Research Publications

2024

66. BRECS: Enhanced Binary Representation of Word Embeddings via Cosine Similarity: R. Sarkar, S. Dutta and J. P. McCrae (ECAI).

65. Improved Out‑of‑Scope Intent Classification with Dual Encoding and Threshold‑based Re‑Classification: H. M. Zawbaa, S. Dutta and W. Rashwan (LREC-COLING). [paper]

64. Adapter-Based Contextualized Meta Embeddings: J. O'Neill and S. Dutta (IJCAI-GLOW).

63. VeNoM: Approximate Subgraph Matching with Enhanced Neighbourhood Structural Information: S. Agarwal, S. Dutta and A. Bhattacharya (CODS-COMAD). [paper]

2023

62. Self-Distilled Quantization: Achieving High Compression Rates in Transformer-Based Language Models: J. O’Neil and S. Dutta (ACL). [paper]

61. Improved Vector Quantization For Dense Retrieval with Contrastive Distillation: J. O’Neil and S. Dutta (SIGIR). [paper]

60. AdaSent: Efficient Domain-Adapted Sentence Embeddings for Few-Shot Classification: Y. Huang, K. Wang, S. Dutta, R. N. Patel, G. Glavas and I. Gurevych (EMNLP). [paper]

59. Gradient Sparsification for Masked Fine-Tuning of Transformers: J. O’Neil and S. Dutta (IJCNN). [paper]

58. Attention over pre-trained Sentence Embeddings for Long Document Classification: A. Abdaoui and S. Dutta (SIGIR-ReNeuIR).

57. Learning Fine-grained Search Space Pruning and Heuristics for Combinatorial Optimization: J. Lauri, S. Dutta, M. Grassia, and D. Ajwani (Journal of Heuristics). [paper]

56. Intent Classification by the use of Automatically Generated Knowledge Graphs: M. Arcan, S. Manjunath, C. Robin, G. Verma, D. Pillai, S. Sarkar, S. Dutta, H. Assem, J. P. McCrae, and P. Buitelaar (Information – Knowledge Graph Technology and its Applications II). [paper]

55. Learning of Cluster Centroids for Multi-Task Training in Information Retrieval: E. Burgin and S. Dutta (ECIR).

54. Attending to Entity Class Attributes for Named Entity Recognition with Few-Shot Learning: R. N. Patel, S. Dutta, and H. Assem (IntelliSys). [paper]

2022

53. Semantic Aware Answer Sentence Selection using Self-Learning based Domain Adaptation: R. Sarkar, S. Dutta, H. Assem, M. Arcan, and J. McCrae (KDD). [paper]

52. Aligned Weight Regularizers for Pruning Pretrained Neural Networks: J. O'Neil, S. Dutta, and H. Assem (ACL). [paper]

51. AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis: S. Kamila, W. Magdy, S. Dutta, and M. X. Wang (EMNLP). [paper]

50. Multi-Stage Framework with Refinement Based Point Set Registration for Unsupervised Bi-Lingual Word Alignment: S. V. Oprea, S. Dutta, and H. Assem (COLING). [paper]

49. CAGE: A Hybrid Framework for Closed-Domain Conversational Agents: E. Burgin, S. Dutta, H. Assem, and R. N. Patel (ECML-PKDD). [paper]

48. Self-Distilled Pruning of Neural Networks: J. O’ Neil, S. Dutta, and H. Assem (ECML-PKDD). [paper]

47. Enhanced Sentence Meta-Embeddings for Textual Understanding: S. Dutta and H. Assem (ECIR). [paper]

2021

46. The Cyborg Philharmonic: Synchronizing interactive musical performances between humans and machines: S. Chakraborty, S. Dutta, and J. Timoney (Nature). [paper]

45. DTAFA: Decoupled Training Architecture for Efficient FAQ Retrieval: H. Assem, S. Dutta, and E. Burgin (SIGDIAL). [paper]

