Pronoun Language Model and Grammatical Heuristics for Aiding Pronoun Prediction
نویسندگان
چکیده
The cross-lingual pronoun prediction task at WMT 2016 requires to restore the missing target pronouns from source text and target lemmatized and POS-tagged translations. We study the benefits for this task of a specific Pronoun Language Model (PLM), which captures the likelihood of a pronoun given the gender and number of the nouns or pronouns preceding it, on the target-side only. Experimenting with the English-to-French subtask, we select the best candidate pronoun by applying the PLM and additional heuristics based on French grammar rules to the target-side texts provided in the subtask. Although the PLM helps to outperform a random baseline, it still scores far lower than system using both source and target texts.
منابع مشابه
Iranian EFL learners’ knowledge of overt pronoun constraint in English
The present study aims to investigated Iranian L2 speaker`s knowledge of the overt pronounconstraint (OPC) in English. It also aims to examine L2 learners understanding of UniversalGrammar (Chomsky 1981, 1986, 2000, 2001) and if it is common to all languages. Specifically,this study takes a new look at the L2 acquisition of knowledge of the overt pronoun constraint(Montalbetti 1984) by Persian ...
متن کاملPronoun Translation and Prediction with or without Coreference Links
The Idiap NLP Group has participated in both DiscoMT 2015 sub-tasks: pronounfocused translation and pronoun prediction. The system for the first sub-task combines two knowledge sources: grammatical constraints from the hypothesized coreference links, and candidate translations from an SMT decoder. The system for the second sub-task avoids hypothesizing a coreference link, and uses instead a lar...
متن کاملBaseline Models for Pronoun Prediction and Pronoun-Aware Translation
This paper presents baseline models for the cross-lingual pronoun prediction task and the pronoun-focused translation task at DiscoMT 2015. We present simple yet effective classifiers for the former and discuss the impact of various contextual features on the prediction performance. In the translation task we rely on the document-level decoder Docent and a cross-sentence target language-model o...
متن کاملCross-linguistic Influence at Syntax-pragmatics Interface: A Case of OPC in Persian
Recent research in the area of Second Language Acquisition has proposed that bilinguals and L2 learners show syntactic indeterminacy when syntactic properties interface with other cognitive domains. Most of the research in this area has focused on the pragmatic use of syntactic properties while the investigation of compliance with a grammatical rule at syntax-related interfaces has not received...
متن کاملIt-disambiguation and source-aware language models for cross-lingual pronoun prediction
We present our systems for the WMT 2016 shared task on cross-lingual pronoun prediction. The main contribution is a classifier used to determine whether an instance of the ambiguous English pronoun “it” functions as an anaphoric, pleonastic or event reference pronoun. For the English-to-French task the classifier is incorporated in an extended baseline, which takes the form of a source-aware la...
متن کامل