Navigation auf zora.uzh.ch

Search

ZORA (Zurich Open Repository and Archive)

Multi-word Adverbs – How well are they handled in Parsing and Machine Translation?

Volk, Martin; Graën, Johannes (2017). Multi-word Adverbs – How well are they handled in Parsing and Machine Translation? In: The 3rd Workshop on Multi-word Units in Machine Translation and Translation Technology (MUMTTT 2017), London, 14 November 2017, s.n..

Abstract

Multi-word expressions are often considered problematic for parsing or other tasks in natural language processing. In this paper we investigate a specific type of multi-word expressions: binomial adverbs. These adverbs follow the pattern adverb + conjunction + adverb. We identify and evaluate binomial adverbs in English, German and Swedish. We compute their degree of idiomaticity with an ordering test and with a mutual information score. We show that these idiomaticity measures point us to a number of fixed multi-word expressions which are often mis-tagged and mis-parsed. Interestingly, a second evaluation shows that state-of-the-art machine translation handles them well – with some exceptions.

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:06 Faculty of Arts > Institute of Computational Linguistics
Dewey Decimal Classification:000 Computer science, knowledge & systems
410 Linguistics
Uncontrolled Keywords:multiword expressions, machine translation, syntactic parsing, language technology, text analytics
Language:English
Event End Date:14 November 2017
Deposited On:13 Nov 2017 12:56
Last Modified:27 Nov 2020 07:27
Publisher:s.n.
OA Status:Green

Metadata Export

Statistics

Downloads

340 downloads since deposited on 13 Nov 2017
25 downloads since 12 months
Detailed statistics

Authors, Affiliations, Collaborations

Similar Publications