Filters








25,155 Hits in 8.0 sec

Broad-Coverage Parsing with Neural Networks

Marshall R. Mayberry, Risto Miikkulainen
<span title="">2005</span> <i title="Springer Nature"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rcs76v6h7jf2lnaoy2wi3gg4ny" style="color: black;">Neural Processing Letters</a> </i> &nbsp;
In this study, we show that it is possible to keep track of long-distance dependencies and to parse into deeper structures than before based on two techniques: a localist encoding of the input sequence  ...  Yet, it has been very hard to scale them up to realistic language due to training time, limited memory, and the difficulty of representing linguistic structure.  ...  Rather, the network must learn to associate word sequences with the rule names as they appear in the parse tree, and generalize to new sequences.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11063-004-3423-4">doi:10.1007/s11063-004-3423-4</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nwbp4c6sq5caxehekenhnsx55i">fatcat:nwbp4c6sq5caxehekenhnsx55i</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170922052112/http://www.cs.utexas.edu/users/ai-lab/pubs/mayberry.nepl05.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/85/eb/85ebcb022d7a8a9b083733b0e0cbec5cf2671ca6.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/s11063-004-3423-4"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Monte Carlo Tree Search for Scheduling Activity Recognition

Mohamed R. Amer, Sinisa Todorovic, Alan Fern, Song-Chun Zhu
<span title="">2013</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/753trptklbb4nj6jquqadzwwdu" style="color: black;">2013 IEEE International Conference on Computer Vision</a> </i> &nbsp;
To address challenges of the domain, we use an expressive spatiotemporal AND-OR graph (ST-AOG) that jointly models activity parts, their spatiotemporal relations, and context, as well as enables multitarget  ...  This paper presents an efficient approach to video parsing. Our videos show a number of co-occurring individual and group activities.  ...  through the node so far during the search.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccv.2013.171">doi:10.1109/iccv.2013.171</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/iccv/AmerTFZ13.html">dblp:conf/iccv/AmerTFZ13</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nhajpvubrbgbphnu7547vwzkxm">fatcat:nhajpvubrbgbphnu7547vwzkxm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20140616224305/http://www.cs.ucf.edu:80/courses/cap6412/spr2014/papers/iccv13_MCTS.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/f6/d6/f6d6ed64e5e2826effb396dbec01d46b0a1555b0.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/iccv.2013.171"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Leveraging Subword Embeddings for Multinational Address Parsing [article]

Marouane Yassine, David Beauchemin, François Laviolette, Luc Lamontagne
<span title="2021-05-02">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose an approach in which we employ subword embeddings and a Recurrent Neural Network architecture to build a single model capable of learning to parse addresses from multiple countries at the same  ...  We explore the possibility of transferring the address parsing knowledge obtained by training on some countries' addresses to others with no further training in a zero-shot transfer learning setting.  ...  These results illustrate that our model, regardless of the embeddings model, learned the representation of an address sequence even if the words' representations are not native to the language (French  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16152v3">arXiv:2006.16152v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/szrhytozdfeqxhwu5ulbu5t2ja">fatcat:szrhytozdfeqxhwu5ulbu5t2ja</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210505161352/https://arxiv.org/pdf/2006.16152v3.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/08/fb/08fbf46a0a74e4a68727c60c276113ba25124b4c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2006.16152v3" 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>

Toward large-scale learning design

Dan Davis, Daniel Seaton, Claudia Hauff, Geert-Jan Houben
<span title="">2018</span> <i title="ACM Press"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/stnb4l4vlfebzbocpqypc4dziq" style="color: black;">Proceedings of the Fifth Annual ACM Conference on Learning at Scale - L@S &#39;18</a> </i> &nbsp;
environments through quantitative modeling of the structure and design of Massive Open Online Courses.  ...  Course materials from these MOOCs are parsed and abstracted into sequences of components, such as videos and problems.  ...  By understanding the theory and methodology from the learning design literature and applying it to large-scale learning environments, we are able to advance the field of learning at scale through a quantitative  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3231644.3231663">doi:10.1145/3231644.3231663</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/lats/DavisSHH18.html">dblp:conf/lats/DavisSHH18</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/devm3kue5zf7lnlsnt2k4q76qu">fatcat:devm3kue5zf7lnlsnt2k4q76qu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200306031630/https://repository.tudelft.nl/islandora/object/uuid%3A8f38bb9e-996f-450e-8a5d-f692a1ced74b/datastream/OBJ/download" 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/a1/5c/a15c1cd7c8dd218113a7e9d2db2fd828ba37febd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3231644.3231663"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

