How to Account for Idiomatic German Support Verb Constructions in Statistical Machine Translation

Abstract

Support-verb constructions (i.e., multiword expressions combining a semantically light verb with a predicative noun) are problematic for standard statistical machine translation systems, because SMT systems cannot distinguish between literal and idiomatic uses of the verb. We work on the German to English translation direction, for which the identification of support-verb constructions is challenging due to the relatively free word order of German. We show that we achieve improved translation quality for verb-object supportverb constructions by marking the verbs when occuring in such constructions. Additional evaluations revealed that our systems produce more correct verb translations than a contrastive baseline system without verb markup.

Factoring Ambiguity out of the Prediction of Compositionality for German Multi-Word Expressions

“…For example, studies such as Cholakov and Kordoni (2014), Weller et al (2014), Cap et al (2015), and Salehi et al (2015b) have integrated the prediction of multi-word compositionality into statistical machine translation.…”

Addressing Problems across Linguistic Levels in SMT: Combining Approaches to Model Morphology, Syntax and Lexical Choice

“…Typically, the verb does not contribute its full meaning, and thus cannot be translated literally. Cap et al (2015) improved German-English phrasebased SMT by annotating support verb status on source-side verbs, which essentially divides verbs into two groups: "non-literal use" in a support verb construction, and "literal use" otherwise. The set of support verb constructions consists of highly associated noun+verb tuples.…”

“…The set of support verb constructions consists of highly associated noun+verb tuples. Cap et al (2015) opted for a hard annotation by adding markup. Instead, we add a classifier feature and compare two variants: (i) setting the feature to a binary support verb status (yes/no) for a fixed set of tuples (using a log-likelihood threshold of 1000, as in Cap et al (2015)).…”

“…Cap et al (2015) opted for a hard annotation by adding markup. Instead, we add a classifier feature and compare two variants: (i) setting the feature to a binary support verb status (yes/no) for a fixed set of tuples (using a log-likelihood threshold of 1000, as in Cap et al (2015)). There is no dependency information in this variant, only the basic features lemma and POS-tag.…”

Discovering Light Verb Constructions and their Translations from Parallel Corpora without Word Alignment

“…It has been shown that the presence of MWEs can harm the quality of both statistical (Ramisch et al, 2013) and rulebased (Barreiro et al, 2014) MT systems. Simple techniques for taking MWEs into account such as binary features (Carpuat and Diab, 2010) and special token markers (Cap et al, 2015) can help improving translation quality. However, this may not suffice if the expressions are not correctly identified with the help of bilingual MWE lexicons.…”