Alignment and tagging

Abstract

It is sometimes said that part of speech (POS) tags are likely to be the same for translation equivalent words. If this is correct, we could formulate the following hypothesis: It should be possible to use POS tagging for one language in combination with a word alignment system, in order to obtain a (partial) POS tagging for another language. This hypothesis is investigated both empirically-an experiment is described where POS tags were transferred from a POS tagged German text to a parallel Swedish text by automatic word alignment-and theoretically, in the form of a review of relevant linguistic work on the typology of POS systems. The conclusions are that the hypothesis seems to hold at least for closely related languages, that the findings of typological research do not contradict it (or a slightly modified form of it), but that further empirical research is needed.

Projecting POS tags and syntactic dependencies from English and French to Polish in aligned corpora

“…Considering POS tags, the level of direct correspondence is the highest one when compared to the number and gender subcategories as well as to dependencies. The precision performed is however lower with respect to the figures obtained by Borin (2002) on the one hand, and Yarowski et al's (2001) on the other hand. In Borin's study, precision was assessed provided the word alignments used to project POS tags were correct.…”

“…The results of the projection of POS tags and dependencies concur with those reported in the related works presented in section 2. First, concerning the number and gender subcategories, Borin (2002) has found that the former is applicable across languages whereas the latter is less relevant, at least for the German/Swedish language pair. As seen in section 3, the projection of the number subcategory offers the highest score and the projection of the gender the lowest-0.59.…”

“…This study shows that such a simple approach can perform fairly well as far as precision is concerned. The results are likely to be improved by implementing basic POS tag conversion rules as suggested in (Borin, 2002). For the projection of dependencies, defining such conversion rules seems necessary as suggested by the significant difference in precision when the projection of unlabeled and labeled dependencies are compared.…”

“…A clear imbalance may be observed between languages, such as English or French, for which a number of NLP tools as well as different linguistic resources exist (Leech, 1997) and those for which they are sparse or even absent, such as Polish. One possible option to enrich resource-poor languages consists in taking advantage of resourcerich/resource-poor language aligned corpora to induce linguistic information for the resource-poor side from the resource-rich side (Yarowski et al, 2001;Borin, 2002;Hwa et al, 2002). For Polish, this has been made possible on account of its accessing to the European Union (EU) which has resulted in the construction of a large multilingual corpus of EU legislative texts and a growing interest for new Member States languages.…”

“…Syntactic relationships are projected to Chinese either directly or using elementary transformation rules which leads to 68% precision and about 66% recall. Finally, Borin (2002) has tested the projection of major POS tags and associated grammatical informations (number, case, person, etc. ) from Swedish to German.…”