Filters








1,121 Hits in 4.7 sec

BinMLM: Binary Authorship Verification with Flow-aware Mixture-of-Shared Language Model [article]

Qige Song, Yongzheng Zhang, Linshu Ouyang, Yige Chen
<span title="2022-03-09">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
Furthermore, BinMLM can perform organization-level verification on a real-world APT malware dataset, which can provide valuable auxiliary information for exploring the group behind the APT attack.  ...  We propose an effective binary authorship verification framework, BinMLM.  ...  ACKNOWLEDGMENT The authors would like to thank the anonymous reviewers for their insightful comments. This work was supported by the National Natural Science Foundation of China under Grant U1736218.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.04472v1">arXiv:2203.04472v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/w46qme7zr5eklkhavu4aszfngi">fatcat:w46qme7zr5eklkhavu4aszfngi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220315215310/https://arxiv.org/pdf/2203.04472v1.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/4c/d9/4cd9eb1beaf72493d7ed54c41718e72a4681c56e.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2203.04472v1" 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 Relation-Specific Attention Network for Joint Entity and Relation Extraction

Yue Yuan, Xiaofei Zhou, Shirui Pan, Qiannan Zhu, Zeliang Song, Li Guo
<span title="">2020</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
Experiments on two public datasets show that our model can effectively extract overlapping triplets and achieve state-of-the-art performance.  ...  Joint extraction of entities and relations is an important task in natural language processing (NLP), which aims to capture all relational triplets from plain texts.  ...  However, applying deep learning on the authorship verification problem faces a major challenge: the amount of training texts for each author is extremely limited, which poses significant challenges to  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/557">doi:10.24963/ijcai.2020/557</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/OuyangZLCW20.html">dblp:conf/ijcai/OuyangZLCW20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/e6h4dv27dvghvlynpimswjgvlq">fatcat:e6h4dv27dvghvlynpimswjgvlq</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201104211807/https://www.ijcai.org/Proceedings/2020/0557.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/0c/8e/0c8ec2eb41ea511cd2517e0708fc24969b3db1d8.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/557"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Idiosyncratic but not Arbitrary: Learning Idiolects in Online Registers Reveals Distinctive yet Consistent Individual Styles [article]

Jian Zhu, David Jurgens
<span title="2021-09-08">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
The neural model achieves strong performance at authorship identification on short texts and through an analogy-based probing task, showing that the learned representations exhibit surprising regularities  ...  that encode qualitative and quantitative shifts of idiolectal styles.  ...  We are also grateful for comments from anonymous reviewers, which helped improve the paper greatly. This material is based upon work supported by the National Science Foundation under Grant No 185022.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03158v2">arXiv:2109.03158v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wdpyhxqeuray3jn5ymtsrbh65a">fatcat:wdpyhxqeuray3jn5ymtsrbh65a</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210916072756/https://arxiv.org/pdf/2109.03158v2.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/d7/3c/d73c0ce83f4567703b650c9ec0f0ad4adbf168b3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03158v2" 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-Domain Authorship Attribution Using Pre-trained Language Models [chapter]

Georgios Barlas, Efstathios Stamatatos
<span title="">2020</span> <i title="Springer International Publishing"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/kss7mrolvja63k4rmix3iynkzi" style="color: black;">IFIP Advances in Information and Communication Technology</a> </i> &nbsp;
In this paper, we modify a successful authorship verification approach based on a multi-headed neural network language model and combine it with pre-trained language models.  ...  An especially challenging but very realistic scenario is cross-domain attribution where texts of known authorship (training set) differ from texts of disputed authorship (test set) in topic or genre.  ...  The main idea is that a character-level RNN is produced using all available texts by the candidate authors while a separate output is built for each author (MHC).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-49161-1_22">doi:10.1007/978-3-030-49161-1_22</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/j7kjmdxtezb4rbc3agisl23ym4">fatcat:j7kjmdxtezb4rbc3agisl23ym4</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201108152258/https://link.springer.com/content/pdf/10.1007%2F978-3-030-49161-1_22.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/09/8d/098dd3c44576981da2f4517b71e5c4dc54e7f7df.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-030-49161-1_22"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

A Self-supervised Representation Learning of Sentence Structure for Authorship Attribution [article]

Fereshteh Jafariakinabad, Kien A. Hua
<span title="2022-02-24">2022</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
the performance of deep neural models in the domain of authorship attribution.  ...  Our experimental results indicate that the structural embeddings significantly improve the classification tasks when concatenated with the existing pre-trained word embeddings.  ...  In particular, Raghahvan et al. investigated the use of syntactic information by proposing a probabilistic context-free grammar for the authorship attribution purpose, and used it as a language model for  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.06786v2">arXiv:2010.06786v2</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h3zlsaqnnbdijonbqwh7erwkbu">fatcat:h3zlsaqnnbdijonbqwh7erwkbu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201023124050/https://arxiv.org/pdf/2010.06786v1.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/ce/f9/cef9ef28b226fc21885651b7915be6f4ece4e022.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.06786v2" 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>

Improving Authorship Verification using Linguistic Divergence [article]

Yifan Zhang, Dainis Boumber, Marjan Hosseinia, Fan Yang, Arjun Mukherjee
<span title="2021-03-12">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We propose an unsupervised solution to the Authorship Verification task that utilizes pre-trained deep language models to compute a new metric called DV-Distance.  ...  The proposed metric is a measure of the difference between the two authors comparing against pre-trained language models.  ...  Acknowledgement Research was supported in part by grants NSF 1838147, NSF 1838145, ARO W911NF-20-1-0254.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.07052v1">arXiv:2103.07052v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/vrowv74chnd63h3cxozmlv5mem">fatcat:vrowv74chnd63h3cxozmlv5mem</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210319174521/https://arxiv.org/pdf/2103.07052v1.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/96/88/968870576c3f38b3bcf8836e74cc2924280ee0c2.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2103.07052v1" 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>

Similarity Learning for Authorship Verification in Social Media

Benedikt Boenninghoff, Robert M. Nickel, Steffen Zeiler, Dorothea Kolossa
<span title="">2019</span> <i title="IEEE"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/rc5jnc4ldvhs3dswicq5wk3vsq" style="color: black;">ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)</a> </i> &nbsp;
Authorship verification tries to answer the question if two documents with unknown authors were written by the same author or not.  ...  Forensic authorship verification for social media, however, is a much more challenging task since messages tend to be relatively short, with a large variety of different genres and topics.  ...  The document representation vectors encode those stylistic characteristics of a document that are relevant for authorship verification.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icassp.2019.8683405">doi:10.1109/icassp.2019.8683405</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/icassp/BoenninghoffNZK19.html">dblp:conf/icassp/BoenninghoffNZK19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/sirwhgmewrar5oerzwkf47stsy">fatcat:sirwhgmewrar5oerzwkf47stsy</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200904225331/https://arxiv.org/pdf/1908.07844v1.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/21/77/21779d3b24fe44fbd33a6becc9144514fed66bd9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/icassp.2019.8683405"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

LG4AV: Combining Language Models and Graph Neural Networks for Author Verification [article]

Maximilian Stubbemann, Gerd Stumme
<span title="2021-09-03">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
By directly feeding the available texts in a pre-trained transformer architecture, our model does not need any hand-crafted stylometric features that are not meaningful in scenarios where the writing style  ...  To this point, we present our novel approach LG4AV which combines language models and graph neural networks for authorship verification.  ...  The authors would like to thank Dominik Dürrschnabel and Lena Stubbemann for fruitful discussions and comments on the manuscript.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.01479v1">arXiv:2109.01479v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/wtihhkl3nzg4hesgado2wy5ycm">fatcat:wtihhkl3nzg4hesgado2wy5ycm</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210909152423/https://arxiv.org/pdf/2109.01479v1.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/1a/56/1a56f7d89a7a5f34cb12818b1d746449bb1e4c50.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.01479v1" 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 Profile-Based Method for Authorship Verification [chapter]

Nektaria Potha, Efstathios Stamatatos
<span title="">2014</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;
Authorship verification is one of the most challenging tasks in stylebased text categorization.  ...  Recently, in the framework of the PAN-2013 evaluation lab, a competition in authorship verification was organized and the vast majority of submitted approaches, including the best performing models, followed  ...  The modification of Stamatatos [19] uses assymetric profiles where the profile of the unknown text has the maximum possible length while the profile of the known texts by one candidate author is pre-defined  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-07064-3_25">doi:10.1007/978-3-319-07064-3_25</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/pq75idjf4rdnvgrhnuthlz3izu">fatcat:pq75idjf4rdnvgrhnuthlz3izu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20171026042110/https://core.ac.uk/download/pdf/24060924.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/01/69/016935c5422c6db2c3b7f2facb1866bddacd0381.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1007/978-3-319-07064-3_25"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> springer.com </button> </a>

Towards Improved Model Design for Authorship Identification: A Survey on Writing Style Understanding [article]

Weicheng Ma, Ruibo Liu, Lili Wang, Soroush Vosoughi
<span title="2020-09-30">2020</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We are optimistic about the applicability of these models to authorship-based tasks and hope our survey will help advance research in this field.  ...  We then describe outstanding methods in style-related tasks in general and analyze how they are used in combination in the top-performing models.  ...  For example, Dong and de Melo (2018) keep pre-trained sentiment embeddings of words from multiple domains in a memory module and inject the lexical information into CNN encodings of documents by appending  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2009.14445v1">arXiv:2009.14445v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/bnrh5e6rc5debo4apsoqn257nu">fatcat:bnrh5e6rc5debo4apsoqn257nu</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201005125727/https://arxiv.org/pdf/2009.14445v1.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/2009.14445v1" 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>

Protecting Anonymous Speech: A Generative Adversarial Network Methodology for Removing Stylistic Indicators in Text [article]

