Search Results for author:
Found 20 papers, 15 papers with code
Inceptive Transformers: Enhancing Contextual Representations through Multi-Scale Feature Learning Across Domains and Languages
Conventional transformer models typically compress the information from all tokens in a sequence into a single \texttt{[CLS]} token to represent global context-- an approach that can lead to information loss in tasks requiring localized or hierarchical cues.
Multi-ToM: Evaluating Multilingual Theory of Mind Capabilities in Large Language Models
Theory of Mind (ToM) refers to the cognitive ability to infer and attribute mental states to oneself and others.
ChakmaNMT: A Low-resource Machine Translation On Chakma Language
Thus, we have worked on MT between CCP-BN(Chakma-Bangla) by introducing a novel dataset of 15, 021 parallel samples and 42, 783 monolingual samples of the Chakma Language.
ConVerSum: A Contrastive Learning-based Approach for Data-Scarce Solution of Cross-Lingual Summarization Beyond Direct Equivalents
Cross-lingual summarization (CLS) is a sophisticated branch in Natural Language Processing that demands models to accurately translate and summarize articles from different source languages.
An Empirical Study of Gendered Stereotypes in Emotional Attributes for Bangla in Multilingual Large Language Models
All of our resources including code and data are made publicly available to support future research on Bangla NLP.
Social Bias in Large Language Models For Bangla: An Empirical Study on Gender and Religious Bias
The rapid growth of Large Language Models (LLMs) has put forward the study of biases as a crucial field.
An Empirical Study on the Characteristics of Bias upon Context Length Variation for Bangla
Specifically, in this study, we (1) create a dataset for intrinsic gender bias measurement in Bangla, (2) discuss necessary adaptations to apply existing bias measurement methods for Bangla, and (3) examine the impact of context length variation on bias measurement, a factor that has been overlooked in previous studies.
IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models
We discover that In-Context Learning (ICL) and Chain-of-Thought reasoning substantially degrade the performance of Gemini-Pro in the localization task.
Ranked #1 on
Object Localization
on IllusionVQA
BanglaParaphrase: A High-Quality Bangla Paraphrase Dataset
In this work, we present BanglaParaphrase, a high-quality synthetic Bangla Paraphrase dataset curated by a novel filtering pipeline.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
BanglaNLG and BanglaT5: Benchmarks and Resources for Evaluating Low-Resource Natural Language Generation in Bangla
This work presents BanglaNLG, a comprehensive benchmark for evaluating natural language generation (NLG) models in Bangla, a widely spoken yet low-resource language.
CrossSum: Beyond English-Centric Cross-Lingual Summarization for 1,500+ Language Pairs
LaSE is strongly correlated with ROUGE and, unlike ROUGE, can be reliably measured even in the absence of references in the target language.
XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages
XL-Sum induces competitive results compared to the ones obtained using similar monolingual datasets: we show higher than 11 ROUGE-2 scores on 10 languages we benchmark on, with some of them exceeding 15, as obtained by multilingual training.
CoDesc: A Large Code-Description Parallel Dataset
In this study, we present CoDesc -- a large parallel dataset composed of 4. 2 million Java methods and natural language descriptions.
Ranked #1 on
Code Search
on CoDesc
Text2App: A Framework for Creating Android Apps from Text Descriptions
We overcome this limitation by transforming natural language into an abstract intermediate formal language representing an application with a substantially smaller number of tokens.
BERT2Code: Can Pretrained Language Models be Leveraged for Code Search?
In this work, we leverage the efficacy of these embedding models using a simple, lightweight 2-layer neural network in the task of semantic code search.
BanglaBERT: Language Model Pretraining and Benchmarks for Low-Resource Language Understanding Evaluation in Bangla
In this work, we introduce BanglaBERT, a BERT-based Natural Language Understanding (NLU) model pretrained in Bangla, a widely spoken yet low-resource language in the NLP literature.
Not Low-Resource Anymore: Aligner Ensembling, Batch Filtering, and New Datasets for Bengali-English Machine Translation
With the segmenter and the two methods combined, we compile a high-quality Bengali-English parallel corpus comprising of 2. 75 million sentence pairs, more than 2 million of which were not available before.
Early Prediction for Merged vs Abandoned Code Changes in Modern Code Reviews
In our empirical study on the 146, 612 code changes from the three software projects, we find that (1) The new features like reviewer dimensions that are introduced in PredCR are the most informative.
