Filters








136,957 Hits in 6.4 sec

Using Argumentation to Improve Classification in Natural Language Problems

Lucas Carstens, Francesca Toni
<span title="2017-07-12">2017</span> <i title="Association for Computing Machinery (ACM)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/3pxayimhcfdzhf6admua73ekfe" style="color: black;">ACM Transactions on Internet Technology</a> </i> &nbsp;
For both tasks we improve classification performance when using our methodology, compared to using standard classifiers, only. 3  ...  To do so we identify arguments that formalise prototypical knowledge of a problem and use them to correct misclassifications.  ...  to 6 : 6 Lucas Carstens & Francesca Toni -Using Argumentation to improve classification in Natural Language problems (under review for ASM ACM TOIT 2017 : Argumentation in Social This paper describes part  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3017679">doi:10.1145/3017679</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dt5n5efxkfcvlkdbxnmnngs5g4">fatcat:dt5n5efxkfcvlkdbxnmnngs5g4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180722092458/http://spiral.imperial.ac.uk/bitstream/10044/1/34929/5/Carstens-L-2016-PhD-Thesis.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/be/0d/be0d424ce6d5d76befaa8fc8193aa4575d10b48d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3017679"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

Automatic Question Generation Using Semantic Role Labeling for Morphologically Rich Languages

<span title="2021-06-05">2021</span> <i title="Mechanical Engineering Faculty in Slavonski Brod"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/t73uxenjnncj3pwpreqsfuzkyi" style="color: black;">Tehnički Vjesnik</a> </i> &nbsp;
In the first stage we present a novel approach to SRL of texts written in Croatian language that uses Conditional Random Fields (CRF).  ...  In the second stage the proposed SRL model is used to develop AQG system for question generation from texts written in Croatian language.  ...  The system uses various natural language processing techniques to enable the learner to communicate in natural language.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.17559/tv-20200402175619">doi:10.17559/tv-20200402175619</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7lf37m66fne6dnw5mlrasr7dsu">fatcat:7lf37m66fne6dnw5mlrasr7dsu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210615133138/https://hrcak.srce.hr/file/375247" 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/07/90/07903e749599bcab2ddc55284f3948ab0360c81f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.17559/tv-20200402175619"> <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>

Explaining Arguments with Background Knowledge

Maria Becker, Ioana Hulpuş, Juri Opitz, Debjit Paul, Jonathan Kobbe, Heiner Stuckenschmidt, Anette Frank
<span title="2020-07-06">2020</span> <i title="Springer Science and Business Media LLC"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2md4vy5wrff7tl4i7hse65hita" style="color: black;">Datenbank-Spektrum</a> </i> &nbsp;
We introduce the problems and challenges we need to address, and present the progress we achieved until now by applying advanced natural language and knowledge processing methods.  ...  This requires human background knowledge and reasoning capacity, in order to explicate the complete reasoning of an argument.  ...  While many natural language processing (NLP) tasks can be solved with surprising accuracy using surface features, arguments are often rhetorically framed, and thus many approaches to computational argumentation  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s13222-020-00348-6">doi:10.1007/s13222-020-00348-6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zd55bxjr7bhs5ab5whi3ih4q4y">fatcat:zd55bxjr7bhs5ab5whi3ih4q4y</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108174008/https://link.springer.com/content/pdf/10.1007/s13222-020-00348-6.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/cd/2b/cd2b4da009cd463664a98334ba1649c5695287df.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s13222-020-00348-6"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> springer.com </button> </a>

Event Arguments Extraction via Dilate Gated Convolutional Neural Network with Enhanced Local Features [article]

Zhigang Kan, Linbo Qiao, Sen Yang, Feng Liu, Feng Huang
<span title="2020-06-02">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In pipelined structures, the difficulty of event arguments extraction lies in its lack of classification feature, and the much higher computation consumption.  ...  Further analysis of extraction procedure is presented, as well as experiments are conducted to analyze impact factors related to the performance improvement.  ...  FINE-TUNING VIA BIDIRECTIONAL TRANSFORMER Generally speaking, there are three classes of neural networks applied to solve problems in natural language processing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.01854v1">arXiv:2006.01854v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/n42kpogubndmllbi6iv5y6rgxy">fatcat:n42kpogubndmllbi6iv5y6rgxy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200901191259/https://arxiv.org/pdf/2006.01854v1.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/69/11/691115ded9a4b67cbb970381bd367dd668931375.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.01854v1" 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>

