In other words: using paraphrases in translation
نویسنده
چکیده
This paper is inspired by an event that took place 15 years ago. Recently graduated, I had eagerly started up a small consultancy company in Sweden with the aim of producing new translation software. The first collaborative project I was involved in was to offer consultancy around a translation memory called Eurolang Optimizer, where my task would involve producing Swedish localisation. The translation aid, as all other translation memories on the market, had as its main feature a database where it would store previous translations and later offer them as suggestions when the same source sentence was found in subsequent translation work.
منابع مشابه
Improved Statistical Machine Translation Using Monolingually-Derived Paraphrases
Untranslated words still constitute a major problem for Statistical Machine Translation (SMT), and current SMT systems are limited by the quantity of parallel training texts. Augmenting the training data with paraphrases generated by pivoting through other languages alleviates this problem, especially for the so-called “low density” languages. But pivoting requires additional parallel texts. We...
متن کاملDeriving Paraphrases for Highly Inflected Languages from Comparable Documents
We describe an automatic paraphrase-inference procedure for a highly inflected language like Arabic. Paraphrases are derived from comparable documents, that is, distinct documents dealing with the same topic. A co-training approach is taken, with two classifiers, one designed to model the contexts surrounding occurrences of paraphrases, and the other trained to identify significant features of ...
متن کاملLarge Scale Acquisition of Paraphrases for Learning Surface Patterns
Paraphrases have proved to be useful in many applications, including Machine Translation, Question Answering, Summarization, and Information Retrieval. Paraphrase acquisition methods that use a single monolingual corpus often produce only syntactic paraphrases. We present a method for obtaining surface paraphrases, using a 150GB (25 billion words) monolingual corpus. Our method achieves an accu...
متن کاملAn Evaluation of the Translation of Antagonyms in the Quran
Homonymy is found in a significant portion of the single words used the Quran. One of the subsets of homonymy is related to antagonyms, which have two opposite meanings, such as the word 'asas'. The remarkable point about these words is that their meanings can be understood using such criteria as Quranic verses, narrations, dictionaries and commentaries. After acquiring the meanings of such wor...
متن کاملParaphrase Detection Based on Identical Phrase and Similar Word Matching
Paraphrase detection has numerous important applications in natural language processing (such as clustering, summarizing, and detecting plagiarism). One approach to detecting paraphrases is to use predicate argument tuples. Although this approach achieves high paraphrase recall, its accuracy is generally low. Other approaches focus on matching similar words, but word meaning is often contextual...
متن کامل