Filters








86 Hits in 4.1 sec

Frame Detection over the Semantic Web [chapter]

Bonaventura Coppola, Aldo Gangemi, Alfio Gliozzo, Davide Picca, Valentina Presutti
2009 Lecture Notes in Computer Science  
In the past, research in ontology learning from text has mainly focused on entity recognition, taxonomy induction and relation extraction.  ...  In this work we approach a challenging research issue: detecting semantic frames from texts and using them to encode web ontologies.  ...  Acknowledgements We thank Daniele Pighin and Alessandro Moschitti at University of Trento for their critical support in developing the Frame Detection module.  ... 
doi:10.1007/978-3-642-02121-3_13 fatcat:ljawn33iyff5pmrff5ci5tmlr4

Coarse Lexical Semantic Annotation with Supersenses: An Arabic Case Study

Nathan Schneider, Behrang Mohit, Kemal Oflazer, Noah A. Smith
2012 Annual Meeting of the Association for Computational Linguistics  
In this paper, we repurpose WordNet's supersense tags for annotation, developing specific guidelines for nominal expressions and applying them to Arabic Wikipedia articles in four topical domains.  ...  Lightweight" semantic annotation of text calls for a simple representation, ideally without requiring a semantic lexicon to achieve good coverage in the language and domain.  ...  Acknowledgments We thank Nourhen Feki and Sarah Mustafa for assistance with annotation, as well as Emad Mohamed, CMU ARK members, and anonymous reviewers for their comments.  ... 
dblp:conf/acl/SchneiderMOS12 fatcat:a3sccljsdrbrzghojyfrwlg6ne

Improving Translation Selection with Supersenses

Haiqing Tang, Deyi Xiong, Oier Lopez de Lacalle, Eneko Agirre
2016 International Conference on Computational Linguistics  
In this paper, we adopt a supersense tagging method to annotate source words with coarse-grained ontological concepts.  ...  : a maximum entropy based model and a supersense embedding model.  ...  We also thank the anonymous reviewers for their insightful comments.  ... 
dblp:conf/coling/TangXLA16 fatcat:3yxbncahkrhhthw7uswqlz2wra

Knowledge Graph Construction and Its Application in Automatic Radiology Report Generation from Radiologist's Dictation [article]

Kaveri Kale, Pushpak Bhattacharyya, Aditya Shetty, Milind Gune, Kush Shrivastava, Rustom Lawyer, Spriha Biswas
2022 arXiv   pre-print
In current research work, we focus on applications of NLP techniques like Information Extraction (IE) and domain-specific Knowledge Graph (KG) to automatically generate radiology reports from radiologist's  ...  Also, our analysis shows that our IE module is performing better than the OpenIE tool for the radiology domain.  ...  We have constructed KGs for Ultrasound scan procedure. We plan to construct KGs for other scan procedures like CT, MRI, X-Ray, etc., using above mentioned KG construction module.  ... 
arXiv:2206.06308v2 fatcat:a5ifhm277rh25a2wdwa3a2arly

Word vs. Class-Based Word Sense Disambiguation

Ruben Izquierdo, Armando Suarez, German Rigau
2015 The Journal of Artificial Intelligence Research  
However, the meanings represented by WordNet have been only used for WSD at a very fine-grained sense level or at a very coarse-grained semantic class level (also called SuperSenses).  ...  Finally, we also demonstrate the robustness of our supervised semantic class-based WSD system when tested on out of domain corpus.  ...  Even better, we can use BLC20 for tagging nouns (558 semantic classes and F1 over 75%) and SuperSenses for verbs (14 semantic classes and F1 around 75%).  ... 
doi:10.1613/jair.4727 fatcat:pgi7mb3ilzayta6d5vszwfbgsi

WikiSense: Supersense Tagging of Wikipedia Named Entities Based WordNet

Joseph Z. Chang, Richard Tzong-Han Tsai, Jason S. Chang
2009 Pacific Asia Conference on Language, Information and Computation  
In this paper, we introduce a minimally supervised method for learning to classify named-entity titles in a given encyclopedia into broad semantic categories in an existing ontology.  ...  Our main idea involves using overlapping entries in the encyclopedia and ontology and a small set of 30 handed tagged parenthetic explanations to automatically generate the training data.  ...  Supersense tagging of Wikipedia title is a preliminary step for providing more specific semantic linkage between Wikipedia and WordNet.  ... 
dblp:conf/paclic/ChangTC09 fatcat:z3mabv6s3rcuxbaggwymfie2ua

A Survey of Thai Knowledge Extraction for the Semantic Web Research and Tools

Ponrudee NETISOPAKUL, Gerhard WOHLGENANNT
2018 IEICE transactions on information and systems  
As the manual creation of domain models and also of linked data is very costly, the extraction of knowledge from structured and unstructured data has been one of the central research areas in the Semantic  ...  To address the goal, first we distinguish nine knowledge extraction for the Semantic Web tasks defined in literature on knowledge extraction from English text, for example taxonomy extraction, relation  ...  Also, this work was supported by the Government of the Russian Federation (Grant 074-U01) through the ITMO Fellowship and Professorship Program.  ... 
doi:10.1587/transinf.2017dar0001 fatcat:ruhxzaxog5durmdu33z6ch6n4e

