Learn More
We present a method for evaluating the quality of Machine Translation (MT) output, using labelled dependencies produced by a Lexical-Functional Grammar (LFG) parser. Our dependency-based method, in contrast to most popular string-based evaluation metrics, does not unfairly penalize perfectly valid syntactic variations in the translation, and the addition of(More)
In this paper we investigate the automatic acquisition of Arabic Multiword Expressions (MWE). We propose three complementary approaches to extract MWEs from available data resources. The first approach relies on the correspondence asymmetries between Arabic Wikipedia titles and titles in 21 different languages. The second approach collects English MWEs from(More)
This paper shows that training a lexicalized parser on a lemmatized morphologically-rich treebank such as the French Treebank slightly improves parsing results. We also show that lemmatizing a similar in size subset of the En-glish Penn Treebank has almost no effect on parsing performance with gold lemmas and leads to a small drop of performance when(More)
We present a novel method for evaluating the output of Machine Translation (MT), based on comparing the dependency structures of the translation and reference rather than their surface string forms. Our method uses a treebank-based, wide-coverage, probabilistic Lexical-Functional Grammar (LFG) parser to produce a set of structural dependencies for each(More)
In this paper we present a novel method for deriving paraphrases during automatic MT evaluation using only the source and reference texts, which are necessary for the evaluation, and word and phrase alignment software. Using target language paraphrases produced through word and phrase alignment a number of alternative reference sentences are constructed(More)
This paper presents a study of the impact of using simple and complex morphological clues to improve the classification of rare and unknown words for parsing. We compare this approach to a language-independent technique often used in parsers which is based solely on word frequencies. This study is applied to three languages that exhibit different levels of(More)
With the steadily increasing demand for high-quality translation, the localisation industry is constantly searching for technologies that would increase translator throughput, with the current focus on the use of high-quality Statistical Machine Translation (SMT) as a supplement to the established Translation Memory (TM) technology. In this paper we present(More)
We describe DCU's LFG dependency-based metric submitted to the shared evaluation task of WMT-MetricsMATR 2010. The metric is built on the LFG F-structure-based approach presented in (Owczarzak et al., 2007). We explore the following improvements on the original metric: 1) we replace the in-house LFG parser with an open source dependency parser that directly(More)
We introduce a set of 1,000 gold standard parse trees for the British National Corpus (BNC) and perform a series of self-training experiments with Charniak and Johnson's reranking parser and BNC sentences. We show that retraining this parser with a combination of one million BNC parse trees (produced by the same parser) and the original WSJ training data(More)
1 Abstract Lexical Functional Grammar (LFG) f-structures are \high-level" syntactic representations ; Quasi-Logical Forms (QLFs) and Underspeciied Discourse Representation Structures (UDRSs) are recent underspeciied and truth-conditionally interpreted semantic representations. It turns out that there are a number of striking structural similarities between(More)