A Neural Probabilistic Structured-Prediction Model for Transition-Based Dependency Parsing

Hao Zhou, Yue Zhang, Shujian Huang, Jiajun Chen
<span title="">2015</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</a> </i> &nbsp;
We propose a neural probabilistic structured-prediction model for transition-based dependency parsing, which integrates search and learning.  ...  Beam search is used for decoding, and contrastive learning is performed for maximizing the sentence-level log-likelihood.  ...  We address the challenge by using a softmax function to directly model the distribution of action sequences.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3115/v1/p15-1117">doi:10.3115/v1/p15-1117</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/ZhouZHC15.html">dblp:conf/acl/ZhouZHC15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vpimiankpfdkjbjxwii4stesh4">fatcat:vpimiankpfdkjbjxwii4stesh4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200505232918/https://www.aclweb.org/anthology/P15-1117.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/22/2c22177821ffebc8bbdd8fd0d10b91a48c18d495.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3115/v1/p15-1117"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Online Object Tracking, Learning and Parsing with And-Or Graphs [article]

Tianfu Wu and Yang Lu and Song-Chun Zhu
<span title="2016-09-03">2016</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Three key issues in online inference and learning are addressed: (i) maintaining purity of positive and negative examples collected online, (ii) controling model complexity in latent structure learning  ...  This paper presents a method, called AOGTracker, for simultaneously tracking, learning and parsing (TLP) of unknown objects in video sequences with a hierarchical and compositional And-Or graph (AOG) representation  ...  Most prior approaches do not address this issue since they focus on marginally optimal solutions with which object models are updated, except for the P-N learning in TLD [17] and the self-paced learning  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1509.08067v6">arXiv:1509.08067v6</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/42v7eqwgm5bztdd52isxkw63km">fatcat:42v7eqwgm5bztdd52isxkw63km</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201001042744/https://arxiv.org/pdf/1509.08067v6.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/f7/19/f719fd04a7f0dbf374314cc2b5cd9e9984829d8c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1509.08067v6" 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>

Multinational Address Parsing: A Zero-Shot Evaluation [article]

Marouane Yassine and David Beauchemin and François Laviolette and Luc Lamontagne
<span title="2021-12-07">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
This paper explores the possibility of transferring the address parsing knowledge acquired by training deep learning models on some countries' addresses to others with no further training in a zero-shot  ...  While these models yield notable results, previous work on neural networks has only focused on parsing addresses from a single source country.  ...  For instance, [4] proposed a large scale HMM-based parsing technique capable of segmenting a large number of addresses whilst being robust to possible irregularities in the input data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.04008v1">arXiv:2112.04008v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/qfscsdffnbbylmlfhgt37wa2py">fatcat:qfscsdffnbbylmlfhgt37wa2py</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211210062143/https://arxiv.org/pdf/2112.04008v1.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/a3/84a32344585cf33ecb507072bc1b530e38874ab7.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2112.04008v1" 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 connectionist architecture for learning to parse

James Henderson, Peter Lane
<span title="">1998</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/5n6volmnonf5tn6xputi5f2t3e" style="color: black;">Proceedings of the 36th annual meeting on Association for Computational Linguistics -</a> </i> &nbsp;
We apply these Simple Synchrony Networks to mapping sequences of word tags to parse trees.  ...  We present a connectionist architecture and demonstrate that it can learn syntactic parsing from a corpus of parsed text.  ...  Computation is performed by the input activation being scaled by the weighted links and passed through the activation functions of the "hidden" units, which are neither part of the input nor output.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3115/980845.980934">doi:10.3115/980845.980934</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/acl/HendersonL98.html">dblp:conf/acl/HendersonL98</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/6xo6jw5morhmhi4upfd3ymkgoq">fatcat:6xo6jw5morhmhi4upfd3ymkgoq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20060109033443/http://ucrel.lancs.ac.uk:80/acl/C/C98/C98-1084.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/b0/69/b069def82263b2c7beaa84cc0f53589ba829327d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3115/980845.980934"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Language (Re)modelling: Towards Embodied Language Understanding [article]

