توضیحات
ABSTRACT
Semantic knowledge has been adopted recently for SMT preprocessing, decoding and evaluation, in order to be able to compare sentences based on their meaning rather than on mere lexical and syntactic similarity. Little attention
has been paid to semantic knowledge in the context of integrating fuzzy matches from a translation memory with SMT. We present work in progress which focuses on semantics-based pretranslation before decoding in SMT. This involves applying fuzzy matching metrics based on lexical semantics and semantic roles, aligning parse trees based
on semantic roles, and pretranslating matching source sentence parts using aligned tree nodes.
INTRODUCTION
Semantic knowledge has been adopted recently for SMT preprocessing, decoding and evaluation. Using such knowledge helps for comparing sentences based on meaning rather than form, and for moving away from the assumption of lexical and syntactic similarity between source and target sentences. Little attention has been paid to semantic knowledge in the context of integrating fuzzy matches with SMT. Fuzzy matching methods were originally designed for translation memories, in which translators store their translations. They are now also being used in
the context of SMT, for pretranslating parts of sentences before or during decoding. These methods pretranslate matching sentence parts through wordalignment, parse node alignment and phrase tables,
and use different degrees of linguistic knowledge.
Year : 2015
Publisher : Association for Computational Linguistics
By : Tom Vanallemeersch, Vincent Vandeghinste
File Information : English Language / 4 Page / Size : 331 KB
Download : click
سال : 2015
ناشر : Association for Computational Linguistics
کاری از : Tom Vanallemeersch, Vincent Vandeghinste
اطلاعات فایل : زبان انگلیسی / 4 صفحه /حجم : 331 کیلو بایت
لینک دانلود : روی همین لینک کلیک کنید
نقد و بررسیها
هنوز بررسیای ثبت نشده است.