To assign semantic roles in building Treebanks, there is a need for annotators having a guideline in determining semantic relations between phrasal head and its modifiers or arguments. Semantic roles are hard to have clear-cut definitions. It is not always easy to determine thematic relations between two concepts. This paper aims to introduce an integrated nominal modifier system. Basically we ...

In this work, the use of a phrasal lexicon for statistical machine translation is proposed, and the relation between data acquisition costs and translation quality for different types and sizes of language resources has been analyzed. The language pairs are Spanish-English and Catalan-English, and the translation is performed in all directions. The phrasal lexicon is used to increase as well as...

In the Slavic languages, the title of this paper cannot be rendered with a phrasal comparative; a clausal comparative must be used instead. I evaluate three types of theories of phrasal comparatives and conclude that only one – the small clause analysis – can accommodate the new observation. I then offer an explanation of the observation in terms of a universal and inviolable anti-locality cons...

We describe a new version of MEANT, which participated in the metrics task of the Second Conference on Machine Translation (WMT 2017). MEANT 2.0 uses idfweighted distributional ngram accuracy to determine the phrasal similarity of semantic role fillers and yields better correlations with human judgments of translation quality than earlier versions. The improved phrasal similarity enables a subv...

We describe a novel approach to statistical machine translation that combines syntactic information in the source language with recent advances in phrasal translation. We depend on a source-language dependency parser and a word-aligned parallel corpus. The only target language resource assumed is a word breaker. These are used to produce treelet (“phrase”) translation pairs as well as several m...

Previous studies have shown that text genres can be computationally distinguished by sophisticated computational and statistical methods. The current study adds to the previous body of work by incorporating phrasal verbs as a text genre identifier. Results indicate that phrasal verbs significantly distinguish between both the spoken/written and formal/informal dimensions, with considerably less...