Minimally Supervised Question Classification and Answering based on WordNet and Wikipedia

Joseph Chang, Tzu-Hsi Yen, Tzong-Han Tsai
2009 Taiwan Conference on Computational Linguistics and Speech Processing  
for open domain question answering.  ...  For this, we also constructed a large scale entity supersense database that contains over 1.5 million entities to the 25 WordNet lexicographer's files (supersenses) from titles of Wikipedia entry.  ...  However, most high performance NER systems deal with a specific domain, focus on homogeneous corpora, and support a small set of NE types.  ... 
dblp:conf/rocling/ChangYT09 fatcat:js2kbnriyrectdh3gwfpndyo7q

Hierarchical Semantic Classification: Word Sense Disambiguation with World Knowledge

Massimiliano Ciaramita, Thomas Hofmann, Mark Johnson
2003 International Joint Conference on Artificial Intelligence  
We present a learning architecture for lexical semantic classification problems that supplements task-specific training data with background data encoding general "world knowledge".  ...  The model compiles knowledge contained in a dictionaryontology into additional training data, and integrates task-specific and background data through a novel hierarchical learning architecture.  ...  Conclusion We have presented a learning architecture for lexical semantic classification that supplements task-specific training data with background data encoding general "world knowledge" extracted from  ... 
dblp:conf/ijcai/CiaramitaHJ03 fatcat:atufyjyshzhbdc5jgphaiu74sa

Scientific document summarization via citation contextualization and scientific discourse

Arman Cohan, Nazli Goharian
2017 International Journal on Digital Libraries  
We propose three approaches for contextualizing citations which are based on query reformulation, word embeddings, and supervised learning.  ...  We evaluate our proposed method on two scientific summarization datasets in the biomedical and computational linguistics domains.  ...  For the ontology, since TAC data is in biomedical domain we use two domain-specific ontologies, Mesh 7 [52] and Protein Ontology (PRO). 8 For the CL-SciSum data, since it is less domain-specific, we  ... 
doi:10.1007/s00799-017-0216-8 fatcat:4zwdaqixnzei3i6yegahz3gxge

Exploiting Semantic Constraints for Estimating Supersenses with CRFs [chapter]

Gerhard Paaß, Frank Reichartz
2009 Proceedings of the 2009 SIAM International Conference on Data Mining  
The annotation of words and phrases by ontology concepts is extremely helpful for semantic interpretation. However many ontologies, e.g.  ...  By this and the use of new features we are able to increase the f-value for about 8% compared to previous results.  ...  Learning Approaches for Supersense Tagging Fine grained word disambiguation has to cope with thousands of categories.  ... 
doi:10.1137/1.9781611972795.42 dblp:conf/sdm/PaassR09 fatcat:jztg4a2myna7pk6cxfpmxunlqq

On Contribution of Sense Dependencies to Word Sense Disambiguation

Jun Hatori, Yusuke Miyao, Jun'ichi Tsujii
2009 Journal of Natural Language Processing  
Furthermore, we incorporate these sense dependencies in combination with various coarse-grained sense tag sets, which are expected to relieve the data sparseness problem, and enable our model to work even  ...  One major obstacle for large-scale and precise WSD is the data sparseness problem caused by the fine-grained nature of the sense distinction.  ...  Acknowledgment This work was partially supported by Grant-in-Aid for Specially Promoted Research (MEXT, Japan).  ... 
doi:10.5715/jnlp.16.5_51 fatcat:j2axsg5ujnfehiyju2ue4gbcbq

Design and Evaluation of Metaphor Processing Systems

Ekaterina Shutova
2015 Computational Linguistics  
These include, for example, (1) machine translation (MT): since a large number of metaphorical expressions are culture-specific, they represent a considerable challenge for MT (e.g. the English metaphor  ...  However, computational work on metaphor is considerably more fragmented than similar research efforts in other areas of NLP and semantics.  ...  roles, WordNet supersenses, named entity types and domain types extracted from ontologies; and semantic properties of concepts, such as animateness and concreteness.  ... 
doi:10.1162/coli_a_00233 fatcat:xndjednwznb6ldr54xh6r4u6wu

Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection

Marek Rei, Luana Bulat, Douwe Kiela, Ekaterina Shutova
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing  
Yet, the majority of metaphor processing systems to date rely on handengineered features and there is still no consensus in the field as to which features are optimal for this task.  ...  In this paper, we present the first deep learning architecture designed to capture metaphorical composition.  ...  still retain their domain-specific semantic information.  ... 
doi:10.18653/v1/d17-1162 dblp:conf/emnlp/ReiBKS17 fatcat:ikyxdqgrg5djfagk5vdarwmghu

Grasping the Finer Point: A Supervised Similarity Network for Metaphor Detection [article]

Marek Rei, Luana Bulat, Douwe Kiela, Ekaterina Shutova
2017 arXiv   pre-print
Yet, the majority of metaphor processing systems to date rely on hand-engineered features and there is still no consensus in the field as to which features are optimal for this task.  ...  In this paper, we present the first deep learning architecture designed to capture metaphorical composition.  ...  still retain their domain-specific semantic information.  ... 
arXiv:1709.00575v1 fatcat:fshqlijhl5fmrh5lrs2g2w434q
« Previous Showing results 1 — 15 out of 86 results