Filters








2,383 Hits in 4.8 sec

Leveraging Type Descriptions for Zero-shot Named Entity Recognition and Classification

Rami Aly, Andreas Vlachos, Ryan McDonald
<span title="">2021</span> <i title="Association for Computational Linguistics"> Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) </i> &nbsp; <span class="release-stage">unpublished</span>
A common issue in real-world applications of named entity recognition and classification (NERC) is the absence of annotated data for target entity classes during training.  ...  This paper presents the first approach for zero-shot NERC, introducing a novel architecture that leverage the fact that textual descriptions for many entity classes occur naturally.  ...  Acknowledgements We thank the anonymous reviewers for their time and effort giving us feedback on our paper.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2021.acl-long.120">doi:10.18653/v1/2021.acl-long.120</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/5nf5of5lp5bdhekyqsxd2wbfsu">fatcat:5nf5of5lp5bdhekyqsxd2wbfsu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210726023809/https://aclanthology.org/2021.acl-long.120.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/b2/e5/b2e51cc8d742c1ba269b304078e2719fab478dd6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/2021.acl-long.120"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling [article]

Zihan Liu, Genta Indra Winata, Peng Xu, Pascale Fung
<span title="2020-04-24">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Furthermore, our model can also be applied to the cross-domain named entity recognition task, and it achieves better adaptation performance than other existing baselines.  ...  Our model first learns the general pattern of slot entities by detecting whether the tokens are slot entities or not. It then predicts the specific types for the slot entities.  ...  Acknowledgments This work is partially funded by ITF/319/16FP and MRP/055/18 of the Innovation Technology Commission, the Hong Kong SAR Government.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.11727v1">arXiv:2004.11727v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/k2xrxo4hsjcadj7kgqvvw7qv6q">fatcat:k2xrxo4hsjcadj7kgqvvw7qv6q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200511220452/https://arxiv.org/pdf/2004.11727v1.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/89/40/894009cd79adab9d32132ea7ea79c8c028d68d3b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.11727v1" 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 from Language Description: Low-shot Named Entity Recognition via Decomposed Framework [article]

Yaqing Wang, Haoda Chu, Chao Zhang, Jing Gao
<span title="2021-09-11">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this work, we study the problem of named entity recognition (NER) in a low resource scenario, focusing on few-shot and zero-shot settings.  ...  We perform extensive experiments on 5 benchmark datasets and evaluate the proposed method in the few-shot learning, domain transfer and zero-shot learning settings.  ...  Acknowledgment The authors would like to thank the anonymous referees for their valuable comments and helpful suggestions.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.05357v1">arXiv:2109.05357v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hgxymfox5vcvndhxknqs24nkzu">fatcat:hgxymfox5vcvndhxknqs24nkzu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210917193055/https://arxiv.org/pdf/2109.05357v1.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/f8/b4/f8b4cb8d58577115a5f8c30f9653b5971c31b965.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.05357v1" 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 from Miscellaneous Other-Class Words for Few-shot Named Entity Recognition [article]

Meihan Tong, Shuai Wang, Bin Xu, Yixin Cao, Minghui Liu, Lei Hou, Juanzi Li
<span title="2021-06-29">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Few-shot Named Entity Recognition (NER) exploits only a handful of annotations to identify and classify named entity mentions. Prototypical network shows superior performance on few-shot NER.  ...  Experimental results demonstrate that our model outperforms five state-of-the-art models in both 1-shot and 5-shots settings on four NER benchmarks. We will release the code upon acceptance.  ...  This work is supported by National Engineering Laboratory for Cyberlearning and Intelligent Technology, Beijing Key Lab of Networked Multimedia and the Institute for Guo Qiang, Tsinghua University (2019GQB0003  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.15167v1">arXiv:2106.15167v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jl6hkgx6cncelbkcxmhh2dfib4">fatcat:jl6hkgx6cncelbkcxmhh2dfib4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210701130404/https://arxiv.org/pdf/2106.15167v1.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/4a/53/4a534218cde7fd2a2efcc05b6f541b4c34596079.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.15167v1" 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>

Neural Entity Linking: A Survey of Models Based on Deep Learning [article]

Ozge Sevgili, Artem Shelmanov, Mikhail Arkhipov, Alexander Panchenko, Chris Biemann
<span title="2021-08-25">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
techniques including zero-shot and distant supervision methods, and cross-lingual approaches.  ...  The vast variety of modifications of this general neural entity linking architecture are grouped by several common themes: joint entity recognition and linking, models for global linking, domain-independent  ...  The work of Artem Shelmanov in the current study (preparation of sections related to application of entity linking to neural language models, entity ranking, contextmention encoding, and overall harmonization  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.00575v3">arXiv:2006.00575v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ra3kwc4tmbfhlmgtlevkcshcqq">fatcat:ra3kwc4tmbfhlmgtlevkcshcqq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210830072050/https://arxiv.org/pdf/2006.00575v3.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/c2/c9/c2c9262c85bfbe0dfcf6c2431dc9c6bc2da8d07d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.00575v3" 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>

Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification [article]

Juan Li, Ruoxu Wang, Ningyu Zhang, Wen Zhang, Fan Yang, Huajun Chen
<span title="2020-10-30">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a novel logic-guided semantic representation learning model for zero-shot relation classification.  ...  To recognize unseen relations at test time, we explore the problem of zero-shot relation classification.  ...  Acknowledgments We want to express gratitude to the anonymous reviewers for their hard work and kind comments, which will further improve our work in the future.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.16068v1">arXiv:2010.16068v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/32mls4yobvdr5lzyy3wd4o2ojq">fatcat:32mls4yobvdr5lzyy3wd4o2ojq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201103002952/https://arxiv.org/pdf/2010.16068v1.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/af/78/af786e7bc80b21a633f78915bccbf339c2e8b936.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.16068v1" 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>

Neural entity linking: A survey of models based on deep learning

Özge Sevgili, Artem Shelmanov, Mikhail Arkhipov, Alexander Panchenko, Chris Biemann, Mehwish Alam, Davide Buscaldi, Michael Cochez, Francesco Osborne, Diego Reforgiato Recupero, Harald Sack
<span title="2022-03-23">2022</span> <i title="IOS Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/pcapks3huberdozbvfqowysuly" style="color: black;">Semantic Web Journal</a> </i> &nbsp;
including zero-shot and distant supervision methods, and cross-lingual approaches.  ...  This work distills a generic architecture of a neural EL system and discusses its components, such as candidate generation, mention-context encoding, and entity ranking, summarizing prominent methods for  ...  The work of Artem Shelmanov in the current study (preparation of sections related to application of entity linking to neural language models, entity ranking, context-mention encoding, and overall harmonization  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3233/sw-222986">doi:10.3233/sw-222986</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6gwmbtev7ngbliovf6cpf5hyde">fatcat:6gwmbtev7ngbliovf6cpf5hyde</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220421070535/https://content.iospress.com/download/semantic-web/sw222986?id=semantic-web%2Fsw222986" 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] </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3233/sw-222986"> <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>

Attributes2Classname: A discriminative model for attribute-based unsupervised zero-shot learning [article]

Berkan Demirel, Ramazan Gokberk Cinbis, Nazli Ikizler-Cinbis
<span title="2017-08-05">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names.  ...  Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names.  ...  Zero Shot Action Recognition For zero-shot action recognition, we evaluate our approach on UCF-Sports Action Recognition Dataset [30] .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.01734v2">arXiv:1705.01734v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/4ojsapf5pzdhxiou3myyyg7asu">fatcat:4ojsapf5pzdhxiou3myyyg7asu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200908121903/https://arxiv.org/pdf/1705.01734v2.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/2c/d2/2cd2cef4d2eabc954c34eb5b19301ce24e9efa6c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1705.01734v2" 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>

Recent Advances in Zero-shot Recognition [article]

Yanwei Fu, Tao Xiang, Yu-Gang Jiang, Xiangyang Xue, Leonid Sigal, and Shaogang Gong
<span title="2017-10-13">2017</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We also overview related recognition tasks including one-shot and open set recognition which can be used as natural extensions of zero-shot recognition when limited number of class samples become available  ...  or when zero-shot recognition is implemented in a real-world setting.  ...  Yanwei Fu is supported by The Program for Professor of Special Appointment (Eastern Scholar) at Shanghai Institutions of Higher Learning.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1710.04837v1">arXiv:1710.04837v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u3mp6dgj2rgqrarjm4dcywegmy">fatcat:u3mp6dgj2rgqrarjm4dcywegmy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902194609/https://arxiv.org/pdf/1710.04837v1.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/db/9d/db9ddb2c730d75ab741544654c7c227831ed1243.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1710.04837v1" 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>

Zero-Shot Open Information Extraction using Question Generation and Reading Comprehension [article]

Himanshu Gupta, Amogh Badugu, Tamanna Agrawal, Himanshu Sharad Bhatt
<span title="2021-09-16">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper presents a zero-shot open information extraction technique that extracts the entities (value) and their descriptions (key) from a sentence, using off the shelf machine reading comprehension  ...  The dataset consists of paragraphs, tagged values (entities), and their keys (descriptions) and is one of the largest among entity extraction datasets.  ...  For entity extraction, this paper leverages 'ner-ontonotes-fast' by Flair 2 , which is an 18-class named entity recognition model.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.08079v1">arXiv:2109.08079v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nu47mgsep5eijn6asr5uwu3wlq">fatcat:nu47mgsep5eijn6asr5uwu3wlq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210921104329/https://arxiv.org/pdf/2109.08079v1.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/51/0c/510c0ef3b85d9befc1f435e07be2dfa06b486e60.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.08079v1" 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>

OAG-BERT: Pre-train Heterogeneous Entity-augmented Academic Language Models [article]

