no code implementations • 3 Apr 2024 • Abhijit Anand, Venktesh V, Vinay Setty, Avishek Anand
In our extensive experiments on the DL-Hard dataset, we find that a principled query performance based scoring method using base and specialized ranker offers a significant improvement of up to 25% on the passage ranking task and up to 48. 4% on the document ranking task when compared to the baseline performance of using original queries, even outperforming SOTA model.
1 code implementation • 25 Mar 2024 • Venktesh V, Abhijit Anand, Avishek Anand, Vinay Setty
This addresses the challenge of verifying real-world numerical claims, which are complex and often lack precise information, not addressed by existing works that mainly focus on synthetic claims.
no code implementations • 26 Oct 2023 • Venktesh V, Sourangshu Bhattacharya, Avishek Anand
We transfer the ability to decompose complex questions to simpler questions or generate step-by-step rationales to LLMs, by careful selection from available data sources of related tasks.
no code implementations • 31 Aug 2023 • Abhijit Anand, Venktesh V, Vinay Setty, Avishek Anand
We find that there are two inherent limitations of using LLMs as query re-writers -- concept drift when using only queries as prompts and large inference costs during query processing.
no code implementations • 3 Jul 2023 • Mayank Goel, Venktesh V, Vikram Goyal
Math Word Problems (MWPs) in online assessments help test the ability of the learner to make critical inferences by interpreting the linguistic information in them.
no code implementations • 28 Jun 2023 • Avishek Anand, Venktesh V, Abhijit Anand, Vinay Setty
Querying, conversing, and controlling search and information-seeking interfaces using natural language are fast becoming ubiquitous with the rise and adoption of large-language models (LLM).
no code implementations • 1 Jun 2023 • Arun Balajiee Lekshmi Narayanan, Rully Agus Hendrawan, Venktesh V
Digital textbooks have become an integral part of everyday learning tasks.
no code implementations • 20 Dec 2022 • Maksimjeet Chowdhary, Sanyam Goyal, Venktesh V, Mukesh Mohania, Vikram Goyal
The repository of questions has to be constantly updated to ensure a diverse pool of questions to conduct assessments for learners.
1 code implementation • 16 Jun 2022 • Rishabh Gupta, Venktesh V, Mukesh Mohania, Vikram Goyal
There is a need for paraphrase scoring methods in the context of AWP to enable the training of good paraphrasers.
no code implementations • 25 May 2022 • Aarish Chhabra, Nandini Bansal, Venktesh V, Mukesh Mohania, Deep Dwivedi
Exams are conducted to test the learner's understanding of the subject.
1 code implementation • 24 May 2022 • Vasu Goel, Dhruv Sahnan, Venktesh V, Gaurav Sharma, Deep Dwivedi, Mukesh Mohania
However, there has not been a model specifically adapted for the education domain (particularly K-12) across subjects to the best of our knowledge.
no code implementations • 24 May 2022 • Venktesh V, Md. Shad Akhtar, Mukesh Mohania, Vikram Goyal
Hence we soft label another dataset with a model fine-tuned to predict Bloom's labels to demonstrate the applicability of our method to datasets with only difficulty labels.
1 code implementation • 17 Jan 2022 • Venktesh V, Mukesh Mohania, Vikram Goyal
The salient phrases are extracted using a ranking algorithm on an undirected graph constructed for the given document.
1 code implementation • 3 Jul 2021 • Venktesh V, Mukesh Mohania, Vikram Goyal
The loss function maximizes the similarity between the question-answer pair and the correct label representations and minimizes the similarity to unrelated labels.
Ranked #1 on Question-Answer categorization on QC-Science
Multi-class Classification Question-Answer categorization +1
no code implementations • 12 Jan 2021 • Akansha Gautam, Venktesh V, Sarah Masud
One such research contribution came in the form of the Constraint@AAA12021 Shared Task on COVID19 Fake News Detection in English.