Sutanu Chakraborti
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Sutanu Chakraborti has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Deepak Padmanabhan
Queen’s University Belfast, Belfast, UK
4 shared publications - Adwait P. Parsodkar
Indian Institute of Technology, Madras
3 shared publications Aakash Srinivasan
Dept. of Computer Science University of California Los Angeles
1 shared publication- Abhijit Sahoo
Indian Institute of Technology
1 shared publication - Deepak Khemani
Department of CS&E, IIT Madras, Chennai, India
1 shared publication Devi Ganesan
Dept. of Computer Science and Engineering Indian Institute of Technology Madras
1 shared publication
Latest Publications
- 29 November 2024
- Published by Springer Nature
- p. 235-249
Navigating the Landscape of Case Fidelity and Competence in Case-Based Reasoning
- 29 November 2024
- Published by Springer Nature
- p. 235-249
Navigating the Landscape of Case Fidelity and Competence in Case-Based Reasoning
- 14 August 2022
- Published by Springer Nature
- p. 256-270
Never Judge a Case by Its (Unreliable) Neighbors: Estimating Case Reliability for CBR
- 14 August 2022
- Published by Springer Nature
- p. 256-270
Never Judge a Case by Its (Unreliable) Neighbors: Estimating Case Reliability for CBR
- Open Access
Integrating Lexical Knowledge in Word Embeddings using Sprinkling and Retrofitting
Neural network based word embeddings, such as Word2Vec and GloVe, are purely data driven in that they capture the distributional information about words from the training corpus. Past works have attempted to improve these embeddings by incorporating semantic knowledge from lexical resources like WordNet. Some techniques like retrofitting modify word embeddings in the post-processing stage while some others use a joint learning approach by modifying the objective function of neural networks. In this paper, we discuss two novel approaches for incorporating semantic knowledge into word embeddings. In the first approach, we take advantage of Levy et al's work which showed that using SVD based methods on co-occurrence matrix provide similar performance to neural network based embeddings. We propose a 'sprinkling' technique to add semantic relations to the co-occurrence matrix directly before factorization. In the second approach, WordNet similarity scores are used to improve the retrofitting method. We evaluate the proposed methods in both intrinsic and extrinsic tasks and observe significant improvements over the baselines in many of the datasets.
Open AccessIntegrating Lexical Knowledge in Word Embeddings using Sprinkling and Retrofitting
Neural network based word embeddings, such as Word2Vec and GloVe, are purely data driven in that they capture the distributional information about words from the training corpus. Past works have attempted to improve these embeddings by incorporating semantic knowledge from lexical resources like WordNet. Some techniques like retrofitting modify word embeddings in the post-processing stage while some others use a joint learning approach by modifying the objective function of neural networks. In this paper, we discuss two novel approaches for incorporating semantic knowledge into word embeddings. In the first approach, we take advantage of Levy et al's work which showed that using SVD based methods on co-occurrence matrix provide similar performance to neural network based embeddings. We propose a 'sprinkling' technique to add semantic relations to the co-occurrence matrix directly before factorization. In the second approach, WordNet similarity scores are used to improve the retrofitting method. We evaluate the proposed methods in both intrinsic and extrinsic tasks and observe significant improvements over the baselines in many of the datasets.
- 12 July 2017
- Published by SAGE Publications in AI Communications
- Vol. 30 (3-4) , 295-309
A generalized case competence model for casebase maintenance
A competence guided casebase maintenance algorithm retains a case in the casebase if it is useful to solve many problems and ensures that the casebase is highly competent. In this paper, a generalized case competence model is proposed for casebase ma
- 12 July 2017
- Published by SAGE Publications in AI Communications
- Vol. 30 (3-4) , 295-309
A generalized case competence model for casebase maintenance
A competence guided casebase maintenance algorithm retains a case in the casebase if it is useful to solve many problems and ensures that the casebase is highly competent. In this paper, a generalized case competence model is proposed for casebase ma
- 29 September 2016
- Published by Springer Nature
- p. 77-92
Eager to be Lazy: Towards a Complexity-guided Textual Case-Based Reasoning System
- 29 September 2016
- Published by Springer Nature
- p. 77-92
Eager to be Lazy: Towards a Complexity-guided Textual Case-Based Reasoning System
- 1 January 2015
- Published by Springer Nature
- p. 536-542
Adapting PageRank to Position Events in Time
- 1 January 2015
- Published by Springer Nature
- p. 1-11
Spreading Activation Way of Knowledge Integration