Machine Translation: Past, Present, Future

نویسنده

  • Nigel Ward
چکیده

Machine Translation Past, Present, Future (Ellis Horwood Limited, Chichester, England, 1986, 382 pp., $52.95) by William John Hutchins is a good book. It is organized around projects as “a history and assessment of efforts to mechanise processes of translating” (p.18). It is complete, discussing basically every project in the world since machine translation’s first glimmerings 40 years ago Projects are grouped by time frame, nation, or approach. The organization is, of course, somewhat arbitrary, but it is supplemented by cross-references and summary tables of projects and systems. Hutchins not only presents the theories, algorithms, and designs but also the history, goals, assumptions, and constraints of each project. There are many sample outputs and fair evaluations of the contributions and shortcomings of each approach. Hutchins also includes thorough chapters giving background and commentary on problems, strategies, and methods; for example, the discussion of the ALPAC report includes sketches of the committee member’s backgrounds. The writing is generally clear and is well supported by figures This book is a fine reference, with an extensive bibliography and a good index. It is also a readable introduction to the field. It assumes no previous knowledge of machine translation or even programming. However, because the book includes no traces of system executions, it is harder to get a feel for how these programs work. The book has a few other Book Reviews

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

Modeling Past and Future for Neural Machine Translation

Existing neural machine translation systems do not explicitly model what has been translated and what has not during the decoding phase. To address this problem, we propose a novel mechanism that separates the source information into two parts: translated PAST contents and untranslated FUTURE contents, which are modeled by two additional recurrent layers. The PAST and FUTURE contents are fed to...

متن کامل

The machine translation system MATS - past, present & future

This is a status report of the rule-based machine translation system MATS (Sågvall Hein et al., 2002). It describes the development into its current state, which has recently been focused on extending the linguistic resources to new domains and improving robustness. In cases where an input sentence is not fully processable by the system, partial results are taken care of and used in producing a...

متن کامل

Past, Present and Future

The attempt to translate meaning from one language to another by formal means traces back to the philosophical schools of secret and universal languages as they were originated by Ramon Llull or Johann Joachim Becher. Until today, machine translation (MT) is known as the crowning discipline of natural language processing. Due to current MT approaches, the time needed to develop new systems with...

متن کامل

Contrastive Analysis of Aspectual Oppositions in English and Persian

This article aims at contrasting aspectual oppositions in English and Persian in the context of the novel The Old Man and the Sea, and its translation by Daryabandari (1983) as the data. Unlike English, in Persian perfective and imperfective forms are morphologically marked. While the vast majority of English simple past forms are translated into Persian by past perfective forms, only less than...

متن کامل

Coverage-based Neural Machine Translation

Attention mechanism advanced state-of-the-art neural machine translation (NMT) by jointly learning to align and translate. However, attentional NMT ignores past alignment information, which leads to over-translation and under-translation problems. In response to this problem, we maintain a coverage vector to keep track of the attention history. The coverage vector is fed to the attention model ...

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 2001