Filters








14,976 Hits in 6.9 sec

Extracting Phrases in Vietnamese Document for Summary Generation

Huong Thanh Le, Rathany Chan Sam, Phuc Trong Nguyen
<span title="">2010</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/h22hc7srljgfxlfd7najzrblui" style="color: black;">2010 International Conference on Asian Language Processing</a> </i> &nbsp;
Based on characteristics of Vietnamese, we propose rules for segmenting text into elementary discourse units (edus) and for recognizing discourse relations between textual spans.  ...  This paper describes an approach to Vietnamese text summarization, concentrated on the discourse structure of the text.  ...  ACKNOWLEDGMENT This paper is completed under the sponsor of Vietnam's National Foundation for Science and Technology Development (NAFOSTED).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ialp.2010.8">doi:10.1109/ialp.2010.8</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ialp/LeSN10.html">dblp:conf/ialp/LeSN10</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rzb5cxgolza3lisj6wfeouanya">fatcat:rzb5cxgolza3lisj6wfeouanya</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150406004111/http://phucng.com/pubs/ialp2010.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/a5/b8/a5b80d149c19c5a2fd476de7078d6a8780a958e3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/ialp.2010.8"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Summarizing Short Texts Through a Discourse-Centered Approach in a Multilingual Context [chapter]

Daniel Alexandru Anechitei, Dan Cristea, Ioannidis Dimosthenis, Eugen Ignat, Diman Karagiozov, Svetla Koeva, Mateusz Kopeć, Cristina Vertan
<span title="">2013</span> <i title="Springer New York"> Where Humans Meet Machines </i> &nbsp;
At the core of a summary, which is comprised of clauses and sentences extracted from the original text, is the structure of the discourse and its relationship with its coreferential links.  ...  The approach shows a uniform design for all languages, while language specificity is attributed to the resources that fuel the component modules.  ...  Her method also uses rules to correct some boundaries. clause segmentation evaluation results (achieved by comparing the number of boundaries) for each of the languages under experiment 17 .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-1-4614-6934-6_6">doi:10.1007/978-1-4614-6934-6_6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ezkjjnwwr5fz3gxmpw7t7hfgum">fatcat:ezkjjnwwr5fz3gxmpw7t7hfgum</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170706040835/https://profs.info.uaic.ro/~dcristea/papers/WHMM--Neustein%20and%20Markowitz---CHAP%20SIX-AnechiteiEtAl.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/10/02/1002a5e472e845e198d105c99337eeb82c051b4d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-1-4614-6934-6_6"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Leveraging DistilBERT for Summarizing Arabic Text: An Extractive Dual-stage Approach

Abdullah Alshanqiti, Abdallah Namoun, Aeshah Alsughayyir, Aisha AlMashreqi, Abdul Rehman Gilal, Sami Albouq
<span title="">2021</span> <i title="Institute of Electrical and Electronics Engineers (IEEE)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q7qi7j4ckfac7ehf3mjbso4hne" style="color: black;">IEEE Access</a> </i> &nbsp;
Thus, we present an extractivebased summarizer (ArDBertSum) for text written in Arabic, relying on the DistilBERT model.  ...  The results of our experiments illustrate that our ArDBertSum yields the best performance, compared with non-heuristic Arabic summarizers, in producing an acceptable quality of candidate summaries.  ...  This unavailable and such needed feature has prompted us to con- tribute with a particular sentence clause-based segmenter for the Arabic texts (SCSAR), discussed in the next subsection.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3113256">doi:10.1109/access.2021.3113256</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/iinutizwkna5jns2w2wgoxhelq">fatcat:iinutizwkna5jns2w2wgoxhelq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210924182152/https://ieeexplore.ieee.org/ielx7/6287639/6514899/09539169.pdf?tp=&amp;arnumber=9539169&amp;isnumber=6514899&amp;ref=" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/13/24/13247854f9ce679194b87677e11a714eca0d6950.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2021.3113256"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> ieee.com </button> </a>

