Papers by Fahad Khan

9 papers
Arabic Mini-ClimateGPT : A Climate Change and Sustainability Tailored Arabic LLM (2023.findings-emnlp)

Copied to clipboard

Challenge: Recent large language models like ChatGPT and Bard excel in a wide variety of NLP tasks but are not specifically tailored for climate related domain specific information.
Approach: They propose a lightweight Arabic Mini-ClimateGPT that is built on an open-source LLM and specifically fine-tuned on a conversational-style instruction tuning curated Arabic dataset Clima500-Instruct.
Outcome: The proposed model surpasses the baseline LLM in 88.3% of cases during ChatGPT-based evaluation and human expert prefers it over other open-source models.
Modelling Etymology in LMF/TEI: The Grande Dicionário Houaiss da Língua Portuguesa Dictionary as a Use Case (2020.lrec-1)

Copied to clipboard

Challenge: In this article, we will introduce two of the new parts of the Lexical Markup Framework (LMF) ISO standard . part 3 deals with etymological and diachronic data and part 4 consists of a TEI serialisation of all of the prior parts of TEIS model.
Approach: They introduce two parts of the Lexical Markup Framework (LMF) ISO standard, part 3 dealing with etymological and diachronic data and part 4 containing TEI serialisation of all prior parts of a model.
Outcome: The proposed models are based on examples taken from a Portuguese dictionary conversion and are then compared with TEI-XML models.
Video-ChatGPT: Towards Detailed Video Understanding via Large Vision and Language Models (2024.acl-long)

Copied to clipboard

Challenge: a surge of deep learning applications for video understanding have led to major advancements in video-related tasks.
Approach: They propose a multimodal video-based conversation model that merges a video-adapted visual encoder with an LLM and a dataset that is easily scalable and robust to label noise.
Outcome: The proposed model can understand and generate detailed conversations about videos.
A Multilingual Evaluation Dataset for Monolingual Word Sense Alignment (2020.lrec-1)

Copied to clipboard

Challenge: a new dataset aims to align monolingual dictionaries with a single sense level for 15 languages . this dataset covers a wide range of languages and resources .
Approach: They propose to manually align monolingual dictionaries with possible semantic relationships . they use 15 languages to create a new baseline for the task of monolingual word sense alignment .
Outcome: The proposed dataset covers 15 languages and covers the more challenging task of linking general-purpose language.
One Language to rule them all: modelling Morphological Patterns in a Large Scale Italian Lexicon with SWRL (L18-1)

Copied to clipboard

Challenge: Linked data (LD) is a popular way of publishing lexical resources, but technical limitations and potentialities of LD are not understood as they should be.
Approach: They propose to use the Semantic Web Rule Language to encode morphological patterns for a lexicographic publication as linked open data.
Outcome: The proposed language allows the automatic derivation of inflectional variants of entries in the lexicon.
MultiLexBATS: Multilingual Dataset of Lexical Semantic Relations (2024.lrec-main)

Copied to clipboard

Challenge: Prior work has focused on analysing lexical semantic relations in word embeddings or probing pretrained language models (PLMs) with some exceptions.
Approach: They propose to use a multilingual parallel dataset of lexical semantic relations adapted from BATS in 15 languages including low-resource languages such as Bambara, Lithuanian, and Albanian as an experiment on cross-lingual transfer of relational knowledge.
Outcome: The proposed dataset is adapted from a BATS-based dataset in 15 languages including low-resource languages such as Bambara, Lithuanian, and Albanian.
Towards the Construction of a WordNet for Old English (2022.lrec-1)

Copied to clipboard

Challenge: In this paper we discuss our preliminary work towards the construction of a WordNet for Old English, taking our inspiration from other similar WN construction projects for ancient languages such as Ancient Greek, Latin and Sanskrit.
Approach: They propose to use a legacy Old English dictionary to build a WordNet for Old English using a lexicographic resource and the naisc system to automatically compile a provisional version of the WordNet.
Outcome: The proposed OldEWN will be based on lemmas and definitions extracted from a legacy Old English dictionary and will be automatically compile and enriched by experts using the naisc system.
On Modelling Corpus Citations in Computational Lexical Resources (2024.lrec-main)

Copied to clipboard

Challenge: TEI and OntoLex deal with corpus citations in lexicons.
Approach: They argue that TEI and OntoLex can be used to model corpus citations in lexicons . they also argue that they should be combined to achieve a more accurate encoding .
Outcome: The proposed approach favours a combination of TEI and OntoLex . the proposed approach is based on a model of an example entry from a legacy dictionary .
BiMediX: Bilingual Medical Mixture of Experts LLM (2024.findings-emnlp)

Copied to clipboard

Challenge: a new bilingual medical mixture of experts LLM is designed for seamless interaction in both English and Arabic.
Approach: They propose a semi-automated English-to-Arabic translation pipeline with human refinement to ensure high-quality translations.
Outcome: The proposed model outperforms state-of-the-art medical LLMs in Arabic and Arabic . it outperformed the generic Arabic-English bilingual LLM, Jais-30B by 10% and 15% .

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