Phrase-based Evaluation of Word-to-Word Alignments
نویسندگان
چکیده
We evaluate the English—French word alignment data of the shared tasks from a phrase alignment perspective. We discuss peculiarities of the submitted data and the test data. We show that phrase-based evaluation is closely related to word-based evaluation. We show examples of phrases which are easy to align and also phrases which are difficult to align.
منابع مشابه
Heuristic Word Alignment with Parallel Phrases
This paper presents a method for word alignment that uses parallel phrases from manually word aligned sentence pairs to align words in new texts. Experiments on an English–Swedish parallel corpus showed that the heuristic phrase-based method produced word alignments with high precision. Furthermore, alignment recall was improved by generalizing phrases with part-of-speech categories. We also co...
متن کاملHarmonizing word alignments and syntactic structures for extracting phrasal translation equivalents
Accurate identification of phrasal translation equivalents is critical to both phrase-based and syntax-basedmachine translation systems. We show that the extraction of many phrasal translation equivalents is made impossible by word alignments done without taking syntactic structures into consideration. To address the problem, we propose a new annotation scheme where word alignment and the align...
متن کاملImproving Phrase-Based Translation via Word Alignments from Stochastic Inversion Transduction Grammars
We argue that learning word alignments through a compositionally-structured, joint process yields higher phrase-based translation accuracy than the conventional heuristic of intersecting conditional models. Flawed word alignments can lead to flawed phrase translations that damage translation accuracy. Yet the IBM word alignments usually used today are known to be flawed, in large part because I...
متن کاملReassessment of the Role of Phrase Extraction in PBSMT
In this paper we study in detail the relation between word alignment and phrase extraction. First, we analyze different word alignments according to several characteristics and compare them to hand-aligned data. Secondly, we analyzed the phrase-pairs generated by these alignments. We observed that the number of unaligned words has a large impact on the characteristics of the phrase table. A man...
متن کاملImproving Phrase-Based Statistical Translation Through Combination of Word Alignments
This paper investigates the combination of word-alignments computed with the competitive linking algorithm and well-established IBM models. New training methods for phrase-based statistical translation are proposed, which have been evaluated on a popular traveling domain task, with English as target language, and Chinese, Japanese, Arabic and Italian as source languages. Experiments were perfor...
متن کامل