Matches in SemOpenAlex for { <https://semopenalex.org/work/W80257477> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W80257477 abstract "Resolving pronominal anaphors in English has been a focus of research in natural language processing for decades. Methods ranging from linguistics-oriented, rule-based approaches to data-oriented, machine-learning approaches have been applied to the problem of finding the antecedents of pronouns. In contrast to the abundance of research in English, there is almost no work on the problem in Chinese. This thesis addresses that gap. Both a rule-based and a machine-learning anaphora resolution approach are presented in this work. An important difference between Chinese and English is that Chinese, unlike English, is a pro-drop language, and has null (zero) pronouns. The rule-based approach is applied to resolving these null pronouns as well as to the overt, third-person pronouns. The Hobbs algorithm is used for the rule-based method of anaphora resolution. Three versions of the algorithm are presented. The first uses only syntactic structure to select an antecedent. The second uses limited number and gender agreement, while the third incorporates semantic constraints on the proposed antecedents. For the machine-learning method, maximum entropy, supervised machine-learning models are used. Different models were trained using sets of features that paralleled the information sources used by the different versions of the Hobbs algorithm. Two sets of data were used. The Penn Chinese Treebank provided the test data for resolution of both overt, third-person pronouns and of zero pronouns. The CTB parses were annotated for coreference using guidelines that were drawn up for the work presented here. Data annotated for the 2004 Chinese ACE program were used for training and testing the maximum entropy models to find the antecedents for overt, third-person pronouns. The results from experiments with the two basic methods using the different levels of linguistic information will be presented and discussed." @default.
- W80257477 created "2016-06-24" @default.
- W80257477 creator A5014732258 @default.
- W80257477 creator A5017464054 @default.
- W80257477 date "2006-01-01" @default.
- W80257477 modified "2023-09-26" @default.
- W80257477 title "Pronominal anaphora resolution in chinese" @default.
- W80257477 hasPublicationYear "2006" @default.
- W80257477 type Work @default.
- W80257477 sameAs 80257477 @default.
- W80257477 citedByCount "26" @default.
- W80257477 countsByYear W802574772013 @default.
- W80257477 countsByYear W802574772014 @default.
- W80257477 countsByYear W802574772015 @default.
- W80257477 countsByYear W802574772016 @default.
- W80257477 countsByYear W802574772017 @default.
- W80257477 countsByYear W802574772018 @default.
- W80257477 countsByYear W802574772019 @default.
- W80257477 countsByYear W802574772020 @default.
- W80257477 countsByYear W802574772021 @default.
- W80257477 crossrefType "journal-article" @default.
- W80257477 hasAuthorship W80257477A5014732258 @default.
- W80257477 hasAuthorship W80257477A5017464054 @default.
- W80257477 hasConcept C138268822 @default.
- W80257477 hasConcept C138496976 @default.
- W80257477 hasConcept C138885662 @default.
- W80257477 hasConcept C154945302 @default.
- W80257477 hasConcept C155092808 @default.
- W80257477 hasConcept C15744967 @default.
- W80257477 hasConcept C186644900 @default.
- W80257477 hasConcept C204321447 @default.
- W80257477 hasConcept C206134035 @default.
- W80257477 hasConcept C24184978 @default.
- W80257477 hasConcept C2764733 @default.
- W80257477 hasConcept C2777530160 @default.
- W80257477 hasConcept C2778551981 @default.
- W80257477 hasConcept C2780277889 @default.
- W80257477 hasConcept C2781256819 @default.
- W80257477 hasConcept C2781449363 @default.
- W80257477 hasConcept C28076734 @default.
- W80257477 hasConcept C41008148 @default.
- W80257477 hasConcept C41895202 @default.
- W80257477 hasConcept C67277372 @default.
- W80257477 hasConcept C9679016 @default.
- W80257477 hasConceptScore W80257477C138268822 @default.
- W80257477 hasConceptScore W80257477C138496976 @default.
- W80257477 hasConceptScore W80257477C138885662 @default.
- W80257477 hasConceptScore W80257477C154945302 @default.
- W80257477 hasConceptScore W80257477C155092808 @default.
- W80257477 hasConceptScore W80257477C15744967 @default.
- W80257477 hasConceptScore W80257477C186644900 @default.
- W80257477 hasConceptScore W80257477C204321447 @default.
- W80257477 hasConceptScore W80257477C206134035 @default.
- W80257477 hasConceptScore W80257477C24184978 @default.
- W80257477 hasConceptScore W80257477C2764733 @default.
- W80257477 hasConceptScore W80257477C2777530160 @default.
- W80257477 hasConceptScore W80257477C2778551981 @default.
- W80257477 hasConceptScore W80257477C2780277889 @default.
- W80257477 hasConceptScore W80257477C2781256819 @default.
- W80257477 hasConceptScore W80257477C2781449363 @default.
- W80257477 hasConceptScore W80257477C28076734 @default.
- W80257477 hasConceptScore W80257477C41008148 @default.
- W80257477 hasConceptScore W80257477C41895202 @default.
- W80257477 hasConceptScore W80257477C67277372 @default.
- W80257477 hasConceptScore W80257477C9679016 @default.
- W80257477 hasLocation W802574771 @default.
- W80257477 hasOpenAccess W80257477 @default.
- W80257477 hasPrimaryLocation W802574771 @default.
- W80257477 hasRelatedWork W138910040 @default.
- W80257477 hasRelatedWork W1510598116 @default.
- W80257477 hasRelatedWork W1539928571 @default.
- W80257477 hasRelatedWork W2021692535 @default.
- W80257477 hasRelatedWork W2038245978 @default.
- W80257477 hasRelatedWork W2039813897 @default.
- W80257477 hasRelatedWork W204341599 @default.
- W80257477 hasRelatedWork W2077810047 @default.
- W80257477 hasRelatedWork W2123024554 @default.
- W80257477 hasRelatedWork W2124741472 @default.
- W80257477 hasRelatedWork W2133258739 @default.
- W80257477 hasRelatedWork W2155069789 @default.
- W80257477 hasRelatedWork W2158831095 @default.
- W80257477 hasRelatedWork W2196463948 @default.
- W80257477 hasRelatedWork W2250555572 @default.
- W80257477 hasRelatedWork W2251357896 @default.
- W80257477 hasRelatedWork W2251784867 @default.
- W80257477 hasRelatedWork W2252071042 @default.
- W80257477 hasRelatedWork W2397240125 @default.
- W80257477 hasRelatedWork W2512290434 @default.
- W80257477 isParatext "false" @default.
- W80257477 isRetracted "false" @default.
- W80257477 magId "80257477" @default.
- W80257477 workType "article" @default.