Rishi Balakrishnan, Stephen Sloan, Anil Aswani
<span title="2021-10-18">2021</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
In this paper, we develop a new approach to authorship anonymization by constructing a generative adversarial network that protects identity and optimizes for three different losses corresponding to anonymity  ...  Existing approaches to authorship anonymization, also known as authorship obfuscation, often focus on protecting binary demographic attributes rather than identity as a whole.  ...  The function of the discriminator is authorship verification -taking in two pieces of text and identifying whether they are by the same author.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.09495v1">arXiv:2110.09495v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/cc6pfo2otjb37ooeqobvt6fhay">fatcat:cc6pfo2otjb37ooeqobvt6fhay</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20211025145653/https://arxiv.org/pdf/2110.09495v1.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/07/1f/071f128b40aba5642d747f1dbe49e986a1cc092b.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2110.09495v1" 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>

The Trumpiest Trump? Identifying a Subject's Most Characteristic Tweets

Charuta Pethe, Steve Skiena
<span title="">2019</span> <i title="Association for Computational Linguistics"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/u3ideoxy4fghvbsstiknuweth4" style="color: black;">Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</a> </i> &nbsp;
We then use these models to compute characterization scores among all of an author's texts.  ...  A user study shows human evaluators agree with our characterization model for all 15 celebrities in our dataset, each with p-value < 0.05.  ...  This work was partially supported by NSF grants IIS-1546113 and IIS-1927227.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d19-1175">doi:10.18653/v1/d19-1175</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/emnlp/PetheS19.html">dblp:conf/emnlp/PetheS19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/q73nkg4ewrgm5ns4ova66sooru">fatcat:q73nkg4ewrgm5ns4ova66sooru</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200821142118/https://www.aclweb.org/anthology/D19-1175.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/69/50/69506360738280669622a70c0dd7c591ca0eaee3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.18653/v1/d19-1175"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

The Trumpiest Trump? Identifying a Subject's Most Characteristic Tweets [article]

Charuta Pethe, Steven Skiena
<span title="2019-09-09">2019</span> <i > arXiv </i> &nbsp; <span class="release-stage" >pre-print</span>
We then use these models to compute characterization scores among all of an author's texts.  ...  A user study shows human evaluators agree with our characterization model for all 15 celebrities in our dataset, each with p-value < 0.05.  ...  This work was partially supported by NSF grants IIS-1546113 and IIS-1927227.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.04002v1">arXiv:1909.04002v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uid62qp2snfznhtbh7a5miedia">fatcat:uid62qp2snfznhtbh7a5miedia</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200902013444/https://arxiv.org/pdf/1909.04002v1.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/a0/5b/a05bfd2cec20a6022017af1d80712134fc834de3.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1909.04002v1" 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>

Gated POS-Level Language Model for Authorship Verification

Linshu Ouyang, Yongzheng Zhang, Hui Liu, Yige Chen, Yipeng Wang
<span title="">2020</span> <i title="International Joint Conferences on Artificial Intelligence Organization"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/vfwwmrihanevtjbbkti2kc3nke" style="color: black;">Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence</a> </i> &nbsp;
The state-of-the-art deep authorship verification methods typically leverage character-level language models to encode author-specific writing styles.  ...  The author-agnostic syntactic information obtained from the POS tagger pre-trained on large external datasets greatly reduces the number of effective parameters of our model, enabling the model to learn  ...  Acknowledgments This work was supported by the National Key Research and Development Project of China (No. 2018AAA0101900).  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/553">doi:10.24963/ijcai.2020/553</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/ijcai/XiaoZLST0W20.html">dblp:conf/ijcai/XiaoZLST0W20</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/oys33p4ltvbqvfymuyyjzatnby">fatcat:oys33p4ltvbqvfymuyyjzatnby</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201104233123/https://www.ijcai.org/Proceedings/2020/0553.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/6d/3d/6d3d58f0ba7bd64ffd626c33bf74b62f8c0a09f5.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.24963/ijcai.2020/553"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

Authorship Attribution of Social Media and Literary Russian-Language Texts Using Machine Learning Methods and Feature Selection

Anastasia Fedotova, Aleksandr Romanov, Anna Kurtukova, Alexander Shelupanov
<span title="2021-12-22">2021</span> <i title="MDPI AG"> <a target="_blank" rel="noopener" href="https://fatcat.wiki/container/hijy7jexkvcipg3tulqv73bck4" style="color: black;">Future Internet</a> </i> &nbsp;
The effectiveness of the models was evaluated on the two Russian-language datasets: literary texts and short comments from users of social networks.  ...  A particular experiment was devoted to the selection of informative features using genetic algorithms (GA) and evaluation of the classifier trained on the optimal feature space.  ...  Acknowledgments: The authors express their gratitude to the editor and reviewers for their work and valuable comments on the article.  ... 
<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/fi14010004">doi:10.3390/fi14010004</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/u2aqr6jurrabjlr6bizziibxhi">fatcat:u2aqr6jurrabjlr6bizziibxhi</a> </span>
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220502154309/https://mdpi-res.com/d_attachment/futureinternet/futureinternet-14-00004/article_deploy/futureinternet-14-00004-v2.pdf?version=1640243479" 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/14/c4/14c414a5a71994b830091e8e1ff14ef7b16dee51.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/fi14010004"> <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>
&laquo; Previous Showing results 1 &mdash; 15 out of 1,121 results