RACAI: Meaning Affinity Models
نویسندگان
چکیده
This article introduces an unsupervised word sense disambiguation algorithm that is inspired by the lexical attraction models of Yuret (1998). It is based on the assumption that the meanings of the words that form a sentence can be best assigned by constructing an interpretation of the whole sentence. This interpretation is facilitated by a dependency-like context specification of a content word within the sentence. Thus, finding the context words of a target word is a matter of finding a pseudo-syntactic dependency analysis of the sentence, called a linkage.
منابع مشابه
The RACAI Text-to-Speech Synthesis System
This paper describes the RACAI Text-to-Speech (TTS) entry for the Blizzard Challenge 2013. The development of the RACAI TTS started during the Metanet4U project and the system is currently part of the METASHARE platform. This paper describes the work carried out for preparing the RACAI entry during the Blizzard Challenge 2013 and provides a detailed description of our system and future developm...
متن کاملRACAI: Unsupervised WSD Experiments @ SemEval-2, Task 17
This paper documents the participation of the Research Institute for Artificial Intelligence of the Romanian Academy (RACAI) to the Task 17 – All-words Word Sense Disambiguation on a Specific Domain, of the SemEval-2 competition. We describe three unsupervised WSD systems that make extensive use of the Princeton WordNet (WN) structure and WordNet Domains in order to perform the disambiguation. ...
متن کاملMining for Term Translations in Comparable Corpora
This paper presents the techniques currently developed at RACAI for extracting parallel terminology from the comparable collection of Romanian and English documents collected in the ACCURAT project. Apart from being used for enriching translation models, parallel terminology can be (and very often is) a goal in itself, since such resources can be used for building dictionaries or indexing techn...
متن کاملRomanian to English automatic MT experiments at IWSLT12 (system description paper)
The paper presents the system developed by RACAI for the ISWLT 2012 competition, TED task, MT track, Romanian to English translation. We describe the starting baseline phrasebased SMT system, the experiments conducted to adapt the language and translation models and our post-translation cascading system designed to improve the translation without external resources. We further present our attem...
متن کاملRACAI GEC - A hybrid approach to Grammatical Error Correction
This paper describes RACAI’s (Research Institute for Artificial Intelligence) hybrid grammatical error correction system. This system was validated during the participation into the CONLL’14 Shared Task on Grammatical Error Correction. We offer an analysis of the types of errors detected and corrected by our system, we present the necessary steps to reproduce our experiment and also the re-
متن کامل