Generic Parsing and Hybrid Transfer in Automatic Translation
نویسندگان
چکیده
The ITS-3 project (LATL, University of Geneva) aims at developing an automatic translation system involving French, Italian, English and German. The translation system relies on the classical architecture parsing-transfer-generation. Parsing of the source language is done by the IPS system, which is based on the Principles & Parameters Theory of Chomsky’s Generative Grammar (Chomsky and Lasnik, 1995). The parser produces rich syntactic structures containing lexical, phrasal, grammatical and thematic information, and focuses on (i) robustness, (ii) genericity, and (iii) deep linguistic analyses. These properties are essential for a system to be efficient in multilingual large-scale applications. The transfer mechanism acts on hybrid structures, called pseudo-semantic structures (PSS), that mix lexical items with abstract semantic information. On the basis of these PSS, the generation module produces correct output sentences
منابع مشابه
Segmentation Assisted Object Distinction for Direct Volume Rendering
Ray Casting is a direct volume rendering technique for visualizing 3D arrays of sampled data. It has vital applications in medical and biological imaging. Nevertheless, it is inherently open to cluttered classification results. It suffers from overlapping transfer function values and lacks a sufficiently powerful voxel parsing mechanism for object distinction. In this work, we are proposing an ...
متن کاملبرچسبزنی خودکار نقشهای معنایی در جملات فارسی به کمک درختهای وابستگی
Automatic identification of words with semantic roles (such as Agent, Patient, Source, etc.) in sentences and attaching correct semantic roles to them, may lead to improvement in many natural language processing tasks including information extraction, question answering, text summarization and machine translation. Semantic role labeling systems usually take advantage of syntactic parsing and th...
متن کاملAutomatic Acquisition of Transfer Rules from Translation Examples
In our research, we have developed a transfer-based machine translation architecture for the translation from Japanese into German. One main feature of the system is the fully automatic acquisition of transfer rules from translation examples by using structural matching between the parsing trees. The translation system has been implemented as part of a language learning environment with the aim...
متن کاملA Hybrid System for Chinese-English Patent Machine Translation
This paper presents a novel hybrid system, which combines rule-based machine translation (RBMT) with phrase-based statistical machine translation (SMT), to translate Chinese patent texts into English. The hybrid architecture is basically guided by the RBMT engine which processes source language parsing and transformation, generating proper syntactic trees for the target language. In the generat...
متن کاملAnalysis for Speech Translation Using Grammar-Based Parsing and Automatic Classification
In this paper, I describe a novel approach to analysis for spoken language translation which uses a combination of phrase-level grammar-based parsing and automatic classification. The job of the analyzer is to transform spoken taskoriented utterances into a shallow semantic interlingua representation. The goal of this hybrid approach is to provide accurate real-time analyses and to improve robu...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2000