44. Cross-lingual Sentence Embedding using Multi-Task Learning: K. Goswami, S. Dutta, H. Assem, T. Fransen and J. McCrae (EMNLP). [paper]

43. VerSaChI: Finding Statistically Significant Subgraph Matches using Chebyshev’s Inequality: S. Agarwal, S. Dutta and A. Bhattacharya (CIKM). [paper]

42. QASAR: Self-Supervised Learning Framework for Extractive Question Answering: H. Assem, R. Sarkar and S. Dutta (IEEE Big Data). [paper]

41. MUFIN: Enriching Semantic Understanding of Sentence Embedding using Dual Tune Framework: K. Goswami, S. Dutta  and H. Assem (IEEE Big Data). [paper]

40. Efficient Multi-Lingual Sentence Classification Framework with Sentence Meta Encoders: R. Patel, E. Burgin, H. Assem and S. Dutta (IEEE Big Data). [paper]

39. Categorizing Roles of Legal Texts via Sequence Tagging on Domain-Specific Language Models: S. Dutta (AILA-FIRE). [paper]

38. Sequence-to-Sequence Learning on Keywords for Efficient FAQ Retrieval: S. Dutta, H. .Assem, and E. Burgin (ASEA-IJCAI).  [paper]

37. “Alignment is All You Need”: Analyzing Cross-Lingual Text Similarity for Domain-Specific Applications: S. Dutta (CLEOPATRA-WWW). [paper] [video]

2020

36. ChiSeL: Graph Similarity Search using Chi-Squared Statistics in Large Probabilistic Graphs : S. Agarwal, S. Dutta and A. Bhattacharya (VLDB). [paper]

35. Towards Quantifying the Distance between Opinions : S. Gurukar, D. Ajwani, S. Dutta, J. Lauri, S. Parthasarathy and A. Sala (ICWSM). [paper]

34. RADAR: Fast Approximate Reverse Rank Queries : S. Dutta (IntelliSys). [paper]

2019

33. Fine-Grained Search Space Classification for Hard Enumeration Variants of Subset Problems : J. Lauri and S. Dutta (AAAI). [paper]

32. Finding a Maximum Clique in Dense Graphs via Chi-Square Statistics : S. Dutta and J. Lauri (CIKM). [paper]

31. Automated Assessment of Knowledge Hierarchy Evolution: Comparing Directed Acyclic Graphs : G. Nayak, S. Dutta, D. Ajwani, P. Nicholson and A. Sala (Transaction of IRJ). [paper]

30. A System for Analysis and Remediation of Attrition : N. Brockett, C. Clarke, M. Berlingerio and S. Dutta (IEEE Big Data). [paper]

29. Learning Multi-Stage Sparsification for Maximum Clique Enumeration : M. Grassia, J. Lauri, S. Dutta and D. Ajwani (IJCAI-DSO). [paper]

2018

28. Enriching Taxonomies with Functional Domain Knowledge : N. Vedula, P. K. Nicholson, D. Ajwani, S. Dutta, A. Sala, and S. Parthasarathy (SIGIR). [paper]

27. ANNOTATE: orgANizing uNstructured cOntenTs viA Topic labEls : D. Ajwani, B. Taneva, S. Dutta, P. K. Nicholson, G. Nobari and A. Sala (IEEE Big Data). [paper]

26. Efficient Auto-Generation of Taxonomies for Structured Knowledge Discovery and Organization: D. Ajwani, S. Dutta, P. K. Nicholson, L. M. Aiello, and A. Sala (Tutorial in HT). [paper]

25. Trade-offs in Social Media for Interpreting Unstructured Data : D. Ajwani, S. Dutta, P. K. Nicholson, A. Marascu, and A. Sala (Tutorial in ICWSM). [link]

24. Automated Knowledge Hierarchy Assessment : G. Nayak, S. Dutta, D. Ajwani, P. K. Nicholson, and A. Sala (SIGIR-KG4IR). [paper]

