language is a system and every system has rules that govern the structure of its vocabulary. the rules of the arabic language are based on the vowels that consistent with the meanings used in the context represent the words' position. there are some basic rules in addition to vowels which are mostly seen in the written texts. one of these rules is the matching rule that refers to the condi...

This paper proposes a method to resolve Japanese zero pronouns with extrasentential reference which can be realized in a practical machine translation system. This method focuses on semantic and pragmatic constraints such as modal expressions, verbal semantic attributes and conjunctions to determine the extrasentential referents of Japanese zero pronouns. According to a window test, 100% of zer...

This paper investigates the causes of the comparatively low success rates in finding the antecedents of plural pronouns as compared to finding antecedents of singular pronouns. We are trying to show experimentally that considering morphological agreement as a strong constraint in pronoun resolution results in the erroneous interpretation of almost a quarter of the plural pronouns. The work is b...

In this paper I propose a unified account of two phenomena that have so far only been treated independently of each other: (I.) the strong tendency of German demonstrative pronouns (henceforth: D-pronouns or DEM) like der and die to be resolved to antecedents that have not been maximally salient in the preceding sentence, and (II.) the fact that D-pronouns cannot be interpreted as syntactically...

Pronoun interpretation in English has been demonstrated to be sensitive to an interaction between grammatical and pragmatically-driven factors. This study investigated the interpretation of pronouns in Japanese, which has both null and overt forms. Thirty-two native speakers of Japanese per experiment participated in passage completion studies with transfer-of-possession contexts (Experiment 1)...

Previous research has shown that anaphor resolution in a non-native language may be more vulnerable to interference from structurally inappropriate antecedents compared to native anaphor resolution. To test whether previous findings on reflexive anaphors generalize to non-reflexive pronouns, we carried out an eye-movement monitoring study investigating the application of binding condition B dur...

We implement a fully probabilistic model to combine the hypotheses of a Spanish anaphora resolution system with those of a Spanish-English machine translation system. The probabilities over antecedents are converted into probabilities for the features of translated pronouns, and are integrated with phrase-based MT using an additional translation model for pronouns. The system improves the trans...

This paper evaluates the different tasks carried out in the translation of pronominal anaphora in a machine translation (MT) system. The MT interlingua approach named AGIR (Anaphora Generation with an Interlingua Representation) improves upon other proposals presented to date because it is able to translate intersentential anaphors, detect co-reference chains, and translate Spanish zero pronoun...

The paperpresents a computationally tractable application of Bulgarian pronouns representation using Universal Networking Language (UNL) formalism. It analyses grammar features of pronouns and offers a model of their formal representation based on incorporation of grammar, semantic and lexical knowledge by using standard UNL knowledge representation mechanisms. Also a comparison of different ap...