ProTIP: Progressive Tool Retrieval Improves Planning

no code implementations • 16 Dec 2023 • Raviteja Anantha, Bortik Bandyopadhyay, Anirudh Kashi, Sayantan Mahinder, Andrew W Hill, Srinivas Chappidi

Large language models (LLMs) are increasingly employed for complex multi-step planning tasks, where the tool retrieval (TR) step is crucial for achieving successful outcomes.

Contrastive Learning Retrieval

Understanding Knowledge Gaps in Visual Question Answering: Implications for Gap Identification and Testing

no code implementations • 8 Apr 2020 • Goonmeet Bajaj, Bortik Bandyopadhyay, Daniel Schmidt, Pranav Maneriker, Christopher Myers, Srinivasan Parthasarathy

After identifying KGs for each question, we examine the skew in the distribution of questions for each KG.

Question Answering Question Generation +3

Automatic Table completion using Knowledge Base

no code implementations • 20 Sep 2019 • Bortik Bandyopadhyay, Xiang Deng, Goonmeet Bajaj, Huan Sun, Srinivasan Parthasarathy

In this work, we propose to resolve a new type of heterogeneous query viz: tabular query, which contains a natural language query description, column names of the desired table, and an example row.

Decision Making

ATP: Directed Graph Embedding with Asymmetric Transitivity Preservation

1 code implementation • 2 Nov 2018 • Jiankai Sun, Bortik Bandyopadhyay, Armin Bashizade, Jiongqian Liang, P. Sadayappan, Srinivasan Parthasarathy

Directed graphs have been widely used in Community Question Answering services (CQAs) to model asymmetric relationships among different types of nodes in CQA graphs, e. g., question, answer, user.

Community Question Answering Graph Embedding +1

Cognitive Database: A Step towards Endowing Relational Databases with Artificial Intelligence Capabilities

no code implementations • 19 Dec 2017 • Rajesh Bordawekar, Bortik Bandyopadhyay, Oded Shmueli

We propose Cognitive Databases, an approach for transparently enabling Artificial Intelligence (AI) capabilities in relational databases.