Event Arguments Extraction via Dilate Gated Convolutional Neural Network with Enhanced Local Features

Zhigang Kan, Linbo Qiao, Sen Yang, Feng Liu, Feng Huang
<span title="">2020</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;
In pipelined structures, the difficulty of event arguments extraction lies in its lack of classification feature, and the much higher computation consumption.  ...  Further analysis of extraction procedure is presented, as well as experiments are conducted to analyze impact factors related to the performance improvement.  ...  FINE-TUNING VIA BIDIRECTIONAL TRANSFORMER Generally speaking, there are three classes of neural networks applied to solve problems in natural language processing.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3004378">doi:10.1109/access.2020.3004378</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/d2dyorwlebbvhpibtq7hqey5lq">fatcat:d2dyorwlebbvhpibtq7hqey5lq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210429183259/https://ieeexplore.ieee.org/ielx7/6287639/8948470/09123341.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/c0/e0/c0e0299568407b1cc40cbd38305f570e5ca79a30.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.3004378"> <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>

Korean Semantic Role Labeling with Bidirectional Encoder Representations from Transformers and Simple Semantic Information

Jangseong Bae, Changki Lee
<span title="2022-06-13">2022</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/smrngspzhzce7dy6ofycrfxbim" style="color: black;">Applied Sciences</a> </i> &nbsp;
To obtain the latter, we used PropBank, which described the relational information between predicates and arguments.  ...  In recent years, breakthroughs achieved using end-to-end neural network models have resulted in a state-of-the-art SRL performance even without syntactic features.  ...  Recently, the natural language processing (NLP) community has shown interest in neural models that heavily use pre-training based on language modeling [16] [17] [18] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app12125995">doi:10.3390/app12125995</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nsi2mngt5nacrekyky6bg3lrua">fatcat:nsi2mngt5nacrekyky6bg3lrua</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220615152824/https://mdpi-res.com/d_attachment/applsci/applsci-12-05995/article_deploy/applsci-12-05995.pdf?version=1655105519" 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/39/9c/399c94c4a6c9394e04b68c6434301f81c489ea06.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/app12125995"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations [article]

Qian Li, Hao Peng, Jianxin Li, Jia Wu, Yuanxing Ning, Lihong Wang, Philip S. Yu, Zheng Wang
<span title="2021-12-22">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
It then uses the newly obtained information to improve the decisions of previously extracted arguments.  ...  Event extraction is a fundamental task for natural language processing. Finding the roles of event arguments like event participants is essential for event extraction.  ...  In the future, we plan to improve types.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.12384v2">arXiv:2106.12384v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/blyylym77vdupbrolil2dtmrna">fatcat:blyylym77vdupbrolil2dtmrna</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211229230306/https://arxiv.org/pdf/2106.12384v2.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/66/b7/66b76bd54f35d314b6eb359d06afddfcb83712d6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.12384v2" 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>

Cross-Lingual Argumentative Relation Identification: from English to Portuguese

Gil Rocha, Christian Stab, Henrique Lopes Cardoso, Iryna Gurevych
<span title="">2018</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/q26wled75jfangocpbylu6no7q" style="color: black;">Proceedings of the 5th Workshop on Argument Mining</a> </i> &nbsp;
To overcome the lack of annotated resources in less-resourced languages, we present the first attempt to address this subtask in a cross-lingual setting.  ...  In this paper, we aim to address the task of argumentative relation identification, a subtask of argument mining, for which several approaches have been recently proposed in a monolingual setting.  ...  Aiming to improve the results for the "support" label (minority class), we explore two widely used techniques to deal with unbalanced datasets in ML problems (He and Garcia, 2009) : random undersampling  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w18-5217">doi:10.18653/v1/w18-5217</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/argmining/RochaSCG18.html">dblp:conf/argmining/RochaSCG18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/a7zsp2dptrgn5m47ykhx7svwse">fatcat:a7zsp2dptrgn5m47ykhx7svwse</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190322171748/http://aclweb.org/anthology/W18-5217" 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/f4/80/f4807ef95df79b550ab1a0d98f15f31d0345cfe7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w18-5217"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Using Context to Predict the Purpose of Argumentative Writing Revisions

