Search Results for author:
Found 33 papers, 11 papers with code
Fine-tuning and Sampling Strategies for Multimodal Role Labeling of Entities under Class Imbalance
We propose our solution to the multimodal semantic role labeling task from the CONSTRAINT’22 workshop.
Effectiveness of Data Augmentation and Pretraining for Improving Neural Headline Generation in Low-Resource Settings
We tackle the problem of neural headline generation in a low-resource setting, where only limited amount of data is available to train a model.
Transport Optimal pour le Changement Sémantique à partir de Plongements Contextualisés (Optimal Transport for Semantic Change Detection using Contextualised Embeddings )
Plusieurs méthodes de détection des changements sémantiques utilisant des plongements lexicaux contextualisés sont apparues récemment.
Tâches Auxiliaires Multilingues pour le Transfert de Modèles de Détection de Discours Haineux (Multilingual Auxiliary Tasks for Zero-Shot Cross-Lingual Transfer of Hate Speech Detection)
La tâche de détection de contenus haineux est ardue, car elle nécessite des connaissances culturelles et contextuelles approfondies ; les connaissances nécessaires varient, entre autres, selon la langue du locateur ou la cible du contenu.
Caveats of Measuring Semantic Change of Cognates and Borrowings using Multilingual Word Embeddings
Cognates and borrowings carry different aspects of etymological evolution.
DRIVINGVQA: Analyzing Visual Chain-of-Thought Reasoning of Vision Language Models in Real-World Scenarios with Driving Theory Tests
Large vision-language models (LVLMs) augment language models with visual understanding, enabling multimodal reasoning.
PICLe: Pseudo-Annotations for In-Context Learning in Low-Resource Named Entity Detection
In-context learning (ICL) enables Large Language Models (LLMs) to perform tasks using few demonstrations, facilitating task adaptation when labeled examples are hard to obtain.
INCLUDE: Evaluating Multilingual Language Understanding with Regional Knowledge
The performance differential of large language models (LLM) between languages hinders their effective deployment in many regions, inhibiting the potential economic and societal value of generative AI tools in many communities.
Could ChatGPT get an Engineering Degree? Evaluating Higher Education Vulnerability to AI Assistants
We investigate the potential scale of this vulnerability by measuring the degree to which AI assistants can complete assessment questions in standard university-level STEM courses.
Course Recommender Systems Need to Consider the Job Market
In light of the job market's rapid changes and the current state of research in course recommender systems, we outline essential properties for course recommender systems to address these demands effectively, including explainable, sequential, unsupervised, and aligned with the job market and user's goals.
Multi-Task Learning for Features Extraction in Financial Annual Reports
For assessing various performance indicators of companies, the focus is shifting from strictly financial (quantitative) publicly disclosed information to qualitative (textual) information.
ConGeo: Robust Cross-view Geo-localization across Ground View Variations
Cross-view geo-localization aims at localizing a ground-level query image by matching it to its corresponding geo-referenced aerial view.
"Flex Tape Can't Fix That": Bias and Misinformation in Edited Language Models
We introduce a novel benchmark dataset, Seesaw-CF, for measuring bias-related harms of model editing and conduct the first in-depth investigation of how different weight-editing methods impact model bias.
ConVQG: Contrastive Visual Question Generation with Multimodal Guidance
However, generating focused questions using textual constraints while enforcing a high relevance to the image content remains a challenge, as VQG systems often ignore one or both forms of grounding.
Rethinking Skill Extraction in the Job Market Domain using Large Language Models
Skill Extraction involves identifying skills and qualifications mentioned in documents such as job postings and resumes.
JOBSKAPE: A Framework for Generating Synthetic Job Postings to Enhance Skill Matching
Recent approaches in skill matching, employing synthetic training data for classification or similarity model training, have shown promising results, reducing the need for time-consuming and expensive annotations.
InterpretCC: Intrinsic User-Centric Interpretability through Global Mixture of Experts
Interpretability for neural networks is a trade-off between three key requirements: 1) faithfulness of the explanation (i. e., how perfectly it explains the prediction), 2) understandability of the explanation by humans, and 3) model performance.
Instruction-tuning Aligns LLMs to the Human Brain
Instruction-tuning is a widely adopted finetuning method that enables large language models (LLMs) to generate output that more closely resembles human responses.
MEDITRON-70B: Scaling Medical Pretraining for Large Language Models
Large language models (LLMs) can potentially democratize access to medical knowledge.
Ranked #1 on
Multiple Choice Question Answering (MCQA)
on MedMCQA
(Dev Set (Acc-%) metric)
CRAB: Assessing the Strength of Causal Relationships Between Real-world Events
In this work, we present CRAB, a new Causal Reasoning Assessment Benchmark designed to evaluate causal understanding of events in real-world narratives.
CRoW: Benchmarking Commonsense Reasoning in Real-World Tasks
Recent efforts in natural language processing (NLP) commonsense reasoning research have yielded a considerable number of new datasets and benchmarks.
Multilingual Auxiliary Tasks Training: Bridging the Gap between Languages for Zero-Shot Transfer of Hate Speech Detection Models
Zero-shot cross-lingual transfer learning has been shown to be highly challenging for tasks involving a lot of linguistic specificities or when a cultural gap is present between languages, such as in hate speech detection.
Measure and Evaluation of Semantic Divergence across Two Languages
We propose a set of scenarios to characterize semantic divergence across two languages, along with a setup to differentiate them in a bilingual corpus.
Scalable and Interpretable Semantic Change Detection
We propose a novel scalable method for word usage-change detection that offers large gains in processing time and significant memory savings while offering the same interpretability and better performance than unscalable methods.
Discovery Team at SemEval-2020 Task 1: Context-sensitive Embeddings Not Always Better than Static for Semantic Change Detection
This paper describes the approaches used by the Discovery Team to solve SemEval-2020 Task 1 - Unsupervised Lexical Semantic Change Detection.
\'Etude des variations s\'emantiques \`a travers plusieurs dimensions (Studying semantic variations through several dimensions )
Nous exp{\'e}rimentons sur un corpus de rapports financiers d{'}entreprises fran{\c{c}}aises, pour appr{\'e}hender les enjeux et pr{\'e}occupations propres {\`a} certaines p{\'e}riodes, acteurs et secteurs d{'}activit{\'e}s.
Capturing Evolution in Word Usage: Just Add More Clusters?
The way the words are used evolves through time, mirroring cultural or technological evolution of society.
Empirical Study of Diachronic Word Embeddings for Scarce Data
Word meaning change can be inferred from drifts of time-varying word embeddings.
Learning dynamic word embeddings with drift regularisation
Word usage, meaning and connotation change throughout time.
Exploring sentence informativeness
This study is a preliminary exploration of the concept of informativeness -how much information a sentence gives about a word it contains- and its potential benefits to building quality word representations from scarce data.
Apprentissage de plongements de mots dynamiques avec r\'egularisation de la d\'erive (Learning dynamic word embeddings with drift regularisation)
L{'}usage, le sens et la connotation des mots peuvent changer au cours du temps.
