Filters








2,224 Hits in 7.1 sec

Novel Semantics-based Distributed Representations for Message Polarity Classification using Deep Convolutional Neural Networks

Abhinay Pandya, Mourad Oussalah
2017 Proceedings of the 9th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management  
Unsupervised learning of distributed representations (word embeddings) obviates the need for task-specific feature engineering for various NLP applications.  ...  In this paper, we propose three semantics-based distributed representations of words and phrases as features for message polarity classification: Sentiment-Specific Multi-Word Expressions Embeddings(SSMWE  ...  ACKNOWLEDGEMENTS We would like to thank the anonymous reviewers for their valuable suggestions because of which the technical quality of the work presented in this paper has improved.  ... 
doi:10.5220/0006500800710082 dblp:conf/ic3k/PandyaO17 fatcat:kx3t2cb32rg5tite6joaziknbm

A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios [article]

Michael A. Hedderich, Lukas Lange, Heike Adel, Jannik Strötgen, Dietrich Klakow
2021 arXiv   pre-print
This includes mechanisms to create additional labeled data like data augmentation and distant supervision as well as transfer learning settings that reduce the need for target supervision.  ...  After a discussion about the different dimensions of data availability, we give a structured overview of methods that enable learning when training data is sparse.  ...  A multi-source weak supervision for neural text classi- brief survey of relation extraction based on distant fication.  ... 
arXiv:2010.12309v3 fatcat:26dwmlkmn5auha2ob2qdlrvla4

Semantic Relations and Deep Learning [article]

Vivi Nastase, Stan Szpakowicz
2021 arXiv   pre-print
A new Chapter 5 of the book, by Vivi Nastase and Stan Szpakowicz, discusses relation classification/extraction in the deep-learning paradigm which arose after the first edition appeared.  ...  The second edition of "Semantic Relations Between Nominals" by Vivi Nastase, Stan Szpakowicz, Preslav Nakov and Diarmuid \'O S\'eaghdha has been published in April 2021 by Morgan & Claypool (www.morganclaypoolpublishers.com  ...  In word-level distant supervision for relation extraction, where filtering is based on syntactic information, a robust entity-wise attention model will give more weight to semantic features of relational  ... 
arXiv:2009.05426v4 fatcat:rmzoalfwcza4nex7pd4u6w7kbe

Generalized Tuning of Distributional Word Vectors for Monolingual and Cross-Lingual Lexical Entailment

Goran Glavaš, Ivan Vulić
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
In this work, we propose a simple and effective method for fine-tuning distributional word vectors for LE.  ...  Lexical entailment (LE; also known as hyponymy-hypernymy or is-a relation) is a core asymmetric lexical relation that supports tasks like taxonomy induction and text generation.  ...  Due to simplicity and robust downstream performance, 3 we opt for the simple supervised learning of the cross-lingual projection matrix W g (Smith et al., 2017) based on (closed-form) solution of the Procrustes  ... 
doi:10.18653/v1/p19-1476 dblp:conf/acl/GlavasV19 fatcat:4rfdb6vbhvep7bz3nnr3ydulbi

Editorial to special issue on hybrid artificial intelligence and machine learning technologies in intelligent systems

Hari Mohan Pandey, Nik Bessis, Swagtam Das, David Windridge, Ankit Chaudhary
2020 Neural computing & applications (Print)  
The article title ''A distant supervision method based on paradigmatic relations for learning word embeddings'' by Jianquan Li, Renfen Hu, Xiaokang Liu, Prayag Tiwari, Hari Mohan Pandey, Wei Chen, Benyou  ...  The article title ''Density-based semi-supervised online sequential extreme learning machine'' by Min Xia, Jie Wang, Jia Liu, Liguo Weng & Yiqing Xu, presents a novel semi-supervised online sequential  ... 
doi:10.1007/s00521-020-04903-w fatcat:of7n3duwija2taekrrnyznvxra

Cross-lingual Semantic Specialization via Lexical Relation Induction

Edoardo Maria Ponti, Ivan Vulić, Goran Glavaš, Roi Reichart, Anna Korhonen
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
Our results also suggest that the transfer method is effective even for lexically distant source-target language pairs.  ...  relation prediction model trained on the source language constraints.  ...  We thank the three anonymous reviewers for their helpful comments and suggestions.  ... 
doi:10.18653/v1/d19-1226 dblp:conf/emnlp/PontiVGRK19 fatcat:iik7yixa7nhqloszlj7mhhjqky

From Surrogacy to Adoption; From Bitcoin to Cryptocurrency: Debate Topic Expansion

Roy Bar-Haim, Dalia Krieger, Orith Toledo-Ronen, Lilach Edelstein, Yonatan Bilu, Alon Halfon, Yoav Katz, Amir Menczel, Ranit Aharonov, Noam Slonim
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
We introduce the task of Debate Topic Expansion -finding such related topics for a given debate topic, along with a novel annotated dataset for the task.  ...  We focus on relations between Wikipedia concepts, and show that they differ from well-studied lexical-semantic relations such as hypernyms, hyponyms and antonyms.  ...  Distant supervision for relation ex- traction without labeled data.  ... 
doi:10.18653/v1/p19-1094 dblp:conf/acl/Bar-HaimKTEBHKM19 fatcat:rewhq3nwsng7zk7z5pb3bqfopu

A Study of Various Text Augmentation Techniques for Relation Classification in Free Text

Praveen Giridhara, Chinmaya Mishra, Reddy Venkataramana, Syed Bukhari, Andreas Dengel
2019 Proceedings of the 8th International Conference on Pattern Recognition Applications and Methods  
We study the effect of various augmented datasets on the efficiency of different deep learning models for relation classification in text.  ...  In this paper, we explore various text data augmentation techniques in text space and word embedding space.  ...  DEEP LEARNING METHODS We have used two deep learning models namely; CNN and Attention-Based Bidirectional LSTM, for our experiments.  ... 
doi:10.5220/0007311003600367 dblp:conf/icpram/GiridharaMVBD19 fatcat:4l7qbyeogvgmzn4qslavxguoyu

