Filters








29 Hits in 5.6 sec

Towards Evaluating the Impact of Anaphora Resolution on Text Summarisation from a Human Perspective [chapter]

Mostafa Bayomi, Killian Levacher, M. Rami Ghorab, Peter Lavin, Alexander O'Connor, Séamus Lawless
2016 Lecture Notes in Computer Science  
The study reported in this paper seeks to establish whether Anaphora Resolution (AR) can improve the quality of generated summaries, and to assess whether AR has the same impact on text from different  ...  Summarisation evaluation is critical to the development of automatic summarisation systems. Previous studies have evaluated their summaries using automatic techniques.  ...  Anaphora Resolution. The AR system used is the Stanford Deterministic Coreference Resolution System [22] which implements a multi-pass sieve coreference resolution (or anaphora resolution) system.  ... 
doi:10.1007/978-3-319-41754-7_16 fatcat:bluminc6xjbttcjpz5is3wmsje

Concept-Map-Based Multi-Document Summarization using Concept Coreference Resolution and Global Importance Optimization

Tobias Falke, Christian M. Meyer, Iryna Gurevych
2017 International Joint Conference on Natural Language Processing  
It learns to identify and merge coreferent concepts to reduce redundancy, determines their importance with a strong supervised model and finds an optimal summary concept map via integer linear programming  ...  We evaluate the model on two datasets, finding that it outperforms several approaches from previous work.  ...  First, using off-the-shelf coreference resolution, we try to resolve pronominal anaphora in arguments of the propositions.  ... 
dblp:conf/ijcnlp/FalkeMG17 fatcat:4zya63huavahtdaytu6j4wb4qa

A Scientific Information Extraction Dataset for Nature Inspired Engineering [article]

Ruben Kruiper, Julian F.V. Vincent, Jessica Chen-Burger, Marc P.Y. Desmulliez, Ioannis Konstas
2020 arXiv   pre-print
The dataset allows for training and evaluating Relation Extraction algorithms that aim for coarse-grained typing of scientific biological documents, enabling a high-level filter for engineers.  ...  The arguments of these relations can be Multi Word Expressions and have been annotated with modifying phrases to form non-projective graphs.  ...  Acknowledgments The authors would like to thank the reviewers for their useful comments, and gratefully acknowledge the financial support of the Engineering and Physical Sciences Research Council (EPSRC  ... 
arXiv:2005.07753v2 fatcat:hf764ytghne5riqcxiwfzcz3d4

Broad-coverage biomedical relation extraction with SemRep

Halil Kilicoglu, Graciela Rosemblat, Marcelo Fiszman, Dongwook Shin
2020 BMC Bioinformatics  
drug repurposing, literature-based discovery and hypothesis generation, and contributing to improved health outcomes.  ...  The recall and the F 1 score increase to 0.35 and 0.50, respectively, when the evaluation on this corpus is limited to sentence-bound relationships, which represents a fairer evaluation, as SemRep operates  ...  Rindflesch for his design and development of early SemRep iterations and his supervision until his retirement and François-Michel Lang for his contributions to various aspects of SemRep.  ... 
doi:10.1186/s12859-020-3517-7 pmid:32410573 fatcat:2rsnzh7q4nghjdeh2kpqsxozyy

Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction

Yi Luan, Luheng He, Mari Ostendorf, Hannaneh Hajishirzi
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
We introduce a multi-task setup of identifying and classifying entities, relations, and coreference clusters in scientific articles.  ...  The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links.  ...  We are grateful to Waleed Ammar and AI2 for sharing the Semantic Scholar Corpus. We also thank the anonymous reviewers, UW-NLP group and Shoou-I Yu for their helpful comments.  ... 
doi:10.18653/v1/d18-1360 dblp:conf/emnlp/LuanHOH18 fatcat:lbygoo2z2vhb5akdxt2tv4ek2m

Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction [article]

Yi Luan, Luheng He, Mari Ostendorf, Hannaneh Hajishirzi
2018 arXiv   pre-print
We introduce a multi-task setup of identifying and classifying entities, relations, and coreference clusters in scientific articles.  ...  The multi-task setup reduces cascading errors between tasks and leverages cross-sentence relations through coreference links.  ...  We are grateful to Waleed Ammar and AI2 for sharing the Semantic Scholar Corpus. We also thank the anonymous reviewers, UW-NLP group and Shoou-I Yu for their helpful comments.  ... 
arXiv:1808.09602v1 fatcat:2giti24ga5gm7moxpuag77ltri

Which techniques does your application use?: An information extraction framework for scientific articles [article]

Soham Dan, Sanyam Agarwal, Mayank Singh, Pawan Goyal, Animesh Mukherjee
2016 arXiv   pre-print
In this paper, we consider the computational linguistics domain and present a novel information extraction system that automatically constructs a pool of all application areas in this domain and appropriately  ...  pattern learning is employed to extract application areas.  ...  [12] and Lopez et al. [16] are two popular works in automatic keyphrase extraction from scientific articles. Quazvinian et al.  ... 
arXiv:1608.06386v1 fatcat:hmu4kr6lengk3jvshynuge524i

C3EL: A Joint Model for Cross-Document Co-Reference Resolution and Entity Linking

