FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W1550261314> ?p ?o ?g. }

• W1550261314 abstract "Coreference resolution (CR) and entity relation detection (ERD) aim at finding predefined relations between pairs of entities in text. CR focuses on resolving identity relations while ERD focuses on detecting non-identity relations. Both CR and ERD are important as they can potentially improve other natural language processing (NLP) related tasks such information retrieval and extraction, web-searching, and question answering and also enhance non-NLP tasks such as computer vision, database constructions or ontologies. In this thesis, I propose models to handle both coreference resolution (CR) and entity relation detection (ERD). Both systems are built on machine learning models. The CR system is based on Factorial Hidden Markov Models (FHMMs). The ERD is based on Maximum Entropy Discriminant Latent Dirichlet Allocation (MEDLDA). The work on CR only resolves pronouns. It is a supervised system trained on annotated corpus. The basic idea is that the hidden states of FHMMs are an explicit short-term memory with an antecedent buffer containing recently described referents. Thus an observed pronoun can find its antecedent from the hidden buffer, or in terms of a generative model, the entries in the hidden buffer generate the corresponding pronouns. In the hidden buffer, all references are expressed as diverse features. In this work, besides the common gender, number, person and animacy, I converted Givenness Hierarchy and Centering Theories to probabilistic features, thus greatly improving the accuracy. A system implementing this model is evaluated on the ACE corpus and I2B2 medical corpus with promising performance. For ERD, a novel application of topic models is proposed to do this task. In order to make use of the latent semantics of text, the task of relation detection is reformulated as a topic modeling problem. The motivation is to find underlying topics which are indicative of relations between named entities. The approach considers pairs of named entities and features associated with them as mini documents. The system, called ERD-MEDLDA, adapts Maximum Entropy Discriminant Latent Dirichlet Allocation (MedLDA) with mixed membership for relation detection. By using supervision, ERD-MedLDA is able to learn topic distributions indicative of relation types. Further, ERD- MEDLDA is a topic model that combines the benefits of both Maximum Likelihood Estimation (MLE) and Maximum Margin Estimation (MME), and the mixed membership formulation enables the system to incorporate heterogeneous features. We incorporate diverse features into the system and perform experiments on the ACE 2005 corpus. Our approach achieves better overall performance for precision, recall and Fmeasure metrics as compared to SVM-based and LDA-based models. ERD-MedLDA also shows better overall performance than state-of-the-art kernels used previously for relation detection." @default.
• W1550261314 created "2016-06-24" @default.
• W1550261314 creator A5058247448 @default.
• W1550261314 creator A5083826804 @default.
• W1550261314 creator A5086362177 @default.
• W1550261314 date "2011-01-01" @default.
• W1550261314 modified "2023-09-23" @default.
• W1550261314 title "Entity relation detection with factorial hidden markov models and maximum entropy discriminant latent dirichlet allocations" @default.
• W1550261314 cites W1480643256 @default.
• W1550261314 cites W1508666480 @default.
• W1550261314 cites W1509297014 @default.
• W1550261314 cites W1528056001 @default.
• W1550261314 cites W1549589075 @default.
• W1550261314 cites W1550588214 @default.
• W1550261314 cites W1579838312 @default.
• W1550261314 cites W1581262234 @default.
• W1550261314 cites W1587871245 @default.
• W1550261314 cites W1598003989 @default.
• W1550261314 cites W1599286053 @default.
• W1550261314 cites W1612003148 @default.
• W1550261314 cites W1789782362 @default.
• W1550261314 cites W1821047628 @default.
• W1550261314 cites W1880262756 @default.
• W1550261314 cites W196410832 @default.
• W1550261314 cites W1965693266 @default.
• W1550261314 cites W1969486090 @default.
• W1550261314 cites W1981082061 @default.
• W1550261314 cites W1989886885 @default.
• W1550261314 cites W2013039990 @default.
• W1550261314 cites W2023696455 @default.
• W1550261314 cites W2025341897 @default.
• W1550261314 cites W2030408698 @default.
• W1550261314 cites W2042972234 @default.
• W1550261314 cites W2051895482 @default.
• W1550261314 cites W2053238041 @default.
• W1550261314 cites W2059933135 @default.
• W1550261314 cites W2068580143 @default.
• W1550261314 cites W2091033539 @default.
• W1550261314 cites W2096110600 @default.
• W1550261314 cites W2096400145 @default.
• W1550261314 cites W2097606805 @default.
• W1550261314 cites W2098062695 @default.
• W1550261314 cites W2101101940 @default.
• W1550261314 cites W2101268022 @default.
• W1550261314 cites W2105745072 @default.
• W1550261314 cites W2107598941 @default.
• W1550261314 cites W2108211831 @default.
• W1550261314 cites W2119821739 @default.
• W1550261314 cites W2120814856 @default.
• W1550261314 cites W2122207982 @default.
• W1550261314 cites W2122410182 @default.
• W1550261314 cites W2122683976 @default.
• W1550261314 cites W2127713198 @default.
• W1550261314 cites W2129604374 @default.
• W1550261314 cites W2130031580 @default.
• W1550261314 cites W2130300813 @default.
• W1550261314 cites W2132516856 @default.
• W1550261314 cites W2138627627 @default.
• W1550261314 cites W2139354869 @default.
• W1550261314 cites W2144874553 @default.
• W1550261314 cites W2145208835 @default.
• W1550261314 cites W2146191280 @default.
• W1550261314 cites W2147706904 @default.
• W1550261314 cites W2152269015 @default.
• W1550261314 cites W2152311353 @default.
• W1550261314 cites W2152917747 @default.
• W1550261314 cites W2157944021 @default.
• W1550261314 cites W2159149403 @default.
• W1550261314 cites W2161050705 @default.
• W1550261314 cites W2165935464 @default.
• W1550261314 cites W2170495237 @default.
• W1550261314 cites W2170750237 @default.
• W1550261314 cites W2171353991 @default.
• W1550261314 cites W2181470043 @default.
• W1550261314 cites W2756694897 @default.
• W1550261314 cites W65330238 @default.
• W1550261314 hasPublicationYear "2011" @default.
• W1550261314 type Work @default.
• W1550261314 sameAs 1550261314 @default.
• W1550261314 citedByCount "0" @default.
• W1550261314 crossrefType "dissertation" @default.
• W1550261314 hasAuthorship W1550261314A5058247448 @default.
• W1550261314 hasAuthorship W1550261314A5083826804 @default.
• W1550261314 hasAuthorship W1550261314A5086362177 @default.
• W1550261314 hasConcept C138268822 @default.
• W1550261314 hasConcept C153604712 @default.
• W1550261314 hasConcept C154945302 @default.
• W1550261314 hasConcept C171686336 @default.
• W1550261314 hasConcept C195807954 @default.
• W1550261314 hasConcept C204321447 @default.
• W1550261314 hasConcept C23224414 @default.
• W1550261314 hasConcept C28076734 @default.
• W1550261314 hasConcept C41008148 @default.
• W1550261314 hasConcept C500882744 @default.
• W1550261314 hasConcept C9679016 @default.
• W1550261314 hasConceptScore W1550261314C138268822 @default.
• W1550261314 hasConceptScore W1550261314C153604712 @default.
• W1550261314 hasConceptScore W1550261314C154945302 @default.
• W1550261314 hasConceptScore W1550261314C171686336 @default.
• W1550261314 hasConceptScore W1550261314C195807954 @default.

• next