Papers by Mayank Kulkarni

12 papers
MergeME: Model Merging Techniques for Homogeneous and Heterogeneous MoEs (2025.naacl-long)

Copied to clipboard

Challenge: State-of-the-art methods for merging expert models with different architectures do not address parameter interference and require extensive fine-tuning to restore performance.
Approach: They propose a method for merging experts with different architectures into a unified Mixture-of-Experts model with a goal of enhancing performance in each domain while retaining effectiveness on general tasks.
Outcome: Experiments across multiple domains show that the proposed methods reduce fine-tuning costs and improve performance over state-of-the-art methods.
EntSUM: A Data Set for Entity-Centric Extractive Summarization (2022.acl-long)

Copied to clipboard

Challenge: Existing methods for controllable summarization fail to generate entity-centric summaries.
Approach: They propose to use a human-annotated data set EntSUM to generate controllable summarization with a focus on named entities as the aspects to control.
Outcome: The proposed data set shows that existing methods fail to generate entity-centric summaries.
MASSIVE-Agents: A Benchmark for Multilingual Function-Calling in 52 Languages (2025.findings-emnlp)

Copied to clipboard

Challenge: Using the original dataset, we cleaned up the MASSIVE dataset and reformatted it for evaluation within the Berkeley Function-Calling Leaderboard framework.
Approach: They present a new benchmark for assessing multilingual function calling across 52 languages . they clean the original MASSIVE dataset and reformat it for evaluation .
Outcome: The new benchmark covers 55 functions and 286 arguments in 52 languages.
Learning Rich Representation of Keyphrases from Text (2022.findings-naacl)

Copied to clipboard

Challenge: Prior work has referred to extractive (part of document) or abstractive (not part of document).
Approach: They propose to use a new pre-training objective to introduce keyphrases into transformer language models in discriminative and generative settings.
Outcome: The proposed model improves performance in discriminative and generative settings and also improves on named entity recognition, question answering, relation extraction and abstractive summarization tasks.
Extractive Entity-Centric Summarization as Sentence Selection using Bi-Encoders (2022.aacl-short)

Copied to clipboard

Challenge: Entity-centric summarization is a type of controllable summarizing that aims to produce a summary specific to a given target entity.
Approach: They propose to recast a sentence selection task as a controllable summarization using a dataset supported by EntSUM.
Outcome: The proposed framework outperforms the current state-of-the-art in the sentence selection task and outperformed the competitive entity-centric Lead 3 heuristic by 1.1 F1.
Towards a Unified Multi-Domain Multilingual Named Entity Recognition Model (2023.eacl-main)

Copied to clipboard

Challenge: Named Entity Recognition is a key task whose performance is sensitive to genre and language.
Approach: They propose a setup for Named Entity Recognition which includes multi-domain and multilingual training and evaluation across 13 domains and 4 languages.
Outcome: The proposed model improves on 13 domains and 4 languages across 13 domain and 4 language domains.
Multi-Domain Named Entity Recognition with Genre-Aware and Agnostic Inference (2020.acl-main)

Copied to clipboard

Challenge: Named entity recognition (NER) is a key component of many text processing pipelines.
Approach: They propose a new architecture tailored to the task of identifying named entities with data from multiple genres.
Outcome: The proposed architecture outperforms baseline and competitive methods on all three setups with differences ranging between +1.95 to +3.11 average F1 across multiple genres when compared to standard approaches.
Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning (2023.findings-acl)

Copied to clipboard

Challenge: Existing methods to handle catastrophic forgetting fail to retain knowledge learnt in the past when sudden shifts occur in training data distributions.
Approach: They propose a learning rate scheduling method that preserves new information without strongly overwriting past knowledge.
Outcome: The proposed method preserves new information without overwriting past knowledge in a multilingual continuous learning framework.
Clustering-based Sampling for Few-Shot Cross-Domain Keyphrase Extraction (2024.findings-eacl)

Copied to clipboard

Challenge: Scientific domain-specific pre-training has led to state-of-the-art keyphrase extraction performance with a majority of benchmarks being within the domain.
Approach: They propose to leverage topic information available in the data to build a clustering-based sampling approach that facilitates selecting a few samples to label from the target domain .
Outcome: The proposed approach leads to 26.35 points in performance when compared to selecting few-shot samples uniformly at random.
An Empirical Analysis of Leveraging Knowledge for Low-Resource Task-Oriented Semantic Parsing (2023.findings-acl)

Copied to clipboard

Challenge: Task-oriented semantic parsing is a new approach to represent the meaning of user requests with arbitrarily nested semantics.
Approach: They propose to use knowledge-enhanced encoders to parse user requests with arbitrarily nested semantics.
Outcome: The proposed model improves performance in low-resource and low-compute settings.
Cross-lingual Few-Shot Learning on Unseen Languages (2022.aacl-main)

Copied to clipboard

Challenge: Large pre-trained language models have demonstrated the ability to obtain good performance on downstream tasks with limited examples in resource-rich languages.
Approach: They propose to use a downstream sentiment analysis task to analyze the effectiveness of several few-shot learning strategies across 12 languages, including 8 unseen languages, to compare results.
Outcome: The proposed model, XLM-R, gives the best performance on a task with few examples in resource-rich languages.
EntSUMv2: Dataset, Models and Evaluation for More Abstractive Entity-Centric Summarization (2023.emnlp-main)

Copied to clipboard

Challenge: Entity-centric summarization is a form of controllable summarizing that aims to generate a summary for a specific entity given a document.
Approach: They propose to use a more abstract version of the original entity-centric ENTSUM summarization dataset to generate a shorter annotated summary for downstream users.
Outcome: The proposed method is more abstract and uses supervised fine-tuning and large-scale instruction tuning to provide more specific and useful summaries for downstream users.

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