Verbs Taking Clausal and Non-Finite Arguments as Signals of Modality

This repository contains code for experiments described in my ACL paper.

Please use the following citation:

@inproceedings{ecklekohlerACL2016,
author = {Judith Eckle-Kohler},
title = {Verbs Taking Clausal and Non-Finite Arguments as Signals of Modality –
Revisiting the Issue of Meaning Grounded in Syntax},
	month = aug,
	year = {2016},
	publisher = {Association for Computational Linguistics},
	booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL 2016)},
	pages = {811--822},
	volume = {Volume 1: Long Papers},
	address = {Berlin, Germany}
}

Abstract: We revisit Levin’s theory about the correspondence of verb meaning and syntax and infer semantic classes from a large syntactic classification of more than 600 German verbs taking clausal and non-finite arguments. Grasping the meaning components of Levin-classes is known to be hard. We address this challenge by setting up a multi-perspective semantic characterization of the inferred classes. To this end, we link the inferred classes and their English translation to independently constructed semantic classes in three different lexicons – the German wordnet GermaNet, VerbNet and FrameNet – and perform a detailed analysis and evaluation of the resulting German–English classification (available at www.ukp.tu-darmstadt.de/modality-verbclasses/).

Contact person: Dr. Judith Eckle-Kohler, [email protected]

http://www.ukp.tu-darmstadt.de/

http://www.tu-darmstadt.de/

Don't hesitate to send me an e-mail or report an issue, if something is broken (and it shouldn't be) or if you have further questions.

This repository contains experimental software and is published for the sole purpose of giving additional background details on the respective publication.

Project structure

• The package align contains the implementation of the verb sense linking algorithm based on the DKPro Uby framework.
  • to run the main class AlignVerbClasses you need a UBY database contatining the IMSLex subset, GermaNet, VerbNet, FrameNet and WordNet. Please contact me to obtain such a database, this requires that you have a GermaNet license.
• The package corpus contains the verb lemma counting pipelines for German and English based on the DKPro Core framework.
  • to run the pipelines you need to obtain TreeTagger models for German and English (they are not distributed via DKPro Core)

Requirements

• Java 1.7 and higher
• Maven
• tested on 64-bit Linux versions and Windows 7
• recommended: 16 GB RAM