Filters








478 Hits in 4.7 sec

A self-training approach for resolving object coreference on the semantic web

Wei Hu, Jianfeng Chen, Yuzhong Qu
2011 Proceedings of the 20th international conference on World wide web - WWW '11  
In this paper, we propose a self-training approach for object coreference resolution on the Semantic Web, which leverages the two classes of approaches to bridge the gap between semantically coreferent  ...  We implement a scalable system and demonstrate that our approach achieves good precision and recall for resolving object coreference, on both benchmark and large-scale datasets.  ...  In the near future, we will perform more experiments for parameter setting in our self-training approach, such as determining the optimal iteration times.  ... 
doi:10.1145/1963405.1963421 dblp:conf/www/HuCQ11 fatcat:grqj2okvnvh65ig3d5ravcgujm

Bootstrapping path-based pronoun resolution

Shane Bergsma, Dekang Lin
2006 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the ACL - ACL '06  
Through a simple bootstrapping procedure, we learn the likelihood of coreference between a pronoun and a candidate noun based on the path in the parse tree between the two entities.  ...  We present an approach to pronoun resolution based on syntactic paths.  ...  The web-based approach outperformed the corpus-based approach, while a system that combined the two sets of information resulted in the highest performance (Table 3 ).  ... 
doi:10.3115/1220175.1220180 dblp:conf/acl/BergsmaL06 fatcat:fdbxsdabmzftfaewxko2nwvgb4

Joint Semantic Analysis with Document-Level Cross-Task Coherence Rewards [article]

Rahul Aralikatte, Mostafa Abdou, Heather Lent, Daniel Hershcovich, Anders Søgaard
2020 arXiv   pre-print
We present a neural network architecture for joint coreference resolution and semantic role labeling for English, and train graph neural networks to model the 'coherence' of the combined shallow semantic  ...  This leads to improvements on both tasks in multiple datasets from different domains, and across a range of encoders of different expressivity, calling, we believe, for a more holistic approach to semantics  ...  In this paper, we investigate a "minimal" approach to discourse-level semantic parsing, combining coreference and semantic roles in shallow semantic graphs (SSGs) that can be seen as a simple, yet rich  ... 
arXiv:2010.05567v1 fatcat:3nc6abqx3zgnlbyqxtbj2gtmxa

SANAPHOR: Ontology-Based Coreference Resolution [chapter]

Roman Prokofyev, Alberto Tonon, Michael Luggen, Loic Vouilloz, Djellel Eddine Difallah, Philippe Cudré-Mauroux
2015 Lecture Notes in Computer Science  
We tackle the problem of resolving coreferences in textual content by leveraging Semantic Web techniques.  ...  Then, we propose an approach to type noun phrases using an inverted index built on top of a Knowledge Graph (e.g., DBpedia).  ...  This work was supported by the Swiss National Science Foundation under grant number PP00P2 153023, and by the Haslerstiftung in the context of the Smart World 11005 (Mem0r1es) project.  ... 
doi:10.1007/978-3-319-25007-6_27 fatcat:lmcrxneprbfj3illdd54ib2zuq

Using Lexical and Encyclopedic Knowledge [chapter]

Yannick Versley, Massimo Poesio, Simone Ponzetto
2016 Anaphora Resolution  
Semantic information is one of the indispensable ingredients that are necessary to raise the performance of anaphora resolution both for pronominal anaphors and for anaphoric definite descriptions beyond  ...  In contrast to hard criteria such as binding and agreement constraints, however, the question of semantic constraints and preferences and its operationalization in a system that performs anaphora resolution  ...  Learning Semantic Information from Coreference Corpora The fact that it is possible to learn semantics constraints or preferences for coreference from coreferentially annotated corpora sounds self-evident  ... 
doi:10.1007/978-3-662-47909-4_14 dblp:series/tanlp/VersleyPP16 fatcat:xjwq7ae47zhwribgolaj42xlae

Bridging Chasms In Hindustani Music Retrieval

Joe Cheri Ross, Preeti Rao, Pushpak Bhattacharyya
2018 Zenodo  
This research is motivated by the importance of a music recommendation system for Hindustani music.  ...  Our investigation on extracting meta-information from natural language text focuses on coreference resolution, with the aim of improving relation extraction from textual content.  ...  This document is classified as one of the semantic classes with the pre-trained model (output of semantic classid web train).  ... 
doi:10.5281/zenodo.1237568 fatcat:mrshrvhbcbb2lf4n7gys6e6plq

Bridging Chasms In Hindustani Music Retrieval

Joe Cheri Ross, Preeti Rao, Pushpak Bhattacharyya
2018 Zenodo  
This research is motivated by the importance of a music recommendation system for Hindustani music.  ...  Our investigation on extracting meta-information from natural language text focuses on coreference resolution, with the aim of improving relation extraction from textual content.  ...  This document is classified as one of the semantic classes with the pre-trained model (output of semantic classid web train).  ... 
doi:10.5281/zenodo.1239418 fatcat:uix3v2agqrajtcdrn5wm74tnq4

Solving Hard Coreference Problems

Haoruo Peng, Daniel Khashabi, Dan Roth
2015 Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies  
In this paper we propose an algorithmic solution that involves a new representation for the knowledge required to address hard coreference problems, along with a constrained optimization framework that  ...  We present a general coreference resolution system that significantly improves state-of-the-art performance on hard, Winograd-style, pronoun resolution cases, while still performing at the stateof-the-art  ...  Acknowledgments The authors would like to thank Kai-Wei Chang, Alice Lai, Eric Horn and Stephen Mayhew for comments that helped to improve this work.  ... 
doi:10.3115/v1/n15-1082 dblp:conf/naacl/PengKR15 fatcat:3wj6ajrt2bh63cgtynieinehs4

