Filters








595 Hits in 8.4 sec

Target Foresight Based Attention for Neural Machine Translation

Xintong Li, Lemao Liu, Zhaopeng Tu, Shuming Shi, Max Meng
<span title="">2018</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/d5ex6ucxtrfz3clshlkh3f6w2q" style="color: black;">Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</a> </i> &nbsp;
in neural machine translation, an attention model is used to identify the aligned source words for a target word target foresight word in order to select translation context, but it does not make use of  ...  gains in alignment task. however, this approach is useless in machine translation task on which the target foresight word is unavailable. in this paper, we propose a new attention model enhanced by the  ...  Since then many research works have been devoted to improve the neural machine translation by enhancing attention models.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n18-1125">doi:10.18653/v1/n18-1125</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/naacl/LiLTSM18.html">dblp:conf/naacl/LiLTSM18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/gvuv2xk6njgxvlqfekiio7y77e">fatcat:gvuv2xk6njgxvlqfekiio7y77e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200309063537/https://www.aclweb.org/anthology/N18-1125.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/fa/c0fa436f64d856e927fb95c89e6d3cf117c8ea6e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n18-1125"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

POS Tagging for Improving Code-Switching Identification in Arabic

Mohammed Attia, Younes Samih, Ali Elkahky, Hamdy Mubarak, Ahmed Abdelali, Kareem Darwish
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/xxwbxqjhubgp3hjldgjnzinkwa" style="color: black;">Proceedings of the Fourth Arabic Natural Language Processing Workshop</a> </i> &nbsp;
We try to answer the question of how strong is the POS signal in word-level code-switching identification.  ...  We build a deep learning model enriched with linguistic features (including POS tags) that outperforms the state-of-the-art results by 1.9% on the development set and 1.0% on the test set.  ...  Basically, the difference between fine and coarse tags is that in fine tags we preserve and concatenate the POS representation of the affixes and clitics, while in coarse tags we eliminate affix rep-  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w19-4603">doi:10.18653/v1/w19-4603</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/wanlp/AttiaSEMAD19.html">dblp:conf/wanlp/AttiaSEMAD19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wgdxiaulkzfrhhacugwbqqnvnq">fatcat:wgdxiaulkzfrhhacugwbqqnvnq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200505203324/https://www.aclweb.org/anthology/W19-4603.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/84/3f/843f58b5f34b45c29577cc17ebd28efea97fade7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/w19-4603"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

A Survey on Recent Advances in Sequence Labeling from Deep Learning Models [article]

Zhiyong He, Zanbo Wang, Wei Wei, Shanshan Feng, Xianling Mao, Sheng Jiang
<span title="2020-11-13">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
., part-of-speech (POS) tagging, named entity recognition (NER), text chunking, etc.  ...  Recently, deep learning has been employed for sequence labeling tasks due to its powerful capability in automatically learning complex features of instances and effectively yielding the stat-of-the-art  ...  [111] in 2017 and achieves excellent performance for Neural Machine Translation (NMT) tasks.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.06727v1">arXiv:2011.06727v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lbephd7kdjh6libg2v5xju7lri">fatcat:lbephd7kdjh6libg2v5xju7lri</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201117004422/https://arxiv.org/pdf/2011.06727v1.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/39/cb/39cba8da65a0d042f4a40a1e97156080fdca46ff.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2011.06727v1" 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>

Non-Autoregressive Coarse-to-Fine Video Captioning [article]

Bang Yang, Yuexian Zou, Fenglin Liu, Can Zhang
<span title="2021-03-24">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we propose a non-autoregressive decoding based model with a coarse-to-fine captioning procedure to alleviate these defects.  ...  In implementations, we employ a bi-directional self-attention based network as our language model for achieving inference speedup, based on which we decompose the captioning procedure into two stages,  ...  Non-Autoregressive Decoding Non-autoregressive (NA) decoding has aroused widespread attention in the community of neural machine translation (NMT) [16-18, 20, 31, 35, 41, 51] due to its high inference  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.12018v6">arXiv:1911.12018v6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/abfjmfmk4rd35gisvyr4csqvai">fatcat:abfjmfmk4rd35gisvyr4csqvai</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200710053737/https://arxiv.org/pdf/1911.12018v4.pdf" title="fulltext PDF download [not primary version]" 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] <span style="color: #f43e3e;">&#10033;</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/af/be/afbeef9976cc595f80f80b39ade632bd4c8cd0b7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1911.12018v6" 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>

A Survey on Deep Learning for Named Entity Recognition [article]

Jing Li, Aixin Sun, Jianglei Han, Chenliang Li
<span title="2020-03-18">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
NER always serves as the foundation for many natural language applications such as question answering, text summarization, and machine translation.  ...  Then, we systematically categorize existing works based on a taxonomy along three axes: distributed representations for input, context encoder, and tag decoder.  ...  [178] proposed a tag-hierarchy model for heterogeneous tag-sets NER setting, where the hierarchy is used during inference to map fine-grained tags onto a target tag-set.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.09449v3">arXiv:1812.09449v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/36tnstbyo5h4xizjpqn4cevgui">fatcat:36tnstbyo5h4xizjpqn4cevgui</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200320225403/https://arxiv.org/pdf/1812.09449v3.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] </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1812.09449v3" 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>