Improving the comprehension of legal documentation

Nadjet Bouayad-Agha, Gerard Casamayor, Gabriela Ferraro, Simon Mille, Vanesa Vidal, Leo Wanner
<span title="">2009</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hmo6e27pevb7vobfdg5lxi5jwy" style="color: black;">Proceedings of the 12th International Conference on Artificial Intelligence and Law - ICAIL &#39;09</a> </i> &nbsp;
The deep strategies operate on deep-syntactic structures of the claims, using a full fledged text generator for synthesis of the paraphrase or summary, respectively.  ...  With the goal to offer the user the most suitable options and to evaluate alternative techniques that are based on different contextual and linguistic criteria, both paraphrasing and summarization implement  ...  We experimented with both rule-based and machine learning segmentation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1568234.1568244">doi:10.1145/1568234.1568244</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icail/Bouayad-AghaCFMVW09.html">dblp:conf/icail/Bouayad-AghaCFMVW09</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/74hhcv4wh5dbze2ymzphizppry">fatcat:74hhcv4wh5dbze2ymzphizppry</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170308181617/http://users.cecs.anu.edu.au/~gferraro/ICAIL-2009.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/fc/ad/fcad89e587048a3dfe5deecfc4b0f9fa5aa581ec.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/1568234.1568244"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Extracting sentence segments for text summarization

Wesley T. Chuang, Jihoon Yang
<span title="">2000</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ibcfmixrofb3piydwg5wvir3t4" style="color: black;">Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval - SIGIR &#39;00</a> </i> &nbsp;
With the proliferation of the Internet and the huge amount of data it transfers, text summarization is becoming more important.  ...  Results of experiments on U.S. patents indicate that the performance of the proposed approach compares very favorably with other approaches (including Microsoft Word summarizer) in terms of precision,  ...  The cue phrase used here is because which connects the two segments (i.e. main and subordinate clauses) with a cause relationship.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/345508.345566">doi:10.1145/345508.345566</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/sigir/ChuangY00.html">dblp:conf/sigir/ChuangY00</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jmnmikuj5zfffefshxpxduzfti">fatcat:jmnmikuj5zfffefshxpxduzfti</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150618200000/http://wtlab.um.ac.ir/images/e-library/text_summarization/Extracting%20Sentence%20Segments%20for%20Text%20summarization.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d2/bc/d2bcd9e62ef8fa4eb937f987ca23aec46545fb1e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/345508.345566"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Coherence in Natural Language: Data Stuctures and Applications Florian Wolf and Edward Gibson (Massachusetts Institute of Technology) The MIT Press, 2006, vii+137 pp; hardbound, ISBN 0-262-23251-0, $36.00

Alistair Knott
<span title="">2007</span> <i title="MIT Press - Journals"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/e4yflo6sufcufjwloald7xudm4" style="color: black;">Computational Linguistics</a> </i> &nbsp;
Wolf and Gibson develop a number of algorithms for text summarization that use their graph-based text structures.  ...  In the first part of Chapter 2, Wolf and Gibson describe their model of text structure in detail, and give an admirably detailed pro- tocol for manual analysis of texts, with copious examples.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/coli.2007.33.4.591">doi:10.1162/coli.2007.33.4.591</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ln3g2gydnnbljfkivypi6iu5de">fatcat:ln3g2gydnnbljfkivypi6iu5de</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/details/sim_computational-linguistics_2007-12_33_4/page/591" title="read fulltext microfilm" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Archive [Microfilm] <div class="menu fulltext-thumbnail"> <img src="https://archive.org/serve/sim_computational-linguistics_2007-12_33_4/__ia_thumb.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1162/coli.2007.33.4.591"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mitpressjournals.org </button> </a>

Improving Dependency Parsing Using Sentence Clause Charts

Vincent Kríž, Barbora Hladka
<span title="">2016</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the ACL 2016 Student Research Workshop</a> </i> &nbsp;
This method assumes segmentation of input sentences into clauses and does not require to re-train a parser of one's choice.  ...  We represent a sentence clause structure using clause charts that provide a layer of embedding for each clause in the sentence.  ...  We thank three anonymous reviewers for their useful comments and remarks and we truly appreciate suggestions provided by Kemal Oflazer.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p16-3013">doi:10.18653/v1/p16-3013</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/KrizH16.html">dblp:conf/acl/KrizH16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7jf2gg3lsrawni5cjskled6b5e">fatcat:7jf2gg3lsrawni5cjskled6b5e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190223044902/http://pdfs.semanticscholar.org/49a3/4ffb816997c8d8d20225e293004f7d643d81.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/49/a3/49a34ffb816997c8d8d20225e293004f7d643d81.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p16-3013"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Fact-level Extractive Summarization with Hierarchical Graph Mask on BERT [article]