Distantly supervised Web relation extraction for knowledge base population

Isabelle Augenstein, Diana Maynard, Fabio Ciravegna, Krzysztof Janowicz, Stefan Schlobach, Stefan Schlobach, Krzysztof Janowicz
2016 Semantic Web Journal  
In this paper we propose the use of distant supervision for relation extraction from the Web.  ...  Although the method is promising, existing approaches are still not suitable for Web extraction as they suffer from three main issues: data sparsity, noise and lexical ambiguity.  ...  Acknowledgements We thank the EKAW and SWJ reviewers for their valuable feedback.  ... 
doi:10.3233/sw-150180 fatcat:3b4eg5nr25aczife7seenjgrvi

Minimalistic Approach to Coreference Resolution in Lithuanian Medical Records

Voldemaras Žitkus, Rita Butkienė, Rimantas Butleris, Rytis Maskeliūnas, Robertas Damaševičius, Marcin Woźniak
2019 Computational and Mathematical Methods in Medicine  
We present a method for coreference resolution in Lithuanian language and its application for processing e-health records from a hospital reception.  ...  Coreference resolution requires linguistic preprocessing and rich language resources for automatically identifying and resolving such expressions.  ...  Both approaches were trained and evaluated on PTD data with ranker-based approach providing better results.  ... 
doi:10.1155/2019/9079840 fatcat:czajdp2d6ndpvlty2kgvap5h7y

What do you learn from context? Probing for sentence structure in contextualized word representations [article]

Ian Tenney, Patrick Xia, Berlin Chen, Alex Wang, Adam Poliak, R Thomas McCoy, Najoung Kim, Benjamin Van Durme, Samuel R. Bowman, Dipanjan Das, Ellie Pavlick
2019 arXiv   pre-print
We find that existing models trained on language modeling and translation produce strong representations for syntactic phenomena, but only offer comparably small improvements on semantic tasks over a non-contextual  ...  ., 2018) have recently achieved state-of-the-art results on a diverse array of downstream NLP tasks.  ...  Special thanks to Jacob Devlin for providing checkpoints of GPT model trained on the BWB corpus, and to the members of the Google AI Language team for many productive discussions.  ... 
arXiv:1905.06316v1 fatcat:u3bkjoqeunewtklj6fhdvhnsvy

Question Answering on Linked Data

Saeedeh Shekarpour, Kemele M. Endris, Ashwini Jaya Kumar, Denis Lukovnikov, Kuldeep Singh, Harsh Thakkar, Christoph Lange
2016 Proceedings of the 25th International Conference Companion on World Wide Web - WWW '16 Companion  
Thus, it helps researchers to easily spot open rooms for the future research agenda. the Data Web we need similar user friendly approaches i.e. keyword-based interfaces, which lie on the internal structure  ...  In this paper, we raise the challenges for building a Question Answering (QA) system especially with the focus of employing structured data (i.e. knowledge graph).  ...  Based on the results of the DMN on that dataset, it can be assumed that it actually learned to perform coreference resolution where needed without any explicit model or a supervision signal for coreference  ... 
doi:10.1145/2872518.2890571 dblp:conf/www/ShekarpourEKLST16 fatcat:xxdnuur3nnauhcvc7lwhltpjxu

Domain-Independent Entity Coreference for Linking Ontology Instances

Dezhao Song, Jeff Heflin
2013 Journal of Data and Information Quality  
There has been numerous research for linking ontology instances in the Semantic Web. Linked Data 3 [Bizer et al. 2009 ] is one of the leading efforts in this area.  ...  In the Semantic Web, coreferent instances are linked to each other with the owl:sameAs predicate and then such coreference information can be further utilized by other aspects of Semantic Web related research  ...  In a second step, ObjectCoref utilizes self-training [Zhou and Li 2010] to learn the discriminability of property pairs based on the coreferent instances used for training.  ... 
doi:10.1145/2435221.2435223 dblp:journals/jdiq/SongH13 fatcat:jn7ss35ovvglnnz4375cchtfmq

Anaphora and Coreference Resolution: A Review [article]

Rhea Sukthanker, Soujanya Poria, Erik Cambria, Ramkumar Thirunavukarasu
2018 arXiv   pre-print
Entity resolution aims at resolving repeated references to an entity in a document and forms a core component of natural language processing (NLP) research.  ...  The area of entity resolution in NLP has seen proliferation of research in two separate sub-areas namely: anaphora resolution and coreference resolution.  ...  The training objective was a function of the cluster features (lexical, semantic, syntactic, etc.).  ... 
arXiv:1805.11824v1 fatcat:ighrkr6f2nexphrw3qfojatmde

Semantic Web Machine Reading with FRED

Aldo Gangemi, Valentina Presutti, Diego Reforgiato Recupero, Andrea Giovanni Nuzzolese, Francesco Draicchio, Misael Mongiovì, Harith Alani
2017 Semantic Web Journal  
We describe the capabilities of FRED as a semantic middleware for semantic web applications.  ...  FRED is a machine reader for extracting RDF graphs that are linked to LOD and compliant to Semantic Web and Linked Data patterns.  ...  Introduction This paper presents a detailed description of FRED [31] , a machine reader for the Semantic Web, which solves a stack of native Semantic Web (SW) machine reading tasks.  ... 
doi:10.3233/sw-160240 fatcat:6uqoj5ymlfgn5e5gbqiocyg7ni
« Previous Showing results 1 — 15 out of 478 results