Filters








30 Hits in 2.9 sec

Siamese convolutional networks based on phonetic features for cognate identification [article]

Taraka Rama
2016 arXiv   pre-print
In this paper, we explore the use of convolutional networks (ConvNets) for the purpose of cognate identification.  ...  Our experiments show that convolutional networks achieve competitive results across concepts and across language families at the task of cognate identification.  ...  Conclusion In this article, we explored the use of phonetic feature convolutional networks for the task of pairwise cognate identification.  ... 
arXiv:1605.05172v2 fatcat:fovxshl7wfhchbcijhhjqg2ou4

Cross-Family Similarity Learning for Cognate Identification in Low-Resource Languages

Eliel Soisalon-Soininen, Department of Computer Science, University of Helsinki, Finland, Mark Granroth-Wilding
2019 Proceedings - Natural Language Processing in a Deep Learning World  
We apply two models, following previous work: a Siamese convolutional neural network (S-CNN) and a support vector machine (SVM), and compare them with a Levenshtein distance baseline.  ...  We address the problem of cognate identification across vocabularies of any pair of languages.  ...  Siamese convolutional neural network The Siamese convolutional neural network (S-CNN) is a supervised learning model originally proposed by Chopra et al. (2005) for the task of face verification, and  ... 
doi:10.26615/978-954-452-056-4_129 dblp:conf/ranlp/Soisalon-Soininen19 fatcat:k5epjogozvcfjgdigr3cbhqdr4

Challenge Dataset of Cognates and False Friend Pairs from Indian Languages [article]

Diptesh Kanojia, Pushpak Bhattacharyya, Malhar Kulkarni, Gholamreza Haffari
2021 arXiv   pre-print
In this paper, we describe the creation of two cognate datasets for twelve Indian languages, namely Sanskrit, Hindi, Assamese, Oriya, Kannada, Gujarati, Tamil, Telugu, Punjabi, Bengali, Marathi, and Malayalam  ...  Additionally, we use the Wordnet data to create a False Friends' dataset for eleven language pairs.  ...  Siamese convolutional networks for cog- sociation for Computational Linguistics. nate identification. In Proceedings of COLING 2016, the Kondrak, G. (2000).  ... 
arXiv:2112.09526v1 fatcat:paynzxjadnd4lcqx6hx3dy76r4

Siamese Networks for Large-Scale Author Identification [article]

Chakaveh Saedi, Mark Dras
2021 arXiv   pre-print
Siamese networks have been used to develop learned notions of similarity in one-shot image tasks, and also for tasks of mostly semantic relatedness in NLP.  ...  Approaches to tackling it have been conventionally divided into classification-based ones, which work well for small numbers of candidate authors, and similarity-based methods, which are applicable for  ...  There have been two attempts before this work to use Siamese networks for author identification, and two contemporaneous with it.  ... 
arXiv:1912.10616v3 fatcat:has2zgpd2fawrp6b2yk5hhewqa

PREDICTING RATINGS FOR USER REVIEWS AND OPINION MINING ANALYZE FOR PHYSICIANS AND HOSPITALS

Hema Sagar Vakati, Jebakumar R
2017 Asian Journal of Pharmaceutical and Clinical Research  
The patients also browse on their concerneddiseases and use the open forum for discussion on the topics.  ...  The feedback provided by patients is considered and we also analyze the sentiments of the patient to estimate the value of the reviews.The rating for the doctors is divided into various categories such  ...  Rama [7] . proposed the phoneme level Siamese for pairwise cognate identification.  ... 
doi:10.22159/ajpcr.2017.v10i3.16094 fatcat:ve54uhhbjndqjjfm7vpbuyzcqi

Cognition-aware Cognate Detection [article]

Diptesh Kanojia, Prashant Sharma, Sayali Ghodekar, Pushpak Bhattacharyya, Gholamreza Haffari, Malhar Kulkarni
2021 arXiv   pre-print
We collect gaze behaviour data for a small sample of cognates and show that extracted cognitive features help the task of cognate detection.  ...  Previous approaches for the task of cognate detection use orthographic, phonetic and semantic similarity based features sets.  ...  Rama (2016) employs a Siamese convolutional neural network to learn the phonetic features jointly with language relatedness for cognate identification.  ... 
arXiv:2112.08087v1 fatcat:pjkqujnmazaazns77vpbb3boeq

Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages [article]

Diptesh Kanojia, Raj Dabre, Shubham Dewangan, Pushpak Bhattacharyya, Gholamreza Haffari, Malhar Kulkarni
2021 arXiv   pre-print
Cognates are variants of the same lexical form across different languages; for example 'fonema' in Spanish and 'phoneme' in English are cognates, both of which mean 'a unit of sound'.  ...  Additionally, we create evaluation datasets for two more Indian languages, Konkani and Nepali. We observe an improvement of up to 18% points, in terms of F-score, for cognate detection.  ...  Acknowledgements We thank the lexicographers and annotators at the CFILT Lab, IIT Bombay for their efforts in creating the dataset for this study.  ... 
arXiv:2112.08789v1 fatcat:226ghyw4abfe3fd5k5ldof3ylq

