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 • COLING 2022 • Arpita Kundu, Subhasish Ghosh, Pratik Saini, Tapas Nayak, Indrajit Bhattacharya
Predicting difficulty of questions is crucial for technical interviews.
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 • 26 Nov 2018 • Aishwarya Chhabra, Pratik Saini, Amit Sangroya, C. Anantaram
Our latent belief identification approach shows an accuracy of 87% and this results in efficient and meaningful dialog management.