Minimal Supervision for Morphological Inflection [article]

Omer Goldman, Reut Tsarfaty
2021 arXiv   pre-print
Our approach exploits different kinds of regularities in morphological systems in a two-phased setup, where word tagging based on analogies is followed by word pairing based on distances.  ...  In this work we aim to overcome this annotation bottleneck by bootstrapping labeled data from a seed as little as five labeled paradigms, accompanied by a large bulk of unlabeled text.  ...  Acknowledgements We thank Jonathan Berant for the helpful advice and discussion all throughout.  ... 
arXiv:2104.08512v2 fatcat:w35radyr4fgk7hvyifyr3jyow4

Survey of BERT-Base Models for Scientific Text Classification: COVID-19 Case Study

Mayara Khadhraoui, Hatem Bellaaj, Mehdi Ben Ammar, Habib Hamam, Mohamed Jmaiel
2022 Applied Sciences  
CovBERT relies on prior training on a large corpus of scientific publications in the biomedical domain and related to COVID-19 to increase its performance on the literature review task.  ...  To remedy this challenge, we are proposing CovBERT, a pre-trained language model based on the BERT model to automate the literature review process.  ...  Acknowledgments: The authors would like to thank Jihene Maatoug and Sihem Ben Fradj, members of the Epidemiology Department of CHU Farhat Hached, in Sousse, for their valuable cooperation and revision  ... 
doi:10.3390/app12062891 fatcat:pawbtru22rejrnmsjzw3t4imzy

Paradigm Completion for Derivational Morphology [article]

Ryan Cotterell, Ekaterina Vylomova, Huda Khayrallah, Christo Kirov and David Yarowsky
2017 arXiv   pre-print
We overview the theoretical motivation for a paradigmatic treatment of derivational morphology, and introduce the task of derivational paradigm completion as a parallel to inflectional paradigm completion  ...  State-of-the-art neural models, adapted from the inflection task, are able to learn a range of derivation patterns, and outperform a non-neural baseline by 16.4%.  ...  This material is based upon work supported in part by the Defense Advanced Research Projects Agency (DARPA) under Contract No. HR0011-15-C-0113.  ... 
arXiv:1708.09151v1 fatcat:6gv7bkznlrdixn67fzvteaqdoa

Fully-Unsupervised Embeddings-Based Hypernym Discovery

Maurizio Atzori, Simone Balloccu
2020 Information  
We also evaluate the algorithm on a new dataset to measure the improvements when finding hypernyms for sets of words instead of singletons.  ...  words if provided, allowing to find common hypernyms for a set of co-hyponyms—a task ignored in other systems but very useful when coupled with set expansion (that finds co-hyponyms automatically).  ...  [16] present a Chinese language framework for hypernym discovery, based on distant supervision.  ... 
doi:10.3390/info11050268 fatcat:rck4yyygubemvg2wysfj2lr2ti

Emergence of analogy from relation learning

Hongjing Lu, Ying Nian Wu, Keith J. Holyoak
2019 Proceedings of the National Academy of Sciences of the United States of America  
We have developed a computational model that exploits the potential synergy between deep learning from "big data" (to create semantic features for individual words) and supervised learning from "small  ...  for the two words in each pair.  ...  Preparation of this paper was supported by a Google Faculty Research Award and National Science Foundation Grant BCS-1827374 (to H.L. and K.J.H.).  ... 
doi:10.1073/pnas.1814779116 pmid:30770443 pmcid:PMC6410800 fatcat:iz73e4gvgrhwhomomuqnkdsvnu

Paradigm Completion for Derivational Morphology

Ryan Cotterell, Ekaterina Vylomova, Huda Khayrallah, Christo Kirov, David Yarowsky
2017 Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing  
We overview the theoretical motivation for a paradigmatic treatment of derivational morphology, and introduce the task of derivational paradigm completion as a parallel to inflectional paradigm completion  ...  State-of-the-art neural models, adapted from the inflection task, are able to learn a range of derivation patterns, and outperform a non-neural baseline by 16.4%.  ...  This material is based upon work supported in part by the Defense Advanced Research Projects Agency (DARPA) under Contract No. HR0011-15-C-0113.  ... 
doi:10.18653/v1/d17-1074 dblp:conf/emnlp/CotterellVKKY17 fatcat:3fktv2bw75fi7bobxdv3nv6b2i

Multi-SimLex: A Large-Scale Evaluation of Multilingual and Cross-Lingual Lexical Semantic Similarity [article]

Ivan Vulić, Simon Baker, Edoardo Maria Ponti, Ulla Petti, Ira Leviant, Kelly Wing, Olga Majewska, Eden Bar, Matt Malone, Thierry Poibeau, Roi Reichart, Anna Korhonen
2020 arXiv   pre-print
word embeddings (such as fastText, M-BERT and XLM), externally informed lexical representations, as well as fully unsupervised and (weakly) supervised cross-lingual word embeddings.  ...  Each language dataset is annotated for the lexical relation of semantic similarity and contains 1,888 semantically aligned concept pairs, providing a representative coverage of word classes (nouns, verbs  ...  Thierry Poibeau is partly supported by a PRAIRIE 3IA Institute fellowship ("Investissements d'avenir" program, reference ANR-19-P3IA-0001).  ... 
arXiv:2003.04866v1 fatcat:5mp5s7ehyzdshnywt2zvqverwu
« Previous Showing results 1 — 15 out of 2,224 results