Ruifeng Yuan, Zili Wang, Wenjie Li
<span title="2020-11-19">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose to extract fact-level semantic units for better extractive summarization.  ...  However, one of the problems with sentence-level extractive summarization is that there exists a gap between the human-written gold summary and the oracle sentence labels.  ...  For example, in Figure 2 , we first assign the [cls d] segment embedding E A and then for the next granularity level, sentence, we allocate all [cls s] with E B .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.09739v1">arXiv:2011.09739v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dzokulnc7fdsfofip4voh57ojy">fatcat:dzokulnc7fdsfofip4voh57ojy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201121022416/https://arxiv.org/pdf/2011.09739v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0a/7b/0a7bb1bb50849016f654d857109bcfadae9cf4cf.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.09739v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Information Extraction Using Discourse Analysis from Newswires

Ashwini Rahangdale, Agrawal A.J
<span title="2014-06-30">2014</span> <i title="Academy and Industry Research Collaboration Center (AIRCC)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/pmw4omis5ngs5pwn6tj4p2cczm" style="color: black;">International Journal of Advanced Information Technology</a> </i> &nbsp;
RST theory used the Nucleus-Satellite concept for finding most prominent text from the text document.  ...  The Discourse analysis used the Rhetorical Structure theory which is used to find coherent group of text which are most prominent for extracting information from text.  ...  One of the approaches to deal with linguistic is discourse analysis. Discourse analysis used for text based application like information extraction, dialogue generation, and summarization.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5121/ijitcs.2014.4302">doi:10.5121/ijitcs.2014.4302</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mopfl2ry7rfqblnlunzat3dgze">fatcat:mopfl2ry7rfqblnlunzat3dgze</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180604080613/http://www.airccse.org/journal/ijitcs/papers/4314ijitcs02.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/0f/82/0f82b95af87e31c90e91754afa18caeee070c739.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5121/ijitcs.2014.4302"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> Publisher / doi.org </button> </a>

Linking discourse modes and situation entity types in a cross-linguistic corpus study

Kleio-Isidora Mavridou, Annemarie Friedrich, Melissa Peate Sørensen, Alexis Palmer, Manfred Pinkal
<span title="">2015</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u3ideoxy4fghvbsstiknuweth4" style="color: black;">Proceedings of the First Workshop on Linking Computational Models of Lexical, Sentential and Discourse-level Semantics</a> </i> &nbsp;
evoked by clauses of text, and discourse modes (DMs), a characterization of passages at the sub-document level.  ...  We adapt an existing annotation scheme for SEs in English to be used for German data, with a detailed discussion of the most important differences.  ...  We also thank Alessandra Zarcone for invaluable help with experimental design, and the anonymous reviewers for their feedback.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w15-2702">doi:10.18653/v1/w15-2702</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/emnlp/MavridouFSPP15.html">dblp:conf/emnlp/MavridouFSPP15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qj7ecedhpfaipnw54gqxpt5fva">fatcat:qj7ecedhpfaipnw54gqxpt5fva</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180608134542/http://aclweb.org/anthology/W15-2702" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/15/fa/15fa4c7a2e83f89aa98bf4fe29227d9a3dc0efd5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w15-2702"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Sentence Compression in Spanish driven by Discourse Segmentation and Language Models [article]

Alejandro Molina, Juan-Manuel Torres-Moreno, Iria da Cunha, Eric SanJuan, Gerardo Sierra
<span title="2012-12-17">2012</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Previous works demonstrated that Automatic Text Summarization (ATS) by sentences extraction may be improved using sentence compression.  ...  The results presented here show that the proposed solution is able to generate coherent summaries with grammatical compressed sentences.  ...  Introduction Automatic Text Summarization (ATS) is indispensable to cope with ever increasing volumes of valuable information.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1212.3493v2">arXiv:1212.3493v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k5zy2ehizjek7i3uzcafmggcnm">fatcat:k5zy2ehizjek7i3uzcafmggcnm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200908084431/https://arxiv.org/pdf/1212.3493v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/00/76/00765732ed56399e4db39d620f6708e403f8af1f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1212.3493v2" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Learning Features that Predict Cue Usage [article]

