurate, fast and robust enough to be used to obtain syntactic annotations for very large corpora fully automatically. We argue that such parsed corpora are an interesting new resource for linguists. The argument is illustrated by means of a number of recent results which were established with the help of parsed corpora.
متن کاملDCG Induction using MDL and Parsed
We show how partial models of natural language syntax (manually written DCGs, with parameters estimated from a parsed corpus) can be automatically extended when trained upon raw text (using MDL). We also show how we can use a parsed corpus as an alternative constraint upon estimation. Empirical evaluation suggests that a parsed corpus is more informative than a MDL-based prior. However , best r...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2004