Search Results for author: Hassan Kané

Found 6 papers, 2 papers with code

Building Disaster Damage Assessment in Satellite Imagery with Multi-Temporal Fusion

1 code implementation12 Apr 2020 Ethan Weber, Hassan Kané

Automatic change detection and disaster damage assessment are currently procedures requiring a huge amount of labor and manual work by satellite imagery analysts.

2D Semantic Segmentation Change Detection

Combining graph and sequence information to learn protein representations

no code implementations25 Sep 2019 Hassan Kané, Mohamed Coulibali, Pelkins Ajanoh, Ali Abdalla

Using these representations, we train machine learning models that outperform existing methods on the task of tissue-specific protein function prediction on 10 out of 13 tissues.

Protein Function Prediction Representation Learning

JAUNE: Justified And Unified Neural language Evaluation

no code implementations25 Sep 2019 Hassan Kané, Yusuf Kocyigit, Ali Abdalla, Pelkins Ajanoh, Mohamed Coulibali

We review the limitations of BLEU and ROUGE -- the most popular metrics used to assess reference summaries against hypothesis summaries, and introduce JAUNE: a set of criteria for what a good metric should behave like and propose concrete ways to use recent Transformers-based Language Models to assess reference summaries against hypothesis summaries.

Towards Neural Language Evaluators

no code implementations20 Sep 2019 Hassan Kané, Yusuf Kocyigit, Pelkins Ajanoh, Ali Abdalla, Mohamed Coulibali

We review three limitations of BLEU and ROUGE -- the most popular metrics used to assess reference summaries against hypothesis summaries, come up with criteria for what a good metric should behave like and propose concrete ways to use recent Transformers-based Language Models to assess reference summaries against hypothesis summaries.

Towards Neural Similarity Evaluator

no code implementations NeurIPS Workshop Document_Intelligen 2019 Hassan Kané, Yusuf Kocyigit, Pelkins Ajanoh, Ali Abdalla, Mohamed Coulibali

We review three limitations of BLEU and ROUGE – the most popular metrics used to assess reference summaries against hypothesis summaries, come up with criteria for what a good metric should behave like and propose concrete ways to assess the performance of a metric in detail and show the potential of Transformers-based Language Models to assess reference summaries against hypothesis summaries.

AWE-CM Vectors: Augmenting Word Embeddings with a Clinical Metathesaurus

1 code implementation5 Dec 2017 Willie Boag, Hassan Kané

In recent years, word embeddings have been surprisingly effective at capturing intuitive characteristics of the words they represent.

Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.