Papers by Kaustubh Dhole

9 papers
DUQGen: Effective Unsupervised Domain Adaptation of Neural Rankers by Diversifying Synthetic Query Generation (2024.naacl-long)

Copied to clipboard

Challenge: State-of-the-art rankers pre-trained on large task-specific training data such as MS-MARCO exhibit strong performance on various ranking tasks without domain adaptation, also called zero-shot.
Approach: They propose a method to generate unsupervised domain adaptation for ranking using large-scale task-specific training data such as MS-MARCO and Wikipedia retrieval.
Outcome: The proposed method outperforms all zero-shot baselines and significantly outperfies the SOTA baselines on 16 out of 18 datasets, for an average of 4% relative improvement across all datasets.
NusaCrowd: Open Source Initiative for Indonesian NLP Resources (2023.findings-acl)

Copied to clipboard

Challenge: Existing NLP research in Indonesian languages has been held back by factors such as language diversity, orthographic variation, resource limitation and other societal challenges.
Approach: They present a collaborative initiative to collect and unify existing resources for Indonesian languages and open access to previously non-public resources.
Outcome: The results show that the datasets are highly reliable and can be used to generate the first zero-shot benchmarks for natural language understanding and generation in Indonesian and the local languages of Indonesia.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code (2022.emnlp-demos)

Copied to clipboard

Challenge: Evaluations in machine learning rarely use the latest metrics, datasets, or human evaluation in favor of remaining compatible with prior work.
Approach: They propose to use the Generation, Evaluation, and Metrics Benchmark to integrate new evaluation methods into existing evaluations.
Outcome: The proposed evaluation infrastructure bridges the gap between the advantages of leaderboards and in-depth and evolving evaluations by allowing model developers to benefit from each other's work.
Saying No is An Art: Contextualized Fallback Responses for Unanswerable Dialogue Queries (2021.acl-short)

Copied to clipboard

Challenge: despite advances in task-oriented and chit-chat based dialogue systems, many systems rely on static and unnatural responses.
Approach: They propose a neural approach which generates contextually aware responses to user queries . they perform automatic and manual evaluations to demonstrate the efficacy of the system .
Outcome: The proposed approach generates responses which are contextually aware with the user query and say no to the user.
Generative Product Recommendations for Implicit Superlative Queries (2025.naacl-srw)

Copied to clipboard

Challenge: Existing retrieval and ranking systems struggle with implicit superlative queries . lack of explicit attribute mentions and complexity of the query complicates ranking .
Approach: They propose a four-point schema for annotating the best product candidates for superlative queries . they propose pointwise, deliberated pointwise and pairwise methods to analyze the results .
Outcome: The proposed schema can be used to rank products with implicit attributes and reason over them.
QueryExplorer: An Interactive Query Generation Assistant for Search and Exploration (2024.naacl-demo)

Copied to clipboard

Challenge: Formulating effective search queries can be a daunting task for users when they lack expertise in a specific domain or are not proficient in the language of the content.
Approach: QueryExplorer is an interactive query generation, reformulation, and retrieval interface with support for Hug-gingFace generation models and PyTerrier’sretrieval pipelines and datasets.
Outcome: QueryExplorer is an interactive query generation, reformulation, and retrieval interface with support for Hug-gingFace generation models and PyTerrier’sretrieval pipelines and datasets, and extensivelogging of human feedback.
ConQRet: A New Benchmark for Fine-Grained Automatic Evaluation of Retrieval Augmented Computational Argumentation (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for evaluating RAArg are costly and lack long, complex arguments and real-world evidence.
Approach: They propose to use multiple fine-grained LLM judges to evaluate RAArg using a new benchmark that features long and complex human-authored arguments on debated topics.
Outcome: The proposed methods provide better and more interpretable assessments than traditional single-score metrics and even previously reported human crowdsourcing.
Syn-QG: Syntactic and Shallow Semantic Rules for Question Generation (2020.acl-main)

Copied to clipboard

Challenge: Question Generation is a simple syntactic transformation but many aspects of semantics influence what questions are good to form.
Approach: They propose a set of syntactic rules which transform declarative sentences into question-answer pairs.
Outcome: The proposed system generates a larger number of highly grammatical and relevant questions than existing QG systems.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations