Filters








713 Hits in 6.3 sec

Computational aspects of discourse in the context of MUC-3

Lucja Iwańska, Douglas Appelt, Damaris Ayuso, Kathy Dahlgren, Bonnie Glover Stalls, Ralph Grishman, George Krupka, Christine Montgomery, Ellen Riloff
1991 Proceedings of the 3rd conference on Message understanding - MUC3 '91  
CONCLUSIO N We discussed discourse-related processing in the context of MUC-3 conference .  ...  Although many aspects of our discourse module are preliminary, we were impressed with how well i t performed for MUC-3 .  ... 
doi:10.3115/1071958.1071998 dblp:conf/muc/IwanskaAADSGKMR91 fatcat:boqdsdo73zepbic3w2hjpfdj5i

Scoring Coreference Chains with Split-Antecedent Anaphors [article]

Silviu Paun and Juntao Yu and Nafise Sadat Moosavi and Massimo Poesio
2022 arXiv   pre-print
As part of the work towards a new scorer for anaphoric reference able to evaluate all aspects of anaphoric interpretation in the coverage of the Universal Anaphora initiative, we propose in this paper  ...  constructed out of other entities, as in split-antecedent plurals and in some cases of discourse deixis.  ...  Acknowledgments This research was supported in part by the DALI project, ERC Grant 695662.  ... 
arXiv:2205.12323v1 fatcat:iucx7zdmdfgdjf5v4u2vpvk6wm

GE NLTooLSET

George Krupka, Lucja Iwańska, Paul Jacobs, Lisa Rau
1991 Proceedings of the 3rd conference on Message understanding - MUC3 '91  
Abstrac t This paper reports on the GE NLTooLsET customization effort for MUC-3, and analyzes th e results of the TST2 run .  ...  The analysis of this unexpected result explains some of the details of the i1'UC-3 test, and we propose ways of looking at the score s . to distinguish different aspects of system performance .  ...  66 The MUC Tas k Certain aspects of this MUC task did not test the text processing capabilities of the systems .  ... 
doi:10.3115/1071958.1071967 dblp:conf/muc/KrupkaIJR91 fatcat:v3vj4cuutnfddnoxy5b6dyfxxi

Interaction between dialog structure and coreference resolution

Amanda J. Stent, Srinivas Bangalore
2010 2010 IEEE Spoken Language Technology Workshop  
Determining the coreference of entity mentions in a discourse is a key part of the interpretation process for advanced spoken dialog applications.  ...  In this paper, we present the most comprehensive system for statistical coreference resolution in dialog to date.  ...  the impact of two models of dialog structure, the stack model and the cache model, in the context of our system.  ... 
doi:10.1109/slt.2010.5700875 dblp:conf/slt/StentB10 fatcat:ipebg6x4vrcrlbziwqodhsszzy

GE

George Krupka, Paul Jacobs, Lisa Rau, Lucja Iwańska
1991 Proceedings of the 3rd conference on Message understanding - MUC3 '91  
These basic enhancements preceded the other additions, including a discourse processing module ;, which were made for MUC-3 .  ...  The performance of the program on tasks such as MUCK-II and MUC-3 derives mainly from two design characteristics : central knowledge hierarchies and flexible control strategies .  ...  Overview of Exampl e In many ways, TST1-0099 is representative of how the Toolset performed on MUC-3 .  ... 
doi:10.3115/1071958.1071983 dblp:conf/muc/KrupkaJRI91 fatcat:3ht6knhas5ctpdmwsh3pradkai

A Performance Evaluation of Text-Analysis Technologies

Wendy G. Lehnert, Beth Sundheim
1991 The AI Magazine  
does not represent an official analysis of MUC-3, its methodology, or results. The views expressed herein are solely those of the authors as participants in the evaluation and conference.  ...  The official conference report is available in proceedings form (MUC-3 1991). Notes 1.  ...  With a large corpus of the type available for MUC-3, processes at the discourse level can now be studied more systematically.  ... 
doi:10.1609/aimag.v12i3.905 dblp:journals/aim/LehnertS91 fatcat:mfualy6henfnln47jfnvyx7wuu

Event Coreference Resolution with Non-Local Information

Jing Lu, Vincent Ng
2020 International Joint Conference on Natural Language Processing  
of an event mention using discourse contexts computed based on salient entities.  ...  Existing event coreference resolvers have largely focused on exploiting the information extracted from the local contexts of the event mentions under consideration.  ...  Acknowledgments We thank the three anonymous reviewers for their detailed and insightful comments on an earlier draft of the paper.  ... 
dblp:conf/ijcnlp/LuN20 fatcat:yut4e5qxd5befoc5heafsequhu

Whose Idea Was This, and Why Does it Matter? Attributing Scientific Work to Citations

Advaith Siddharthan, Simone Teufel
2007 North American Chapter of the Association for Computational Linguistics  
Scientific papers revolve around citations, and for many discourse level tasks one needs to know whose work is being talked about at any point in the discourse.  ...  We discuss the suitability of different evaluation metrics and evaluate our classification approach to deciding attribution both intrinsically and in an extrinsic evaluation where information about scientific  ...  Acknowledgements This work was funded by the EPSRC project SciBorg (EP/C010035/1, Extracting the Science from Scientific Publications).  ... 
dblp:conf/naacl/SiddharthanT07 fatcat:n7kyvj3fxzavpkvqg2rvl35scm