Ronen Tamari, Chen Shani, Tom Hope, Miriam R. L. Petruck, Omri Abend, Dafna Shahaf
<span title="2020-07-09">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
through embodied interaction.  ...  This work proposes an approach to representation and learning based on the tenets of embodied cognitive linguistics (ECL).  ...  Functionally similar to the executor module in executable semantic parsing, but learned, and obviously far greater in scale.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.00311v2">arXiv:2005.00311v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/giwy3vxpazd73m5nmvj7lwo32e">fatcat:giwy3vxpazd73m5nmvj7lwo32e</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200711102846/https://arxiv.org/pdf/2005.00311v2.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/06/c4/06c47c1575cce38ce57ede8b3de91f9ae6592404.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2005.00311v2" 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>

Temporal Modular Networks for Retrieving Complex Compositional Activities in Videos [chapter]

Bingbin Liu, Serena Yeung, Edward Chou, De-An Huang, Li Fei-Fei, Juan Carlos Niebles
<span title="">2018</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2w3awgokqne6te4nvlofavy5a4" style="color: black;">Lecture Notes in Computer Science</a> </i> &nbsp;
The task of video retrieval using natural language descriptions seeks to address this through rich, unconstrained supervision about complex activities.  ...  A major challenge in computer vision is scaling activity understanding to the long tail of complex activities without requiring collecting large quantities of data for new actions.  ...  Scaling these recognition models to the long tail of complex activities is still an open problem in this paradigm, as it requires collecting large quantities of data for new action classes and does not  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01219-9_34">doi:10.1007/978-3-030-01219-9_34</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/hzf7okpakfhtpaemehxnsfntmu">fatcat:hzf7okpakfhtpaemehxnsfntmu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190819021255/http://openaccess.thecvf.com:80/content_ECCV_2018/papers/Bingbin_Liu_Temporal_Modular_Networks_ECCV_2018_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/f1/f4/f1f45a961cd429d3257d98a9a7f803a2783f11a8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-01219-9_34"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Toward the attribution of Web behavior

Myriam Abramson
<span title="">2012</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/fo5xrgppzfdaho2gthl2w7x66i" style="color: black;">2012 IEEE Symposium on Computational Intelligence for Security and Defence Applications</a> </i> &nbsp;
In this paper we describe some exploratory work and preliminary comparative results of machine learning techniques applicable to the attribution of Web browsing behavior problem.  ...  Structured prediction is being activately researched in natural language processing to predict parse trees from sentences and in sequence matching problems such as machine translation [14] .  ...  Although work has been done on overcoming those limitations resulting in complex models, structured prediction methods provide a unified framework to predict and learn arbitrary activity patterns.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cisda.2012.6291524">doi:10.1109/cisda.2012.6291524</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/cisda/Abramson12.html">dblp:conf/cisda/Abramson12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/7zxkjpblnnaspivwpxqcqhogtu">fatcat:7zxkjpblnnaspivwpxqcqhogtu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170716212802/http://www.dtic.mil/get-tr-doc/pdf?AD=ADA602793" 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/8c/ac/8cac04f5a4016ad87675c08112dac97834857eae.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/cisda.2012.6291524"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Parsing of action sequences: A neural dynamics approach