Fan Zhang, Diane Litman
<span title="">2016</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/d5ex6ucxtrfz3clshlkh3f6w2q" style="color: black;">Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</a> </i> &nbsp;
transforming the classification problem to a sequence labeling task.  ...  We propose two approaches for utilizing contextual information when predicting argumentative revision purposes: developing contextual features for use in the classification paradigm of prior work, and  ...  Acknowledgments We would like to thank our annotators, especially Jiaoyang Li, who contributed significantly to the building of our corpus.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n16-1168">doi:10.18653/v1/n16-1168</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/naacl/ZhangL16.html">dblp:conf/naacl/ZhangL16</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cijduyi4nzcnxnntqbozqduehi">fatcat:cijduyi4nzcnxnntqbozqduehi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200307110232/https://www.aclweb.org/anthology/N16-1168.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/df/8f/df8f000a04ca074dafa8aec0eb6925dfbd9c7847.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n16-1168"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

An enhanced data mining model for text classification

K. Nithya, P C D. Kalaivaani, R. Thangarajan
<span title="">2012</span> <i title="IEEE"> 2012 International Conference on Computing, Communication and Applications </i> &nbsp;
Text classification is a supervised technique that uses labeled training data to learn the classification system and then automatically classifies the remaining text using the learned system.  ...  Classification plays a vital role in many information management and retrieval tasks. This paper studies classification of text document.  ...  INTRODUCTION Natural language processing (NLP) is a field of computer science and linguistics concerned with the interactions between computers and natural languages.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccca.2012.6179179">doi:10.1109/iccca.2012.6179179</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ec7yaoqxafdjdg6xnmh2fmmd7i">fatcat:ec7yaoqxafdjdg6xnmh2fmmd7i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20140411094030/http://ceng.gazi.edu.tr:80/~ozdemir/teaching/dm/R2.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/fd/0afd805e0b6e37e4f27585b33d0a4896ba79383e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccca.2012.6179179"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Bilingual Event Extraction: a Case Study on Trigger Type Determination

Zhu Zhu, Shoushan Li, Guodong Zhou, Rui Xia
<span title="">2014</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)</a> </i> &nbsp;
Event extraction generally suffers from the data sparseness problem. In this paper, we address this problem by utilizing the labeled data from two different languages.  ...  To make the training data in different languages help each other, we propose a uniform text representation with bilingual features to represent the samples and handle the difficulty of locating the triggers  ...  Empirical studies show that our approach is effective in using bilingual corpus to improve monolingual classification in trigger type determination.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3115/v1/p14-2136">doi:10.3115/v1/p14-2136</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/ZhuLZX14.html">dblp:conf/acl/ZhuLZX14</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nnoi5wvdezhyfhbkwpbkoaq72a">fatcat:nnoi5wvdezhyfhbkwpbkoaq72a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170808144253/http://aclweb.org/anthology/P/P14/P14-2136.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/72/9d/729d09e850b0045a13cb5279d387190b0ec5ad0b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3115/v1/p14-2136"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Vietnamese Semantic Role Labelling

