no code implementations • PANDL (COLING) 2022 • Indrajit Bhattacharya, Subhasish Ghosh, Arpita Kundu, Pratik Saini, Tapas Nayak
Semi-structured metadata of a textbook — the table of contents and the index — provide rich cues for technical question generation.
no code implementations • SIGDIAL (ACL) 2020 • Subhasis Ghosh, Arpita Kundu, Aniket Pramanick, Indrajit Bhattacharya
For such mini-dialogs with response uncertainty, we propose a dialog strategy that looks to elicit the schema over as short a dialog as possible.
no code implementations • COLING 2022 • Arpita Kundu, Subhasish Ghosh, Pratik Saini, Tapas Nayak, Indrajit Bhattacharya
Predicting difficulty of questions is crucial for technical interviews.
no code implementations • 16 Mar 2024 • Prayushi Faldu, Indrajit Bhattacharya, Mausam
We propose a new model for KBQA named RetinaQA that is robust against unaswerability.
no code implementations • 15 Nov 2023 • Mayur Patidar, Riya Sawhney, Avinash Singh, Biswajit Chatterjee, Mausam, Indrajit Bhattacharya
Additional experiments in the in-domain setting show that FuSIC-KBQA also outperforms SoTA KBQA models when training data is limited.
no code implementations • 6 Nov 2023 • Prabir Mallick, Tapas Nayak, Indrajit Bhattacharya
Pre-trained Generative models such as BART, T5, etc.
Extractive Question-Answering Long Form Question Answering +1
no code implementations • 1 Oct 2023 • Pratik Saini, Tapas Nayak, Indrajit Bhattacharya
Joint models, which capture interactions across triples, are the more recent development, and have been shown to outperform pipeline models for sentence-level extraction tasks.
no code implementations • 20 Feb 2023 • Pratik Saini, Samiran Pal, Tapas Nayak, Indrajit Bhattacharya
This approach leads to overall performance improvement in these models within the realistic experimental setting.
Ranked #11 on Relation Extraction on NYT
no code implementations • 20 Dec 2022 • Mayur Patidar, Prayushi Faldu, Avinash Singh, Lovekesh Vig, Indrajit Bhattacharya, Mausam
When answering natural language questions over knowledge bases, missing facts, incomplete schema and limited scope naturally lead to many questions being unanswerable.
no code implementations • NAACL 2021 • Soham Datta, Prabir Mallick, Sangameshwar Patil, Indrajit Bhattacharya, Girish Palshikar
Given the diversity of the candidates and complexity of job requirements, and since interviewing is an inherently subjective process, it is an important task to ensure consistent, uniform, efficient and objective interviews that result in high quality recruitment.
no code implementations • EACL 2021 • Aniket Pramanick, Indrajit Bhattacharya
Existing approaches for table annotation with entities and types either capture the structure of table using graphical models, or learn embeddings of table entries without accounting for the complete syntactic structure.
no code implementations • EACL 2021 • Saurabh Srivastava, Mayur Patidar, Sudip Chowdhury, Puneet Agarwal, Indrajit Bhattacharya, Gautam Shroff
Question answering (QA) over a knowledge graph (KG) is a task of answering a natural language (NL) query using the information stored in KG.
no code implementations • 23 Aug 2020 • Pradip Pramanick, Chayan Sarkar, Balamuralidhar P, Ajay Kattepur, Indrajit Bhattacharya, Arpan Pal
In this work, we provide a non-trivial method to combine an NLP engine and a planner such that a robot can successfully identify tasks and all the relevant parameters and generate an accurate plan for the task.
no code implementations • 12 Sep 2018 • Srikanta Bedathur, Indrajit Bhattacharya, Jayesh Choudhari, Anirban Dasgupta
We show using experiments on real and semi-synthetic data that HMHP is able to generalize better and recover the network strengths, topics and diffusion paths more accurately than state-of-the-art baselines.
no code implementations • EACL 2017 • Roy Bar-Haim, Indrajit Bhattacharya, Francesco Dinuzzo, Amrita Saha, Noam Slonim
Recent work has addressed the problem of detecting relevant claims for a given controversial topic.
no code implementations • 26 Aug 2015 • Lavanya Sita Tekumalla, Priyanka Agrawal, Indrajit Bhattacharya
The Hierarchical Dirichlet Process (HDP), is an extension of DP for grouped data, often used for non-parametric topic modeling, where each group is a mixture over shared mixture densities.
no code implementations • 3 Dec 2013 • Sneha Chaudhari, Pankaj Dayama, Vinayaka Pandit, Indrajit Bhattacharya
Arising in the context of two rather disparate applications- banking and medical diagnosis, we pose the active information acquisition problem as a constrained optimization problem.