David Lobato, Yulia Sandamirskaya, Mathis Richter, Gregor Schöner
<span title="2015-01-15">2015</span> <i title="Walter de Gruyter GmbH"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/bzmvliqxvbagrbeayuh67oboom" style="color: black;">Paladyn: Journal of Behavioral Robotics</a> </i> &nbsp;
In this paper, we develop a model for action parsing, based on our understanding of principles of grounded cognitive processes, such as perceptual decision making, behavioral organization, and memory formation.We  ...  present a neural-dynamic architecture, in which action sequences are parsed using a mathematical and conceptual framework for embodied cognition—the Dynamic Field Theory.  ...  During sequence replay, the ordinal nodes may be activated in a sequence and, through the learned connections, activate the intention nodes and the target field.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1515/pjbr-2015-0008">doi:10.1515/pjbr-2015-0008</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/la7cruq6l5g3fcj7ctfh5tt5di">fatcat:la7cruq6l5g3fcj7ctfh5tt5di</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200327034429/https://www.degruyter.com/downloadpdf/journals/pjbr/open-issue/article-10.1515-pjbr-2015-0008/article-10.1515-pjbr-2015-0008.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/6c/45/6c453c9ff433d91880de86b25e627a61b746bcd3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1515/pjbr-2015-0008"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> degruyter.com </button> </a>

Connectionist natural language parsing

Dominic Palmer-Brown, Jonathan A. Tepper, Heather M. Powell
<span title="">2002</span> <i title="Elsevier BV"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/2gvktplqc5gm7mwsea6qgdwy4m" style="color: black;">Trends in Cognitive Sciences</a> </i> &nbsp;
Summary The key developments of two decades of connectionist parsing are reviewed.  ...  is reviewed, and an assessment is made of their ability to model human sentence processing.  ...  Early localist parsing models were able to provide some account of human syntactic and semantic attachment preferences, whereby alternative interpretations remain active until they become incompatible  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s1364-6613(02)01980-0">doi:10.1016/s1364-6613(02)01980-0</a> <a target="_blank" rel="external noopener" href="https://www.ncbi.nlm.nih.gov/pubmed/12413578">pmid:12413578</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/74j5hf54wvgd3ftvh4ei6yzjeu">fatcat:74j5hf54wvgd3ftvh4ei6yzjeu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180719182024/http://irep.ntu.ac.uk/id/eprint/21549/1/196600_618%20Powell%20Postprint.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/88/93/8893024e467b82fc6135db2797ff6b589e8c76d8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1016/s1364-6613(02)01980-0"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> elsevier.com </button> </a>

Compositional Networks Enable Systematic Generalization for Grounded Language Understanding [article]

Yen-Ling Kuo, Boris Katz, Andrei Barbu
<span title="2021-10-19">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
to be learned end-to-end.  ...  Our network also provides a level of interpretability that enables users to inspect what each part of networks learns.  ...  learning and longer action sequences.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.02742v3">arXiv:2008.02742v3</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/ner76upbvzbxjjximwhguopyei">fatcat:ner76upbvzbxjjximwhguopyei</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211029113339/https://arxiv.org/pdf/2008.02742v3.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/32/68/3268a9371aad1bc8ba1458338ab184ef000a9525.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2008.02742v3" 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>

3D Head Pose Estimation through Facial Features and Deep Convolutional Neural Networks

Khalil Khan, Jehad Ali, Kashif Ahmad, Asma Gul, Ghulam Sarwar, Sahib Khan, Qui Thanh Hoai Ta, Tae-Sun Chung, Muhammad Attique
<span title="">2021</span> <i title="Computers, Materials and Continua (Tech Science Press)"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/amujz7fcqna6do727z6ev3ueo4" style="color: black;">Computers Materials &amp; Continua</a> </i> &nbsp;
In this paper we propose a 3D head pose estimation framework developed through a prior end to end deep face parsing model.  ...  For training a deep face parts parsing model, we label face images for seven different classes, including eyes, brows, nose, hair, mouth, skin, and back.  ...  Face parsing part:Step a.1: Training a face parsing DCNNs model through training data.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32604/cmc.2020.013590">doi:10.32604/cmc.2020.013590</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jriv7ogl7zgjlcoicosv5bbn6a">fatcat:jriv7ogl7zgjlcoicosv5bbn6a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220223235928/https://www.techscience.com/ueditor/files/TSP_CMC_66-2/TSP_CMC_13590/TSP_CMC_13590.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/8a/3a8a5b656b3d28c791c6fc0df251c4df63f7381a.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.32604/cmc.2020.013590"> <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 25,155 results