Open-Source Portuguese–Spanish Machine Translation

Abstract

Abstract. This paper describes the current status of development of an open-source shallow-transfer machine translation (MT) system for the [European] Portuguese ↔ Spanish language pair, developed using the OpenTrad Apertium MT toolbox (www.apertium.org). Apertium uses finite-state transducers for lexical processing, hidden Markov models for part-of-speech tagging, and finite-state-based chunking for structural transfer, and is based on a simple rationale: to produce fast, reasonably intelligible and easily correctable translations between related languages, it suffices to use a MT strategy which uses shallow parsing techniques to refine word-for-word MT. This paper briefly describes the MT engine, the formats it uses for linguistic data, and the compilers that convert these data into an efficient format used by the engine, and then goes on to describe in more detail the pilot Portuguese↔Spanish linguistic data.

Alignment-based extraction of multiword expressions

“…The aligned parallel sentences were then PoS-tagged in each language using the corresponding morphological analysers and PoS taggers from Apertium 2 (Armentano- Oller et al 2006). The morphological analysis provides one or more lexical forms or analyses (information on lemma, lexical category and morphological inflection) for each surface form (instance of a word in the text) using a monolingual morphological dictionary.…”

Chinese-to-Spanish rule-based machine translation system

“…Some previous publications that explain Spanish generation can by found in (Armentano-Oller et al, 2006;Corbí-Bellot et al, 2005). Basically, it consists of the three modules of Apertium: morphological generator that delivers a surface (inflected) form for each transferred word.…”

Is singular value decomposition useful for word similarity extraction?

“…The bilingual dictionaries used to select the seed words required by the acquisition algorithm are the lexical resources integrated in OpenTrad, an open source machine translation system for Spanish-Galician and English-Galician (Armentano-Oller et al 2006). The Spanish-Galician dictionary contains about 25,000 entries, and the English-Galician about 12,000.…”