Noun Phrase Identification in Dialogue and its Application
نویسندگان
چکیده
Noun identifications are studied as 'anaphora'. Noun-noun relationships are ambiguous, as are noun-pronoun relations. Generally, nouns must match more 'antecedent' information than pronouns. But noun's 'antecedent' can be more remote. Therefore, the analysis scope of a noun-noun relationship will be larger than that of a noun-pronoun relationship. This expanded scope of analysis may result in errors. The nearest noun which a satisfies conditions is not always the 'antecedent'. A noun phrase identification model must be more comprehensive to deal with this problem.
منابع مشابه
Investigating Embedded Question Reuse in Question Answering
The investigation presented in this paper is a novel method in question answering (QA) that enables a QA system to gain performance through reuse of information in the answer to one question to answer another related question. Our analysis shows that a pair of question in a general open domain QA can have embedding relation through their mentions of noun phrase expressions. We present methods f...
متن کاملWord Formation Approach to Noun Phrase Analysis for Thai
Noun phrase analysis is one of the most important components in Natural Language Processing (NLP) applications, such as information retrieval, extraction and categorization. For Thai, noun phrase analysis has unique problems, i.e., noun phrase boundary identification, noun phrase decomposition and its relation extraction, and core noun detection. Statistical and rule based Word formation is, th...
متن کاملPredicting Noun-Phrase Surface Forms Using Contextual Information
We propose a context-sensitive method to predict noun-phrases ill the next utterance of a telephone inquiry dialogue. First, information about tile utterance type and the discourse entities of the next utterance is graspcd using a dialogue interpretation model. Second, a domain-dependent knowledge base for noun-phrase usage is developed , focusing on the dialogue situations in context. Finally,...
متن کاملMemory-Based Shallow Parsing
We present memory-based learning approaches to shallow parsing and apply these to five tasks: base noun phrase identification, arbitrary base phrase recognition, clause detection, noun phrase parsing and full parsing. We use feature selection techniques and system combination methods for improving the performance of the memory-based learner. Our approach is evaluated on standard data sets and t...
متن کاملDo Heavy-NP Shift Phenomenon and Constituent Ordering in English Cause Sentence Processing Difficulty for EFL Learners?
Heavy-NP shift occurs when speakers prefer placing lengthy or “heavy” noun phrase direct objects in the clause-final position within a sentence rather than in the post-verbal position. Two experiments were conducted in this study, and their results suggested that having a long noun phrase affected the ordering of constituents (the noun phrase and prepositional phrase) by advanced Iranian EFL le...
متن کامل