Machine Translation by Triangulation: Making Effective Use of Multi-Parallel Corpora

نویسندگان

  • Trevor Cohn
  • Mirella Lapata
چکیده

Current phrase-based SMT systems perform poorly when using small training sets. This is a consequence of unreliable translation estimates and low coverage over source and target phrases. This paper presents a method which alleviates this problem by exploiting multiple translations of the same source phrase. Central to our approach is triangulation, the process of translating from a source to a target language via an intermediate third language. This allows the use of a much wider range of parallel corpora for training, and can be combined with a standard phrase-table using conventional smoothing methods. Experimental results demonstrate BLEU improvements for triangulated models over a standard phrase-based system.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

A new model for persian multi-part words edition based on statistical machine translation

Multi-part words in English language are hyphenated and hyphen is used to separate different parts. Persian language consists of multi-part words as well. Based on Persian morphology, half-space character is needed to separate parts of multi-part words where in many cases people incorrectly use space character instead of half-space character. This common incorrectly use of space leads to some s...

متن کامل

Co-training for Statistical Machine Translation

I propose a novel co-training method for statistical machine translation. As co-training requires multiple learners trained on views of the data which are disjoint and sufficient for the labeling task, I use multiple source documents as views on translation. Co-training for statistical machine translation is therefore a type of multi-source translation. Unlike previous mutli-source methods, it ...

متن کامل

استخراج پیکره‌ موازی از اسناد قابل‌مقایسه برای بهبود کیفیت ترجمه در سیستم‌های ترجمه ماشینی

Data used for training statistical machine translation method are usually prepared from three resources: parallel, non-parallel and comparable text corpora. Parallel corpora are an ideal resource for translation but due to lack of these kinds of texts, non-parallel and comparable corpora are used either for parallel text extraction. Most of existing methods for exploiting comparable corpora loo...

متن کامل

Unsupervised Neural Machine Translation

In spite of the recent success of neural machine translation (NMT) in standard benchmarks, the lack of large parallel corpora poses a major practical problem for many language pairs. There have been several proposals to alleviate this issue with, for instance, triangulation and semi-supervised learning techniques, but they still require a strong cross-lingual signal. In this work, we completely...

متن کامل

Translation Dictionaries Triangulation

Probabilistic Translation Dictionaries (PTD) are translation resources that can be obtained automatically from parallel corpora. Although this process is simple, it requires the existence of a parallel corpora for the involved languages. Minoritized languages have a limited amount of available resources. For example, while they can have a few parallel corpora, the number of parallel language-pa...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2007