Papers by Ananjan Nandi

4 papers
Sneaking Syntax into Transformer Language Models with Tree Regularization (2025.naacl-long)

Copied to clipboard

Challenge: Existing methods for incorporating syntactic inductive biases into transformers are limited . we introduce auxiliary loss function that converts bracketing decisions into differentiable orthogonality constraints on vector hidden states.
Approach: They propose to introduce syntactic inductive biases into transformer circuits through a structured regularizer.
Outcome: The proposed approach could unlock more robust and data-efficient learning in transformer language models . it integrates seamlessly with the standard LM objective, requiring no architectural changes.
Simple Augmentations of Logical Rules for Neuro-Symbolic Knowledge Graph Completion (2023.acl-short)

Copied to clipboard

Challenge: Recent studies show that high-quality rule sets struggle with high coverage.
Approach: They propose three simple augmentations to existing rule sets to improve results . they propose transforming rules to their abductive forms and generating equivalent rules that use inverse forms of constituent relations .
Outcome: The proposed methods achieve up to 7.1 pt MRR and 8.5 pT Hits@1 gains over using rules without augmentations.
Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles (2024.emnlp-main)

Copied to clipboard

Challenge: Existing methods for improving LLMs in simulations are limited due to privacy concerns and limited domain knowledge.
Approach: They propose a pipeline that elicits qualitative feedback from a domain-expert and transforms it into a set of principles that govern an LLM-prompted roleplay.
Outcome: The proposed pipeline shows a 30% improvement in response quality and principle following for the downstream task.
DynaSemble: Dynamic Ensembling of Textual and Structure-Based Models for Knowledge Graph Completion (2024.acl-short)

Copied to clipboard

Challenge: Existing approaches to Knowledge Graph Completion use textual descriptions of the KG entities and relations to perform the task.
Approach: They propose a method to combine two popular approaches to Knowledge Graph Completion . structure-based models perform better when gold answer is easily reachable . textual models exploit textual descriptions to give good performance .
Outcome: The proposed method achieves 6.8 pt MRR and 8.3 pTits@1 gains over the best baseline model for WN18RR dataset.

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