Barbara Di Eugenio, Johanna D. Moore
<span title="1997-10-22">1997</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our experiments enable us to identify the features with most predictive power, and show that machine learning can be used to induce decision trees useful for text generation.  ...  Previous attempts to devise rules for text generation were based on intuition or small numbers of constructed examples.  ...  Thanks to Megan Moser for her prior work on this project and for comments on this paper; to Erin Glendening and Liina Pylkkänen for their coding efforts; to Haiqin Wang for running many experiments; to  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/cmp-lg/9710006v1">arXiv:cmp-lg/9710006v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/27k7ltkdh5f55ijuvl2qkbb4v4">fatcat:27k7ltkdh5f55ijuvl2qkbb4v4</a> </span>
<a target="_blank" rel="noopener" href="https://archive.org/download/arxiv-cmp-lg9710006/cmp-lg9710006.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> File Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/c5/b2/c5b2e949e7ad88c7d2922b8e5c5f016e178db493.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/cmp-lg/9710006v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Supporting content evaluation of student summaries by Idea Unit embedding

Marcello Gecchele, Hiroaki Yamada, Takenobu Tokunaga, Yasuyo Sawaki
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/nl6giaap3jbj7g4lipzi4jvbbq" style="color: black;">Proceedings of the Fourteenth Workshop on Innovative Use of NLP for Building Educational Applications</a> </i> &nbsp;
An evaluation experiment with two source texts and 20 summaries showed that the proposed method is more robust against rephrased expressions than the conventional ROUGEbased baselines.  ...  We propose a method to make a correspondence between the segments of the source text and its summary. As a unit of the segment, we adopt "Idea Unit (IU)" which is proposed in Applied Linguistics.  ...  The experiment with 20 summaries for two source texts confirmed that our proposed method is more robust against rephrasing than the ROUGE-based baselines.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w19-4436">doi:10.18653/v1/w19-4436</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/bea/GeccheleYTS19.html">dblp:conf/bea/GeccheleYTS19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2xibym2z3jczzp7onrdcrmrc2i">fatcat:2xibym2z3jczzp7onrdcrmrc2i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200505162745/https://www.aclweb.org/anthology/W19-4436.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/ac/1f/ac1f6e185fd5d349a5cc89199c822d2201a4092b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w19-4436"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Experiment Segmentation in Scientific Discourse as Clause-level Structured Prediction using Recurrent Neural Networks [article]

Pradeep Dasigi, Gully A.P.C. Burns, Eduard Hovy, Anita de Waard
<span title="2017-02-17">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a deep learning model for identifying structure within experiment narratives in scientific literature.  ...  Our model is a Recurrent Neural Network (RNN) with Long Short-Term Memory (LSTM) cells that labels clauses.  ...  The next step is to summarize the clause representations to obtain D summ ∈ R c×d , a matrix corresponding to the entire paragraph, with one vector per clause.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1702.05398v1">arXiv:1702.05398v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7hgg2zc7nvh7vl6qusk35jdzzm">fatcat:7hgg2zc7nvh7vl6qusk35jdzzm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200828130802/https://arxiv.org/pdf/1702.05398v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/32/94/32944621816d2b70d80c573f2397848a722e0651.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1702.05398v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Constructing Topic Person Interaction Networks Using a Tree Kernel-Based Method

Yung-Chun Chang, Zhong-Yong Chen, Chien-Chin Chen, Wen-Lian Hsu
<span title="">2015</span> <i title="EJournal Publishing"> International Journal of Languages, Literature and Linguistics </i> &nbsp;
We proposed a rich interactive tree structure to represent syntactic, content, and semantic information in the text for extracting person interactions.  ...  for comparison.  ...  ACKNOWLEDGMENT We are grateful to the anonymous reviewers for insightful comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18178/ijlll.2015.1.4.46">doi:10.18178/ijlll.2015.1.4.46</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2ag5tbvxirfsffu4jzvxsxfh5a">fatcat:2ag5tbvxirfsffu4jzvxsxfh5a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190430221109/http://www.ijlll.org/vol1/46-CL00016.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e9/a6/e9a646b2612686f487498d9f174c236b6f8acdf9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18178/ijlll.2015.1.4.46"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 14,976 results