2017

23. Neighbor-Aware Search for Approximate Labeled Graph Matching using the Chi-Square Statistics : S. Dutta, P. Nayek, and A. Bhattacharya (WWW). [paper]

22. Efficient Knowledge Management for Named Entity from Text : S. Dutta (IEEE Intelligent Informatics Bulletin). [paper]

2016

21. KOGNAC: Efficient Encoding of Large Knowledge Graphs : J. Urbani, S. Dutta, S. Gurajada, and G. Weikum (IJCAI). [paper]

20. Credible Review Detection with Limited Information using Consistency Features : S. Mukherjee, S. Dutta and G. Weikum (ECML-PKDD). [paper]

19. Dynamic Uncertainty based Analytics for Caching Performance Improvements in 3G/4G Broadband Wireless Networks : S. Dutta and A. Narang (Book Chapter in "Big Data: Principles and Paradigms", Elsevier). [paper]

18. SONIK: Efficient In-situ All Item Rank Generation using Bit Operations : S. Dutta (WCSE). [paper]

2015

17. Unsupervised Rank Aggregation using Hierarchical User Similarity Clustering : S. Dutta (SCAI). [paper]

16. C3EL: A Joint Model for Cross-Document Co-Reference Resolution and Entity Linking : S. Dutta and G. Weikum (EMNLP). [paper]

15. Cross-Document Co-Reference Resolution using Sample-Based Clustering with Knowledge Enrichment : S. Dutta and G. Weikum (Transaction of ACL). [paper]

14. MIST: Top-k Approximate Sub-String Mining using Triplet Statistical Significance : S. Dutta (ECIR). [paper]

13. Predictive Caching Framework for Mobile Wireless Networks : S. Dutta, A. Narang, S. Bhattacherjee, A. S. Das, and D. Krishnaswamy (IEEE MDM). [paper]

12. Mining Wireless Intelligence using Unsupervised Edge and Core Analytics : S. Dutta, S. Bhattacherjee, and A. Narang (ICDCN-SPBDA).

11. Big & Deep Data Analytics using Statistical Significance: An Introductory Survey : S. Dutta (Data Analytics). [paper]

2014

10. Advanced Algorithms for Efficient Approximate Duplicate Detection in Data Streams Using Bloom Filters : S. Dutta and A. Narang (Book Chapter in "Large Scale and Big Data: Processing and Management", CRC Press). [paper]

2013

9. Streaming Quotient Filter: A Near Optimal Approximate Duplicate Detection Approach for Data Streams : S. Dutta, A. Narang, and S. K. Bera (VLDB). [paper]

2012

8. Towards "Intelligent Compression" in Streams: A Biased Reservoir Sampling based Bloom Filter Approach : S. Dutta, S. Bhattacherjee, and A. Narang (EDBT). [paper]

7. SmartScale: Automatic Application Scaling in Enterprise Clouds : S. Dutta, S. Gera, A. Verma, and B. Viswanathan (CLOUD). [paper]

6. CloudMap: Workload-aware Placement in Private Heterogeneous Clouds : B. Viswanathan, A. Verma, and S. Dutta (NOMS). [paper]

2011

5. Caching Stars in the Sky: A Semantic Caching Approach to Accelerate Skyline Queries : A. Bhattacharya, P. Teja, and S. Dutta (DEXA). [paper]

4. Mining Statistically Significant Substrings Based on the Chi-Square Measure : S. Dutta and A. Bhattacharya (Book Chapter in "Pattern Discovery and Sequence Mining: Applications and Studies" IGI-Global). [paper]

3. Service Deactivation Aware Placement and Defragmentation in Enterprise Clouds : S. Dutta and A. Verma (CNSM). [paper]

2010

2. Most Significant Substring Mining Based on Chi-Square Measure : S. Dutta and A. Bhattacharya (PAKDD). [paper]

1. INSTRUCT: Space-efficient structure for indexing and complete query management of string databases : S. Dutta and A. Bhattacharya (COMAD). [paper]