Capturing Discriminative Attributes on Text Representation Learning
Authors: 
Basit Ali, Muhammad RafiAuthors Info & Claims
Basit Ali, Muhammad RafiAuthors Info & ClaimsArticle No.: 68, Pages 1 - 5
Abstract
Semantic representation for natural language text is an active area of research in many realms of Information retrieval, natural language processing, and machine learning. Semantic models based on similarity are common to bridge the semantic gap in representation. These model do capture the one-way sense of similarity but for a better understanding of the text in a semantic context, a discriminating criterion is also important. Some very similar objects may have some peculiar differences that enable human for better understanding, using the same motivation an automatic extraction of these differences and enable them for semantically defining the relationship is vital for semantic models. In this work, we propose an approach to the automatic extraction of discriminating attribute(s) for a pair of terms, in order to contrast and augment the semantic model. Semantic model with discriminative power can be very useful in many applications.
References
[1]
Amos Tversky. Features of similarity. Psychological review, 84(4):327, 1977.
[2]
Ali Farhadi, Ian Endres, Derek Hoiem, and David Forsyth. Describing objects by their attributes. In Computer Vision and Pattern Recognition, 2009. CVPR 2009. IEEE Conference on, pages 1778{1785. IEEE, 2009.
[3]
Tiee-Jian Wu, Ya-Ching Hsieh, and Lung-An Li. Statistical measures of DNA sequence dissimilarity under markov chain models of base composition. Biometrics, 57(2):441{448, 2001.
[4]
Alicia Krebs and Denis Paperno. Capturing discriminative attributes in a distributional space: Task proposal. In Proceedings of the 1st Workshop on Evaluating Vector-Space Representations for NLP, pages 51{54, 2016.
[5]
Maxim Grishin. Similarity-based method for capturing discriminative attributes.
[6]
Huajie Jiang, Ruiping Wang, Shiguang Shan, Yi Yang, and Xilin Chen. Learning discriminative latent attributes for zero-shot classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 4223{4232, 2017.
[7]
Meng Ye and Yuhong Guo. Zero-shot classification with discriminative semantic representation learning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 7140{7148, 2017.
[8]
Muhammad Rafi, M Shahid Shaikh, and Amir Farooq. Document clustering based on topic maps. arXiv preprint arXiv:1112.6219, 2011.
[9]
Marc Moreno Lopez and Jugal Kalita. Deep learning applied to nlp. arXiv preprint arXiv:1703.03091, 2017.
[10]
Ye Zhang, Matthew Lease, and Byron C Wallace. Active discriminative text representation learning. In AAAI, pages 3386{3392, 2017.
[11]
Chuhan Wu, Fangzhao Wu, Zhigang Yuan, Sixing Wu, and Yongfeng Huang. Thu ngn at semeval-2018 task10:Capturing discriminative attributes with mlp-cnn model.
[12]
Angeliki Lazaridou, Marco Baroni, et al. The red one!: On learning to refer to things based on discriminative properties. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), volume 2, pages 213{218, 2016.
[13]
Khurum Nazir Junejo and Asim Karim. A robust discriminative term weighting based linear discriminant method for text classification. In Data Mining, 2008. ICDM'08. Eighth IEEE International Conference on, pages 323{332. IEEE, 2008.
[14]
Khurum Nazir Junejo, Asim Karim, Malik Tahir Hassan, and Moongu Jeon. Terms-based discriminative information space for robust text classification. Information Sciences, 372:518{538, 2016.
[15]
Muhammad Rafi, Farnaz Amin, and Mohammad Shahid Shaikh. Document clustering using graph based document representation with constraints. arXiv preprint arXiv:1412.1888, 2014.
[16]
Manaal Faruqui, Yulia Tsvetkov, Pushpendre Rastogi, and Chris Dyer. Problems with evaluation of word embeddings using word similarity tasks. arXiv preprint arXiv:1605.02276, 2016.
[17]
Masataka Ono, Makoto Miwa, and Yutaka Sasaki. Word embedding-based antonym detection using thesauri and distributional information. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 984{989, 2015.
[18]
Zhigang Chen, Wei Lin, Qian Chen, Xiaoping Chen, Si Wei, Hui Jiang, and Xiaodan Zhu. Revisiting word embedding for contrasting meaning. In 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), volume 1, pages 106{115, 2015.
[19]
Robert Speer and Joanna Lowry-Duda. Conceptnet at semeval-2017 task 2: Extending word embeddings with multilingual relational knowledge. arXiv preprint arXiv:1704.03560, 2017.
[20]
Enrico Santus, Chris Biemann, and Emmanuele Chersoni. Bomji at semeval-2018 task 10: Combining vector-, pattern-and graph-based information to identify discriminative attributes. arXiv preprint arXiv:1804.11251, 2018.
Index Terms
- Capturing Discriminative Attributes on Text Representation Learning
Recommendations
Unsupervised Cross-Lingual Sentence Representation Learning via Linguistic Isomorphism
Knowledge Science, Engineering and ManagementAbstractRecently, many researches on learning cross-lingual word embeddings without parallel data have achieved success by utilizing word isomorphism among languages. However, unsupervised cross-lingual sentence representation, which aims to learn a ...
Focus Set Semantic Differences
K-CAP '23: Proceedings of the 12th Knowledge Capture Conference 2023Ontologies are being utilized widely as sources for formally organized information in a range of fields. The SNOMED CT ontology is a key resource in national and international health sectors for automatically linking information captured by diverse ...
Unsupervised learning of semantic relations of a morphologically rich language
Use of semantic concepts and relations for NLP applications including information retrieval and web search is a major area of research. In this context, semantic relation extraction from open domain web documents is important not only for English but ...
Comments
Information & Contributors
Information
Published In
December 2018
460 pages
ISBN:9781450366250
DOI:10.1145/3302425
Copyright © 2018 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]
In-Cooperation
- The Hong Kong Polytechnic: The Hong Kong Polytechnic University
- City University of Hong Kong: City University of Hong Kong
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 21 December 2018
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
ACAI 2018
ACAI 2018: 2018 International Conference on Algorithms, Computing and Artificial Intelligence
December 21 - 23, 2018
Sanya, China
Acceptance Rates
ACAI '18 Paper Acceptance Rate 76 of 192 submissions, 40%;
Overall Acceptance Rate 173 of 395 submissions, 44%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 73Total Downloads
- Downloads (Last 12 months)2
- Downloads (Last 6 weeks)0
Reflects downloads up to 08 Mar 2025
Other Metrics
Citations
View Options
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in