Harish Tayyar Madabushi's repositories
Cost-Sensitive_Bert_and_Transformers
Transformers for Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data
SemEval_2022_Task2-idiomaticity
Data and preprocessing scripts for SemEval 2022 Task 2: Multilingual Idiomaticity Detection and Sentence Embedding
AStitchInLanguageModels
Data and Baselines for AStitchInLanguageModels dataset
CxGBERT-BERT-meets-Construction-Grammar
Construction Grammar based BERT
Abstraction-not-Memory-BERT-and-the-English-Article-System-NAACL-2022
Article prediction is a task that has long defied accurate linguistic description. As such, this task is ideally suited to evaluate models on their ability to emulate native-speaker intuition. To this end, we compare the performance of native English speakers and pre-trained models on the task of article prediction set up as a three way choice (a/an, the, zero). Our experiments with BERT show that BERT outperforms humans on this task across all articles. In particular, BERT is far superior to humans at detecting the zero article, possibly because we insert them using rules that the deep neural model can easily pick up. More interestingly, we find that BERT tends to agree more with annotators than with the corpus when inter-annotator agreement is high but switches to agreeing more with the corpus as inter-annotator agreement drops. We contend that this alignment with annotators, despite being trained on the corpus, suggests that BERT is not memorising article use, but captures a high level generalisation of article use akin to human intuition.
Adjudicating-LLMs-as-PropBank-Annotators
Data and model outputs for the paper: Adjudicating LLMs as PropBank Annotators
Construction_Grammar_Schematicity_Corpus-CoGS
The Construction Grammar Schematicity (``CoGS'') corpus consists of 10 distinct English constructions, where the constructions vary with respect to schematicity.
Emergent_Abilities_and_in-Context_Learning
Emergent Abilities in Large Language Models just In-Context Learning
HTML_Miner
HTML::Miner - This Module 'Mines' (hopefully) useful information for an URL or HTML snippet.
Net-XMPP-Client-GTalk
Net::XMPP::Client::GTalk - This module provides an easy to use wrapper around the Net::XMPP class of modules for specific access to GTalk ( Both on Gmail and Google Apps ).
sentence-transformers
Multilingual Sentence & Image Embeddings with BERT
WWW-PerlMonks
This (Perl) module provides access to PerlMonks.