MASTER ’ S THESIS Michal Novák Machine Learning Approach to Anaphora
نویسنده
چکیده
2010 I dedicate this thesis to my family, especially to my mother, who supports me and encourages me throughout my whole life. I would like to thank my supervisor, Ing. Zdeněk Žabokrtský, Ph.D., for his patience and for his valuable expert advices. Moreover, I really appreciate that my supervisor and one of my friends, Mgr. Pavol Rusnák, provided me with a technical support for development and testing. This work would not be possible without the project of extended annotation of PDT led by Mgr. Anja Nědolužko and RNDr. Jiří Mírovský, Ph.D. I would like to thank them, too. I declare I wrote my thesis by myself and listed all used references. I agree with making the thesis publicly available.
منابع مشابه
Comparison of Coreference Resolvers for Deep Syntax Translation
This work focuses on using anaphora for machine translation with deep-syntactic transfer. We compare multiple coreference resolvers for English in terms of how they affect the quality of pronoun translation in English-Czech and EnglishDutch machine translation systems with deep transfer. We examine which pronouns in the target language depend on anaphoric information, and design rules that take...
متن کاملComparison of Classification and Ranking Approaches to Pronominal Anaphora Resolution in Czech
In this paper we compare two Machine Learning approaches to the task of pronominal anaphora resolution: a conventional classification system based on C5.0 decision trees, and a novel perceptron-based ranker. We use coreference links annotated in the Prague Dependency Treebank 2.0 for training and evaluation purposes. The perceptron system achieves f-score 79.43% on recognizing coreference of pe...
متن کاملUtilization of Anaphora in Machine Translation
Majority of present machine translation systems do not address the retaining of text coherency, they translate just isolated sentences. On the other hand, the authors of anaphora resolvers rarely integrate these tools into more complex scenarios, e.g. the task of machine translation. We propose the ways how machine translation systems can utilize the knowledge of anaphoric relations both in the...
متن کاملCombining Linguistic Knowledge and Machine Learning for Anaphora Resolution
This thesis focuses on attempting to incorporate linguistically contextual clues into machine learning-based approaches for anaphora resolution, which is the process of identifying whether or not an expression refers to another expression. As the state-ofthe-art of morpho-syntactic analysis and named entity recognition grows more increasingly sophisticated, research focus in natural language pr...
متن کاملCross-lingual Coreference Resolution of Pronouns
This work is, to our knowledge, a first attempt at a machine learning approach to cross-lingual coreference resolution, i.e. coreference resolution (CR) performed on a bitext. Focusing on CR of English pronouns, we leverage language differences and enrich the feature set of a standard monolingual CR system for English with features extracted from the Czech side of the bitext. Our work also incl...
متن کامل