Papers by Indrajit Bhattacharya
RetinaQA: A Robust Knowledge Base Question Answering Model for both Answerable and Unanswerable Questions (2024.acl-long)
Copied to clipboard
| Challenge: | Existing knowledge base question answering models assume all questions to be answerable. |
| Approach: | They propose a new KBQA model that unifies two key ideas in a single architecture . they propose logical form discrimination and sketch-filling-based construction for unanswerable questions . |
| Outcome: | The proposed model outperforms existing models in handling answerable and unanswerable questions. |
Do I have the Knowledge to Answer? Investigating Answerability of Knowledge Base Questions (2023.acl-long)
Copied to clipboard
| Challenge: | missing facts, incomplete schema and limited scope lead to many questions being unanswerable. |
| Approach: | They propose to adapt a KBQA dataset with unanswerable questions to detect missing facts and incomplete schema. |
| Outcome: | The proposed model performs poorly even after adaptation for unanswerable questions. |
Few-shot Transfer Learning for Knowledge Base Question Answering: Fusing Supervised Models with In-Context Learning (2024.acl-long)
Copied to clipboard
| Challenge: | Existing Knowledge Base Question Answering (KBQA) architectures are expensive and time-consuming to deploy. |
| Approach: | They propose a KBQA architecture that performs KB-retrieval using multiple source-trained retrievers and re-ranks using an LLM. |
| Outcome: | The proposed architecture outperforms adaptations of SoTA KBQA models when training data is limited. |
A Weak Supervision Approach for Predicting Difficulty of Technical Interview Questions (2022.coling-1)
Copied to clipboard
| Challenge: | Existing models require large volumes of candidate response data to train . Existing approaches require large amounts of candidate data to generate questions and generate models. |
| Approach: | They create a dataset of interview questions with difficulty scores for deep learning and use it to evaluate SOTA models trained using weak supervision. |
| Outcome: | The proposed model improves the difficulty and promise of weak supervision for interview questions and identifies the potential for weak supervision. |
Iterative Repair with Weak Verifiers for Few-shot Transfer in KBQA with Unanswerability (2025.findings-acl)
Copied to clipboard
| Challenge: | Existing models for KBQA with unanswerable questions are inadequate for real-world applications. |
| Approach: | They propose a task of few-shot transfer for KBQA with unanswerable questions that extends FuSIC-KBQA to include feedback for unanswered questions. |
| Outcome: | The proposed model outperforms suitable adaptations of multiple LLM-based and supervised SoTA models on the task while establishing a new performance for answerable few-shot transfer as well. |
Generating An Optimal Interview Question Plan Using A Knowledge Graph And Integer Linear Programming (2021.naacl-main)
Copied to clipboard
| Challenge: | a large multi-national IT company added roughly 70,000 employees in FY2018-19. |
| Approach: | They propose an interview assistant system to automatically select an optimal set of technical questions personalized for a candidate. |
| Outcome: | The proposed system can help human interviewers plan for an upcoming interview of that candidate. |
Complex Question Answering on knowledge graphs using machine translation and multi-task learning (2021.eacl-main)
Copied to clipboard
Saurabh Srivastava, Mayur Patidar, Sudip Chowdhury, Puneet Agarwal, Indrajit Bhattacharya, Gautam Shroff
| Challenge: | Existing approaches to question answering on knowledge graphs are based on a modularized sequential approach where errors in one module lead to the accumulation of errors in downstream modules. |
| Approach: | They propose a multi-task BERT based Neural Machine Translation model to address these challenges. |
| Outcome: | The proposed model can answer questions over a knowledge graph on one publicly available and one proprietary dataset. |
Joint Learning of Representations for Web-tables, Entities and Types using Graph Convolutional Network (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing approaches for table annotation with entities and types capture the syntactic structure of tables using graphical models or learn embeddings of table entries without accounting for the complete syntaktic structure. |
| Approach: | They propose a Graph Convolutional Network that captures the complete structure of tables, knowledge graph and the training annotations and jointly learns embeddings for table elements as well as the entities and types. |
| Outcome: | The proposed model significantly outperforms state-of-the-art methods on 5 benchmark datasets while showing promising performance on downstream table-related applications. |