Inducing Lexico-Structural Transfer Rules from Parsed Bi-texts
نویسندگان
چکیده
This paper describes a novel approach to inducing lexico-structural transfer rules from parsed bi-texts using syntactic pattern matching, statistical cooccurrence and error-driven filtering. We present initial evaluation results and discuss future directions.
منابع مشابه
Learning Domain-Specific Transfer Rules: An Experiment With Korean To English Translation
We describe the design of an MT system that employs transfer rules induced from parsed bitexts and present evaluation results. The system learns lexico-structural transfer rules using syntactic pattern matching, statistical co-occurrence and errordriven filtering. In an experiment with domainspecific Korean to English translation, the approach yielded substantial improvements over three baselin...
متن کاملF-structure Transfer-based Statistical Machine Translation
In this paper, we describe a statistical deep syntactic transfer decoder that is trained fully automatically on parsed bilingual corpora. Deep syntactic transfer rules are induced automatically from the f-structures of a LFG parsed bitext corpus by automatically aligning local f-structures, and inducing all rules consistent with the node alignment. The transfer decoder outputs the n-best TL f-s...
متن کاملEnriching Lexical Transfer With Cross-Linguistic Semantic Features or How to Do Interlingua without Interlingua
In this paper, we propose an alternative to interlingua which can capture the analyses and generalizations that interlinguas can express, but which uses cross-linguistic semantic features rather than a separate level of representation. This alternative we call lexico-structural transfer. Lexico-structural transfer relies on the expressive power of a lexicalized syntactic representation (or “lex...
متن کاملThe Icelandic Parsed Historical Corpus (IcePaHC)
We describe the background for and building of IcePaHC, a one million word parsed historical corpus of Icelandic which has just been finished. This corpus which is completely free and open contains fragments of 60 texts ranging from the late 12 century to the present. We describe the text selection and text collecting process and discuss the quality of the texts and their conversion to modern I...
متن کاملExtraction of Lexico-Syntactic Information and Acquisition of Causality Schemas for Text Annotation
We present the INSYSE method for the annotation of texts, based on extraction of semantic relations from syntactic structures. We apply this method to a corpus of 5000 Medline abstracts about central nervous system diseases and gene interactions. Our cooperative approach focuses on (1) extracting lexico-syntactic information from sentences in the corpus comprising causation lexemes and (2) elab...
متن کامل