Phuong Le Hong, Hoang Thai Pham, Khoai Xuan Pham, Huyen Thi Minh Nguyen, Luong Thi Nguyen, Hiep Minh Nguyen
<span title="2017-11-21">2017</span> <i title="Vietnam National University Journal of Science"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/r7c5oq2wezc73n7i6xyr3jeloi" style="color: black;">VNU Journal of Science Computer Science and Communication Engineering</a> </i> &nbsp;
programming inference procedure to improve the accuracy.  ...  In this paper, we study semantic role labelling (SRL), a subtask of semantic parsing of natural language sentences and its application for the Vietnamese language.  ...  In order to improve the accuracy of the classification step, and hence of our SRL system as a whole, we have integrated many useful features for use in two statistical classification models, namely Maximum  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.25073/2588-1086/vnucsce.166">doi:10.25073/2588-1086/vnucsce.166</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hsexh47rdvbizjjsk7sa5zebc4">fatcat:hsexh47rdvbizjjsk7sa5zebc4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190430094134/http://jcsce.vnu.edu.vn/index.php/jcsce/article/download/166/77" 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/fd/41/fd411a151b5f15b5d2c14aa517ee202eeccf9f33.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.25073/2588-1086/vnucsce.166"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

The DCU Discourse Parser for Connective, Argument Identification and Explicit Sense Classification

Longyue Wang, Chris Hokamp, Tsuyoshi Okita, Xiaojun Zhang, Qun Liu
<span title="">2015</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/ot5sbt27tzdyrhcooo2wxlw7ki" style="color: black;">Proceedings of the Nineteenth Conference on Computational Natural Language Learning - Shared Task</a> </i> &nbsp;
This paper describes our submission to the CoNLL-2015 shared task on discourse parsing. We factor the pipeline into subcomponents which are then used to form the final sequential architecture.  ...  extraction, and sense classification.  ...  Position Classification of applying deep neural network technologies in natural language processing, we carried out an in- vestigation of the use of recurrent neural network (RNN) for this difficult  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/k15-2014">doi:10.18653/v1/k15-2014</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/conll/WangH0ZL15.html">dblp:conf/conll/WangH0ZL15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qcr3udwkwveodpsbfakcu2e7hi">fatcat:qcr3udwkwveodpsbfakcu2e7hi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180610200427/http://aclweb.org/anthology/K15-2014" 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/72/86/7286080e140c7f0c5cef091c837a94bc2eb2f4b0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/k15-2014"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Building a Semantic Role Labelling System for Vietnamese [article]

Thai-Hoang Pham, Xuan-Khoai Pham, Phuong Le-Hong
<span title="2017-05-11">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Finally, in the classification step, in addition to the common linguistic features, we propose novel and useful features for use in SRL.  ...  Semantic role labelling (SRL) is a task in natural language processing which detects and classifies the semantic arguments associated with the predicates of a sentence.  ...  We would also like to thank the FPT Technology Research Institute for providing us the corpora for use in the experiments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.04038v1">arXiv:1705.04038v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/zvgg6fnfffekfd3xlawuraexqu">fatcat:zvgg6fnfffekfd3xlawuraexqu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200831203436/https://arxiv.org/pdf/1705.04038v1.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/2f/7d/2f7d1374c48132a6790f53adc55111b218795158.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.04038v1" 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>

Relational Learning for Spatial Relation Extraction from Natural Language [chapter]

Parisa Kordjamshidi, Paolo Frasconi, Martijn Van Otterlo, Marie-Francine Moens, Luc De Raedt
<span title="">2012</span> <i title="Springer Berlin Heidelberg"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
We formalize it as an information extraction step required for a mapping from natural language to formal spatial representation.  ...  Our contribution is to formulate the extraction task as a relational learning problem, for which we employ the recently introduced kLog framework.  ...  A solution to this problem is to use linguistic resources, which are often available in a logical representation [5] , and which can be exploited naturally in kLog.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-31951-8_20">doi:10.1007/978-3-642-31951-8_20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/soikpibe6rex7b3gl3iaibkchm">fatcat:soikpibe6rex7b3gl3iaibkchm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170815124620/https://lirias.kuleuven.be/bitstream/123456789/337956/1/ILP_CameraReady10.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/74/f4/74f4bd90b16d76747081195e3a40b38f3579eeb5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-642-31951-8_20"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>
&laquo; Previous Showing results 1 &mdash; 15 out of 136,957 results