Coreference Resolution across Corpora: Languages, Coding Schemes, and Preprocessing Information

Marta Recasens, Eduard H. Hovy
2010 Annual Meeting of the Association for Computational Linguistics  
This paper explores the effect that different corpus configurations have on the performance of a coreference resolution system, as measured by MUC, B 3 , and CEAF.  ...  They also expose systematic biases in the coreference evaluation metrics. We show that system comparison is only possible when corpus parameters are in exact agreement.  ...  Antònia Martí for her generosity in allowing the first author to visit ISI to work with the second. Special thanks to Edgar Gonzàlez for his kind help with conversion issues.  ... 
dblp:conf/acl/RecasensH10 fatcat:exa3yp6tprhypi75tszshfqjoy

New York University

Ralph Grishman, John Sterling, Catherine Macleod
1991 Proceedings of the 3rd conference on Message understanding - MUC3 '91  
in the Context of MUC-3") .  ...  Some further discussion of reference resolution and the subsequent process of template merging i s included in a separate paper on discourse analysis in this volume ("Computational Aspects of Discourse  ... 
doi:10.3115/1071958.1071989 dblp:conf/muc/GrishmanSM91a fatcat:2ezi4zxm2bh2bpwakc3p7gvldm

Peeling Back the Layers: Detecting Event Role Fillers in Secondary Contexts

Ruihong Huang, Ellen Riloff
2011 Annual Meeting of the Association for Computational Linguistics  
The goal of our research is to improve event extraction by learning to identify secondary role filler contexts in the absence of event keywords.  ...  We present results on the MUC-4 event extraction data set and show that this model performs better than previous systems.  ...  Any opinions, findings, and conclusion or recommendations expressed in this material are those of the authors and do not necessarily reflect the view of the DARPA, AFRL, or the U.S. government.  ... 
dblp:conf/acl/HuangR11 fatcat:frx4deuk5fdcjmhkdunzt4ur4m

Anaphora and Coreference Resolution: A Review [article]

Rhea Sukthanker, Soujanya Poria, Erik Cambria, Ramkumar Thirunavukarasu
2018 arXiv   pre-print
The area of entity resolution in NLP has seen proliferation of research in two separate sub-areas namely: anaphora resolution and coreference resolution.  ...  Through this review article, we aim at clarifying the scope of these two tasks in entity resolution.  ...  In the first sentence (3) refers to (2) and in the second sentence (3) refers to (1). What results in this transition here is only the change of the verb involved in the discourse.  ... 
arXiv:1805.11824v1 fatcat:ighrkr6f2nexphrw3qfojatmde

Overview of results of the MUC-6 evaluation

Beth M. Sundheim
1996 Proceedings of a workshop on held at Vienna, Virginia May 6-8, 1996 -  
The inclusion of four different tasks in the evaluation implicitly encouraged sites to design general-purpos e architectures that allow the production of a variety of types of output from a single internal  ...  representation in orde r 13 Report Documentation Page Form Approved OMB No. 0704-0188 Public reporting burden for the collection of information is estimated to average 1 hour per response, including the  ...  Individual thanks go to Ralph Grishman of NYU for serving as program cochair, to Nancy Chinchor for her critical efforts on virtually all aspects of MUC-6, and to the other members o f the program committee  ... 
doi:10.3115/1119018.1119073 dblp:conf/tipster/Sundheim96a fatcat:nsjd2fx5s5di7epbsivm5ktivy

Overview of results of the MUC-6 evaluation

Beth M. Sundheim
1995 Proceedings of the 6th conference on Message understanding - MUC6 '95  
The inclusion of four different tasks in the evaluation implicitly encouraged sites to design general-purpos e architectures that allow the production of a variety of types of output from a single internal  ...  representation in orde r 13 Report Documentation Page Form Approved OMB No. 0704-0188 Public reporting burden for the collection of information is estimated to average 1 hour per response, including the  ...  Individual thanks go to Ralph Grishman of NYU for serving as program cochair, to Nancy Chinchor for her critical efforts on virtually all aspects of MUC-6, and to the other members o f the program committee  ... 
doi:10.3115/1072399.1072402 dblp:conf/muc/Sundheim95 fatcat:tzz5adc6enbzdmsov3yoalsw5i

Information extraction: beyond document retrieval

Robert Gaizauskas, Yorick Wilks
1998 Journal of Documentation  
Here we describe the nature of the IE task, review the history of the area from its origins in AI work in the 1960's and 70's till the present, discuss the techniques being used to carry out the task,  ...  In this paper we give a synoptic view of the growth text processing technology of information extraction (IE) whose function is to extract information about a pre-specified set of entities, relations or  ...  Acknowledgments Thanks to Beth Sundheim of the US Naval Command, Control, and Ocean Surveillance Center RDT\&E Division (NRaD) for detailed comments during the preparation of this paper.  ... 
doi:10.1108/eum0000000007162 fatcat:diexgodbeng4lh6kfrn4kylrfm
« Previous Showing results 1 — 15 out of 713 results