Predicting protein–protein interactions through sequence-based deep learning

Somaye Hashemifar, Behnam Neyshabur, Aly A Khan, Jinbo Xu
2018 Bioinformatics  
Our model efficiently applies a deep, Siamese-like convolutional neural network combined with random projection and data augmentation to predict PPIs, leveraging existing high-quality experimental PPI  ...  Second, DPPI employs a Siamese-like convolutional neural network architecture.  ...  Random projection module DPPI exploits a Siamese-like convolutional neural network architecture, and contains two identical convolutional modules with the same configuration and parameters for a pair of  ... 
doi:10.1093/bioinformatics/bty573 pmid:30423091 pmcid:PMC6129267 fatcat:cimsxsi6szhknnjrpwexya6xgu

Finding Sami Cognates with a Character-Based NMT Approach

Mika Hämäläinen, Jack Reuter
2019 Proceedings of the Workshop on Computational Methods for Endangered Languages  
The language pair of interest, Skolt Sami and North Sami, has too limited a set of parallel data for an NMT model as such.  ...  We approach the problem of expanding the set of cognate relations with a sequence-to-sequence NMT model.  ...  Another take on cognate detection is that of Rama (2016) . This approach employs Siamese convolutional networks to learn phoneme level representation and language relatedness of words.  ... 
doi:10.33011/computel.v1i.395 fatcat:phqlrrpdibcnjo3arqfy7sdc6q

Computational prediction and analysis of protein-protein interaction networks [article]

Somaye Hashemifar
2017 arXiv   pre-print
I will discuss several methods for protein-protein interaction network alignment and investigate their preferences to other existing methods.  ...  Reconstruction and comparative analysis of these networks provide useful information to identify functional modules, prioritization of disease causing genes and also identification of drug targets.  ...  For this purpose, we define ratio ρ as follows: Second, DPPI exploits a Siamese-like convolutional neural network architecture. ρ = d -" − d d ×100, Siamese neural networks are useful for tasks that involve  ... 
arXiv:1709.01923v2 fatcat:cy63jpklarbmxbrcvfgzx2ob2q

A Survey of the Usages of Deep Learning in Natural Language Processing [article]

Daniel W. Otter, Julian R. Medina, Jugal K. Kalita
2019 arXiv   pre-print
A discussion of the current state of the art is then provided along with recommendations for future research in the field.  ...  [134] , used a Siamese network, in which two CNNs sharing weights evaluated two sentences in parallel.  ...  deep [7] . 1) Convolutional Neural Networks: Convolutional neural networks (CNNs) [14] , [15] , built upon Fukashima's neocognitron [16] , [17] , derive the name from the convolution operation in  ... 
arXiv:1807.10854v3 fatcat:ajyv5o743naixeo5c5y6p6tg3e

Cognition-aware Cognate Detection

Diptesh Kanojia, Prashant Sharma, Sayali Ghodekar, Pushpak Bhattacharyya, Gholamreza Haffari, Malhar Kulkarni
2021 Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume   unpublished
We collect gaze behaviour data for a small sample of cognates and show that extracted cognitive features help the task of cognate detection.  ...  Previous approaches for the task of cognate detection use orthographic, phonetic and semantic similarity based features sets.  ...  Rama (2016) employs a Siamese convolutional neural network to learn the phonetic features jointly with language relatedness for cognate identification.  ... 
doi:10.18653/v1/2021.eacl-main.288 fatcat:ohyqcfoorvcpdcpyltbah34jfm

TRANSLIT : a large-scale name transliteration resource

Fernando Benites De Azevedo E Souza, Gilbert François Duivesteijn, Pius Von Däniken, Mark Cieliebak
2020
Our best systems achieve an accuracy of 92% on identification of transliterated pairs.  ...  In addition, we apply several machine learning methods to establish baselines for automatically detecting transliterated names in various languages.  ...  Acknowledgements We would like to thank Dandolo Flumini for the fruitful discussions and and his support with this project.  ... 
doi:10.21256/zhaw-20082 fatcat:j4t4mov5bncmlo42wzfzmjslge

Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages

Diptesh Kanojia, Raj Dabre, Shubham Dewangan, Pushpak Bhattacharyya, Gholamreza Haffari, Malhar Kulkarni
2020 Proceedings of the 28th International Conference on Computational Linguistics   unpublished
Cognates are variants of the same lexical form across different languages; for example "fonema" in Spanish and "phoneme" in English are cognates, both of which mean "a unit of sound".  ...  Additionally, we create evaluation datasets for two more Indian languages, Konkani and Nepali 1 . We observe an improvement of up to 18% points, in terms of F-score, for cognate detection.  ...  Acknowledgements We thank the lexicographers and annotators at the CFILT Lab, IIT Bombay for their efforts in creating the dataset for this study.  ... 
doi:10.18653/v1/2020.coling-main.119 fatcat:q5e7oyvdxna63l5qpnjhh7ehrq

Alignment Analysis of Sequential Segmentation of Lexicons to Improve Automatic Cognate Detection [article]

Pranav A
2018 pre-print
Source code is at: https://github.com/pranav-ust/cognates  ...  This paper focuses on a harder problem, whether we could predict a possible cognate from the given input.  ...  Special thanks to my classmate Chun Sik Chan and SRW mentor Sam Bowman for providing excellent critiques for this paper, and Alina Ciobanu for providing the dataset.  ... 
doi:10.18653/v1/p18-3019 arXiv:1811.08129v1 fatcat:df6bnim5brbahlm2crvqva3ajq
« Previous Showing results 1 — 15 out of 30 results