Sourav Dutta, Gerhard Weikum
2015 Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing  
KB features for already disambiguated mentions to improve CCR.  ...  C3EL incorporates results from the CCR stage into NEL, and vice versa: additional global context obtained from CCR improves the feature space and performance of NEL, while NEL in turn provides distant  ...  Entity Co-reference Resolution (CR) (Haghighi & Klein, 2010; Ng, 2010; Lee et al., 2013 ) is essentially a clustering task to identify mentions (and anaphoras) within a document referring to the same  ... 
doi:10.18653/v1/d15-1101 dblp:conf/emnlp/DuttaW15 fatcat:6wktdxvaljgwdguvfdfkjtqpu4

Cross-Document Co-Reference Resolution using Sample-Based Clustering with Knowledge Enrichment

Sourav Dutta, Gerhard Weikum
2015 Transactions of the Association for Computational Linguistics  
This allows scaling up CCR to large corpora. Experiments with three datasets show significant gains in output quality, compared to the best prior methods, and the run-time efficiency of CROCS.  ...  However, these methods exhibit limitations regarding run-time and robustness. This paper presents the CROCS framework for unsupervised CCR, improving the state of the art in two ways.  ...  The tagged texts and the local coreference chains are then passed to the second stage.  ... 
doi:10.1162/tacl_a_00119 fatcat:ho6w3izyn5frfidafc2e6fxh74

AppTechMiner: Mining Applications and Techniques from Scientific Articles [article]

Mayank Singh, Soham Dan, Sanyam Agarwal, Pawan Goyal, Animesh Mukherjee
2017 arXiv   pre-print
This paper presents AppTechMiner, a rule-based information extraction framework that automatically constructs a knowledge base of all application areas and problem solving techniques.  ...  We also categorize individual research articles based on their application areas and the techniques proposed/improved in the article.  ...  [13] and Lopez et al. [16] are two popular works in automatic keyphrase extraction from scienti c articles. azvinian et al.  ... 
arXiv:1709.03064v2 fatcat:imjvfwzrozea5btyu7yva5hemy

Generating Indicative-Informative Summaries with SumUM

Horacio Saggion, Guy Lapalme
2002 Computational Linguistics  
Relying on human judgment, we have evaluated indicativeness, informativeness, and text acceptability of the automatic summaries.  ...  We present and evaluate SumUM, a text summarization system that takes a raw technical text as input and produces an indicative informative summary.  ...  Acknowledgments We would like specially to thank Eduard Hovy for his valuable comments and suggestions, which helped improve and clarify the present work.  ... 
doi:10.1162/089120102762671963 fatcat:ziupshyti5ebhedftovomzz4cm

Concept Relation Discovery and Innovation Enabling Technology (Cordiet)

Jonas Poelmans, Paul Elzinga, Stijn Viaene, Guido Dedene
2010 Social Science Research Network  
.: Automatic Keyphrase Extraction Automatic Content Extraction (ACE): Task, Data, Evaluation.  ...  We also intend to study methods of combination automatically extracted near-synonyms, methods of coreference resolution and thesaurus relations.  ... 
doi:10.2139/ssrn.1713124 fatcat:f27e6pnel5awtkziz2qxmpqrzq

A Multi-Lingually Applicable Journalist Toolset For The Big-Data Era

G. Kiomourtzis, G. Giannakopoulos, V. Karkaletsis, A. Kosmopoulos
2016 Zenodo  
Acknowledgments I would like to thank Dr. Octavian Popescu for his constant guidance, endless suggestions and encouragement and full support to finish this work.  ...  Acknowledgments: The authors would like to thank the anonymous reviewers for their helpful comments and suggestions.  ...  Anaphora resolution is performed for each of the clauses.  ... 
doi:10.5281/zenodo.1242850 fatcat:nfkqg7jhjffdvgezdjzc6xxppa

Mining meaning from Wikipedia

Olena Medelyan, David Milne, Catherine Legg, Ian H. Witten
2009 International Journal of Human-Computer Studies  
language processing; using it to facilitate information retrieval and information extraction; and as a resource for ontology building.  ...  The article addresses how Wikipedia is being used as is, how it is being improved and adapted, and how it is being combined with other structures to create entirely new resources.  ...  We are also grateful to Enrico Motta and Susan Wiedenbeck for guiding us in the right direction.  ... 
doi:10.1016/j.ijhcs.2009.05.004 fatcat:mzxszf4jlfcizbgxuemgdwzdiy

Improved Local Citation Recommendation Based on Context Enhanced with Global Information

Zoran Medić, Jan Snajder
2020 Proceedings of the First Workshop on Scholarly Document Processing   unpublished
We evaluate our model on datasets with different citation context sizes and demonstrate improvements with globallyenhanced context representations when citation contexts are smaller.  ...  Specifically, we include citing article's title and abstract into context representation.  ...  we show that inclusion of global information besides citation context helps when citation contexts are smaller. 2 Excerpt is from Evaluating anaphora and coreference resolution to improve automatic keyphrase  ... 
doi:10.18653/v1/2020.sdp-1.11 fatcat:cscmajr2dfbyjb7w26a2krxpyi
« Previous Showing results 1 — 15 out of 29 results