Papers by Harish Tayyar Madabushi

15 papers
Pre-Trained Language Models Represent Some Geographic Populations Better than Others (2024.lrec-main)

Copied to clipboard

Challenge: Existing studies have focused on measuring the degree to which pre-trained language models capture purely linguistic knowledge and reasoning abilities and world knowledge.
Approach: They use geography to demarcate different populations around the world and comparable corpora to measure how well two families of LLMs perform across these different populations.
Outcome: The results show that pre-trained models perform better for some populations than others.
CxGBERT: BERT meets Construction Grammar (2020.coling-main)

Copied to clipboard

Challenge: lexico-semantic elements capture a large amount of linguistic information, but they do not capture all information contained in text.
Approach: They propose to use BERT to train a model that uses a deep bidirectional transformer to capture a significant amount of lexico-semantic information.
Outcome: The proposed model captures lexico-semantic information, but it is redundantly encoded in lexical information.
Are Emergent Abilities in Large Language Models just In-Context Learning? (2024.acl-long)

Copied to clipboard

Challenge: Large language models have been claimed to acquire certain capabilities without having been specifically trained on them.
Approach: They propose a theory that explains emergent abilities by taking into account their potential confounding factors and rigorously substantiate this theory through over 1000 experiments.
Outcome: The proposed theory proves that emergent abilities are not truly emergental, but result from a combination of in-context learning, model memory, and linguistic knowledge.
Multi-class Hierarchical Question Classification for Multiple Choice Science Exams (2020.lrec-1)

Copied to clipboard

Challenge: Prior work has demonstrated that question classification (QC) can help answer a question more accurately.
Approach: They propose to use a large dataset for question classification (QC) that contains 7,787 science exam questions paired with detailed classification labels from a fine-grained hierarchical taxonomy of 406 problem domains to train a BERT-based model.
Outcome: The proposed model achieves a large (+0.12 MAP) gain while also achieving state-of-the-art performance on benchmark open-domain and biomedical QC datasets.
A Construction Grammar Corpus of Varying Schematicity: A Dataset for the Evaluation of Abstractions in Language Models (2024.lrec-main)

Copied to clipboard

Challenge: Large Language Models (LLMs) have been developed without a theoretical framework . evaluating and improving LLMs will benefit from theoretical frameworks that enable comparison of structures of human language and model of language built up by LLM.
Approach: They propose to use a construction grammar schema corpus to compare human grammar to LLMs' model of language.
Outcome: The proposed corpus shows that even the largest LLMs are limited to more substantive constructions and do not recognize similarity of purely schematic constructions.
AStitchInLanguageModels: Dataset and Methods for the Exploration of Idiomaticity in Pre-Trained Language Models (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing datasets are limited to providing the degree of idiomaticity of expressions along with the literal and, where applicable, (a single) non-literal interpretation of MWEs.
Approach: They propose to use a dataset to test the effectiveness of a language model in generating representations of sentences containing idioms.
Outcome: The proposed model performs reasonably well on the one-shot and few-shot scenarios, but there is scope for improvement in the zero-shot scenario.
Fine-Tuning on Diverse Reasoning Chains Drives Within-Inference CoT Refinement in LLMs (2025.acl-long)

Copied to clipboard

Challenge: Existing approaches to generate multiple independent CoTs, combining them through ensembling or other post-hoc strategies, have been shown to be effective in boosting performance.
Approach: They propose a method where LLMs are fine-tuned to generate a sequence of Diverse Chains of Thought (DCoT) within a single inference step.
Outcome: The proposed model can generate multiple chains of thought within a single inference step without external feedback.
Code-Mixed Probes Show How Pre-Trained Models Generalise on Code-Switched Text (2024.lrec-main)

Copied to clipboard

Challenge: Code-switching is a prevalent linguistic phenomenon in which multilingual individuals seamlessly alternate between languages.
Approach: They propose to use pre-trained language models to generalise to code-switched text . they use a dataset of well-formed naturalistic code-witched texts and parallel translations into the source languages to examine their results.
Outcome: The proposed model generalises to code-switched text, shedding light on their ability to generalise representations to CS corpora.
Improving Tokenisation by Alternative Treatment of Spaces (2022.emnlp-main)

Copied to clipboard

Challenge: Subword tokenisation is a key initial step in processing natural language . it uses a number of different methods to tokenise text, including a stringsearching technique and a word-matching technique.
Approach: They propose to use a vocabulary-based approach to tokenise text using a numerical ID and a mathematical function to manipulate it.
Outcome: The method is based on a set of training data and learning from it to build a vocabulary and tokenise it at inference time using this vocabulary and learnt parameters.
Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data (D19-50)

Copied to clipboard

Challenge: Popular NLP tasks such as sentiment analysis and event extraction from social media are examples of imbalanced classification problems.
Approach: They propose a method to generalise on dissimilar training and test data using a measure of similarity between datasets.
Outcome: The proposed method achieves the second highest score on sentence-level propaganda classification.
SpeciaLex: A Benchmark for In-Context Specialized Lexicon Learning (2024.findings-emnlp)

Copied to clipboard

Challenge: Specialized lexicons are collections of words with associated constraints such as special definitions, specific roles, and intended target audiences.
Approach: They propose a benchmark to evaluate a language model’s ability to follow specialized lexicon-based constraints across 18 diverse subtasks with 1,785 test instances covering core tasks of Checking, Identification, Rewriting, and Open Generation.
Outcome: The proposed model can follow specialized lexicon-based constraints across 18 diverse subtasks with 1,785 test instances covering core tasks Checking, Identification, Rewriting, and Open Generation.
Standardize: Aligning Language Models with Expert-Defined Standards for Content Generation (2024.emnlp-main)

Copied to clipboard

Challenge: Domain experts in engineering, healthcare, and education follow strict standards for producing quality content.
Approach: They propose a retrieval-style in-context learning-based framework to guide large language models to align with expert-defined standards.
Outcome: The proposed framework shows that models can gain 45% to 100% increase in precise accuracy across open and commercial LLMs evaluated.
UniversalCEFR: Enabling Open Multilingual Research on Language Proficiency Assessment (2025.emnlp-main)

Copied to clipboard

Challenge: Language proficiency research plays a central role in education and often intersects with advances in linguistics and AI.
Approach: They propose a multilingual multidimensional dataset of texts annotated according to the CEFR scale in 13 languages.
Outcome: The proposed dataset supports linguistic features and pretrained models in multilingual CEFR level assessment.
Integrating Question Classification and Deep Learning for improved Answer Selection (C18-1)

Copied to clipboard

Challenge: Question Answering (QA) is the task of automatically generating answers to questions posed in natural language.
Approach: They propose a system for Answer Selection that integrates fine-grained Question Classification with a Deep Learning model designed for Answer selection.
Outcome: The proposed system outperforms the current state of the art in all variations except one . the proposed system improves QA by reducing the search space of potential answers .
Abstraction not Memory: BERT and the English Article System (2022.naacl-main)

Copied to clipboard

Challenge: Pre-trained models are the state of the art in linguistics.
Approach: They compare the performance of pre-trained and native English language models on the task of article prediction set up as a three way choice (a/an, the, zero) they argue that BERT captures a high level generalisation of article use akin to human intuition.
Outcome: The proposed model outperforms humans on the linguistically interesting task of article prediction.

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