Extending Neural Question Answering with Linguistic Input Features

Fabian Hommel, Matthias Orlikowski, Philipp Cimiano, Matthias Hartung
<span title="2019-08-21">2019</span> <i title="Zenodo"> Zenodo </i> &nbsp;
a first approach for integrating linguistic input features such as part-of-speech tags, syntactic dependency relations and semantic roles.  ...  Our findings suggest that these layers of linguistic knowledge have the potential to substantially increase the generalization capacities of neural QA models, thus facilitating cross-domain model transfer  ...  of machine translation.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.3373529">doi:10.5281/zenodo.3373529</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/32he2ngthjhk3eljqckf2e5zum">fatcat:32he2ngthjhk3eljqckf2e5zum</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201223022938/https://zenodo.org/record/3373529/files/paper.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/21/e6/21e6bf9daf4c2cdf65ed6466cf2a46ffaa7881ff.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.3373529"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Transfer Learning for Arabic Named Entity Recognition with Deep Neural Networks

Mohammad AL-Smadi, Saad Al-Zboon, Yaser Jararweh, Patrick Juola
<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;
The main aim of building a new model is to provide better fine-grained results for use in the Natural Language Processing fields.  ...  Our proposed model scored about 17% enhancement when being compared to previous work.  ...  Table 1 , the WikiFANE Gold consists of 8 coarse-grained classes spans over 50 fine-grained classes.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2973319">doi:10.1109/access.2020.2973319</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/dmlzxzs2snd5ne2jfjco3v3ovy">fatcat:dmlzxzs2snd5ne2jfjco3v3ovy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108190105/https://ieeexplore.ieee.org/ielx7/6287639/8948470/08993806.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/11/94/1194752c488632261b82eb9d1216c138538342bc.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/access.2020.2973319"> <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>

Back to Prior Knowledge: Joint Event Causality Extraction via Convolutional Semantic Infusion [article]

Zijian Wang, Hao Wang, Xiangfeng Luo, Jianqi Gao
<span title="2021-02-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Considering the prior knowledge of frequent n-grams that represent cause/effect events may benefit both event and causality extraction, in this paper, we propose convolutional knowledge infusion for frequent  ...  In the future, a potential direction is to adopt our method to few-shot learning of coarse-to-fine causality extraction.  ...  It has been successfully applied in many NLP tasks, such as machine translation and language understanding.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.09923v1">arXiv:2102.09923v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/fwcjpfdn6re5pksbuseyjlbtla">fatcat:fwcjpfdn6re5pksbuseyjlbtla</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210223013333/https://arxiv.org/pdf/2102.09923v1.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/05/78/05788371d2a046acfc60dd86558238bd80813bf8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2102.09923v1" 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>

Ambiguity Resolution : An Analytical Study

Prashant Y. Itankar, Nikhat Raza
<span title="2020-04-15">2020</span> <i title="Technoscience Academy"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/cwo66igunvdiplkdqwpqsgzpem" style="color: black;">International Journal of Scientific Research in Computer Science Engineering and Information Technology</a> </i> &nbsp;
Natural language processing (NLP) is very much needed in today's world to enhance human-machine interaction.  ...  It is an important concern to process textual data and obtain useful and meaningful information from these texts. NLP parses the texts and provides information to machine for further processing.  ...  ., Bengio Y; " Multiway multilingual neural machine translation with a shared attention mechanism",Proceedings of the NAACL-HLT 2016, pp. 866-875.[8].  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32628/cseit2062135">doi:10.32628/cseit2062135</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/p6o43nume5a7biltte4oednosy">fatcat:p6o43nume5a7biltte4oednosy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201107124619/http://ijsrcseit.com/paper/CSEIT2062135.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/a6/0f/a60f1b437611f76feb4a43e6a5beff28e1ac0880.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32628/cseit2062135"> <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>

Neural Supervised Domain Adaptation by Augmenting Pre-trained Models with Random Units [article]

Sara Meftah, Nasredine Semmar, Youssef Tamaazousti, Hassane Essafi, Fatiha Sadat
<span title="2021-06-09">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We show that our approach exhibits significant improvements to the standard fine-tuning scheme for neural domain adaptation from the news domain to the social media domain on four NLP tasks: part-of-speech  ...  Notably, TL is widely used for neural domain adaptation to transfer valuable knowledge from high-resource to low-resource domains.  ...  Neural Machine Translation (NMT)), a shallow classifier is trained on top of the frozen M on a corpus annotated with the linguistic properties of interest.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.04935v1">arXiv:2106.04935v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/blerqmjokfc73insvdudxnpzhy">fatcat:blerqmjokfc73insvdudxnpzhy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210612041306/https://arxiv.org/pdf/2106.04935v1.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/3a/35/3a35958d6ab66f965e20312390462aa60e54dc78.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2106.04935v1" 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>

Automating Reading Comprehension by Generating Question and Answer Pairs [article]

Vishwajeet Kumar, Kireeti Boorla, Yogesh Meena, Ganesh Ramakrishnan, Yuan-Fang Li
<span title="2018-03-07">2018</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Finally, global attention and answer encoding are used for generating the question most relevant to the answer.  ...  In our second stage, we employ sequence to sequence models for question generation, enhanced with rich linguistic features.  ...  Recent successes in neural machine translation [18, 4] have helped address this problem by letting deep neural nets learn the implicit rules through data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.03664v1">arXiv:1803.03664v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ulchnkmf5nbxfbnayyjpfhytcq">fatcat:ulchnkmf5nbxfbnayyjpfhytcq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200927120240/https://arxiv.org/pdf/1803.03664v1.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/3d/09/3d09bbe5e6eebfc5ad2a03d861e7566121773e60.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1803.03664v1" 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>

On the Potential of Lexico-logical Alignments for Semantic Parsing to SQL Queries [article]

Tianze Shi, Chen Zhao, Jordan Boyd-Graber, Hal Daumé III, Lillian Lee
<span title="2020-10-21">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Our annotation enables new training possibilities for encoder-decoder models, including approaches from machine translation previously precluded by the absence of alignments.  ...  We propose and test two methods: (1) supervised attention; (2) adopting an auxiliary objective of disambiguating references in the input queries to table columns.  ...  Acknowledgments We thank the members of UMD CLIP, Xilun Chen, Jack Hessel, Thomas Müller, Ana Smith, and the anonymous reviewers and meta-reviewer for their suggestions and comments.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.11246v1">arXiv:2010.11246v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wpmjjsbhffhxpf4ugtfkjjfspq">fatcat:wpmjjsbhffhxpf4ugtfkjjfspq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201024181051/https://arxiv.org/pdf/2010.11246v1.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/6b/2c/6b2ccee1ac5823ed3d0cf97c75470ea335916c07.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.11246v1" 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>

Deep Contextualized Word Representations

Matthew Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, Luke Zettlemoyer
<span title="">2018</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/d5ex6ucxtrfz3clshlkh3f6w2q" style="color: black;">Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)</a> </i> &nbsp;
., to model polysemy). Our word vectors are learned functions of the internal states of a deep bidirectional language model (biLM), which is pretrained on a large text corpus.  ...  We also present an analysis showing that exposing the deep internals of the pretrained network is crucial, allowing downstream models to mix different types of semi-supervision signals.  ...  In an RNN-based encoder-decoder machine translation system, Belinkov et al. (2017) showed that the representations learned at the first layer in a 2-layer LSTM encoder are better at predicting POS tags  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n18-1202">doi:10.18653/v1/n18-1202</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/naacl/PetersNIGCLZ18.html">dblp:conf/naacl/PetersNIGCLZ18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/lbvmqppuo5cpllcubjt2ubb37m">fatcat:lbvmqppuo5cpllcubjt2ubb37m</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200318203518/https://openreview.net/pdf?id=SJTCsqMUf" 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/ae/cf/aecfdc800fbc7f5e8deb191b28b36da9ae675116.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/n18-1202"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Gap Analysis of Natural Language Processing Systems with respect to Linguistic Modality [article]

Vishal Shukla
<span title="2015-04-18">2015</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
It sees human cognition and intelligence as multi-layered approach that can be implemented by intelligent systems for learning.  ...  It lets speaker to express attitude towards, or give assessment or potentiality of state of affairs. It implies different senses and thus has different perceptions as per the context.  ...  Yet another deep learning approach to machine translation appeared in Mikolov et al (2013b) .  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1504.04716v1">arXiv:1504.04716v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/yyyavwfdv5eshofyoyskbvrnqy">fatcat:yyyavwfdv5eshofyoyskbvrnqy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200922131739/https://arxiv.org/pdf/1504.04716v1.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/d7/79/d779dc8821189b7cf1ddb0ce86e3cbb38d1aae11.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1504.04716v1" 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>

Multi-Task Learning in Natural Language Processing: An Overview [article]

Shijie Chen, Yu Zhang, Qiang Yang
<span title="2021-09-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
However, deep neural models often suffer from overfitting and data scarcity problems that are pervasive in NLP tasks.  ...  In recent years, Multi-Task Learning (MTL), which can leverage useful information of related tasks to achieve simultaneous performance improvement on multiple related tasks, has been used to handle these  ...  [110] feeds the result of morphological tagging to a POS tagging model and the two models are further tied by skip connections.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.09138v1">arXiv:2109.09138v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hlgzjykuvzczzmsgnl32w5qo5q">fatcat:hlgzjykuvzczzmsgnl32w5qo5q</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210922043138/https://arxiv.org/pdf/2109.09138v1.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/76/0f/760f807406272b5ede591f19241824f2d17c319a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.09138v1" 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 595 results