Xiao Liu, Da Yin, Xingjian Zhang, Kai Su, Kan Wu, Hongxia Yang, Jie Tang
<span title="2021-03-23">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
For zero-shot inference, we design a special decoding strategy to allow OAG-BERT to generate entity names from scratch.  ...  We evaluate the OAG-BERT on various downstream academic tasks, including NLP benchmarks, zero-shot entity inference, heterogeneous graph link prediction, and author name disambiguation.  ...  Hit@1 is reported for zero-shot inference and supervised classification. 3 NA is short for Name disambiguation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.02410v2">arXiv:2103.02410v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ba6za5nfnjawvovsl6bdvcdwoi">fatcat:ba6za5nfnjawvovsl6bdvcdwoi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210328033635/https://arxiv.org/pdf/2103.02410v2.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/e9/fce9158de65c5877d40d2f22448e26993b4af6a5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.02410v2" 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>

Robust Zero-Shot Cross-Domain Slot Filling with Example Values

Darsh Shah, Raghav Gupta, Amir Fayazi, Dilek Hakkani-Tur
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</a> </i> &nbsp;
Prior zero-shot slot filling models use slot descriptions to learn concepts, but are not robust to misaligned schemas.  ...  Often, however, little to no target domain training data may be available, or the training and target domain schemas may be misaligned, as is common for web forms on similar websites.  ...  We would also like to thank the Deep Dialogue team at Google Research for their support.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p19-1547">doi:10.18653/v1/p19-1547</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/ShahGFH19.html">dblp:conf/acl/ShahGFH19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qrdmwn45srbdneyourkyaa5nje">fatcat:qrdmwn45srbdneyourkyaa5nje</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200509001110/https://www.aclweb.org/anthology/P19-1547.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/7e/b9/7eb9c6c45244653f902b45744c866734e1cd4bf7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/p19-1547"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Event Extraction by Answering (Almost) Natural Questions [article]

Xinya Du, Claire Cardie
<span title="2021-02-04">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Empirical results demonstrate that our framework outperforms prior methods substantially; in addition, it is capable of extracting event arguments for roles not seen at training time (zero-shot learning  ...  Existing work in event argument extraction typically relies heavily on entity recognition as a preprocessing/concurrent step, causing the well-known problem of error propagation.  ...  Acknowledgments We thank the anonymous reviewers and Heng Ji for helpful suggestions. This research is based on work supported in part by DARPA LwLL Grant FA8750-19-2-0039.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.13625v2">arXiv:2004.13625v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ezpzuaoribb7tjpv44fylhjbvm">fatcat:ezpzuaoribb7tjpv44fylhjbvm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210209072257/https://arxiv.org/pdf/2004.13625v2.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/4e/0f4eb7134e91c04a48c59962da930c3e89762ee4.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2004.13625v2" 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>

Zero-resource Multi-dialectal Arabic Natural Language Understanding

Muhammad Khalifa, Hesham Hassan, Aly Fahmy
<span title="">2021</span> <i title="The Science and Information Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2yzw5hsmlfa6bkafwsibbudu64" style="color: black;">International Journal of Advanced Computer Science and Applications</a> </i> &nbsp;
To remedy such performance drop, we propose self-training with unlabeled DA data and apply it in the context of named entity recognition (NER), part-of-speech (POS) tagging, and sarcasm detection (SRD)  ...  Our work opens up opportunities for leveraging the relatively abundant labeled MSA datasets to develop DA models for zero and low-resource dialects.  ...  TASKS Named Entity Recognition (NER) is defined as the information extraction task that attempts to locate, extract, and automatically classify named entities into predefined classes or types in unstructured  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14569/ijacsa.2021.0120369">doi:10.14569/ijacsa.2021.0120369</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/kw57zdjmmbcjzg42gaa2372bnu">fatcat:kw57zdjmmbcjzg42gaa2372bnu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210403055156/https://thesai.org/Downloads/Volume12No3/Paper_69-Zero_resource_Multi_dialectal_Arabic_Natural_Language.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/ea/d5/ead5076b02ca1358d780b901c86c69dfe751653e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.14569/ijacsa.2021.0120369"> <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>

RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction [article]

Yew Ken Chia, Lidong Bing, Soujanya Poria, Luo Si
<span title="2022-03-17">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Experiments on FewRel and Wiki-ZSL datasets show the efficacy of RelationPrompt for the ZeroRTE task and zero-shot relation classification.  ...  Given an input sentence, each extracted triplet consists of the head entity, relation label, and tail entity where the relation label is not seen at the training stage.  ...  The task setting of Zero-Shot Relation Classification 1 (ZeroRC) was previously introduced by Chen and Li (2021) to classify the relation between a given head and tail entity pair for unseen labels.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.09101v1">arXiv:2203.09101v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sbxrofae3jddnawmizuwutiyhy">fatcat:sbxrofae3jddnawmizuwutiyhy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220319013423/https://arxiv.org/pdf/2203.09101v1.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/74/3d/743dcf234cffd54c4e096a10a284dd81572b16ea.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.09101v1" 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>
&laquo; Previous Showing results 1 &mdash; 15 out of 2,383 results