Papers by Hady Elsahar
T-REx: A Large Scale Alignment of Natural Language with Knowledge Base Triples (L18-1)
Copied to clipboard
Hady Elsahar, Pavlos Vougiouklis, Arslen Remaci, Christophe Gravier, Jonathon Hare, Frederique Laforest, Elena Simperl
| Challenge: | Existing datasets that provide alignments between natural language and knowledge bases (KB) triples are limited in size, lack coverage and are of unreported quality. |
| Approach: | They propose to build a large scale dataset of alignments between Wikipedia abstracts and Wikidata triples that is two orders of magnitude larger than the largest available alignments dataset. |
| Outcome: | The proposed dataset is two orders of magnitude larger than the largest available dataset and covers 2.5 times more predicates. |
What Language Model to Train if You Have One Million GPU Hours? (2022.findings-emnlp)
Copied to clipboard
Teven Le Scao, Thomas Wang, Daniel Hesslow, Stas Bekman, M Saiful Bari, Stella Biderman, Hady Elsahar, Niklas Muennighoff, Jason Phang, Ofir Press, Colin Raffel, Victor Sanh, Sheng Shen, Lintang Sutawika, Jaesung Tae, Zheng Xin Yong, Julien Launay, Iz Beltagy
| Challenge: | Recent years have seen the advent of large language models characterized by emergent capabilities arising from sheer scale alone. |
| Approach: | They propose to use a multilingual model to compare performance to the English-only model by ablation at the billion-parameter scale. |
| Outcome: | The proposed model is based on a multilingual model and its performance against the English-only model. |
Participatory Research for Low-resourced Machine Translation: A Case Study in African Languages (2020.findings-emnlp)
Copied to clipboard
Wilhelmina Nekoto, Vukosi Marivate, Tshinondiwa Matsila, Timi Fasubaa, Taiwo Fagbohungbe, Solomon Oluwole Akinola, Shamsuddeen Muhammad, Salomon Kabongo Kabenamualu, Salomey Osei, Freshia Sackey, Rubungo Andre Niyongabo, Ricky Macharm, Perez Ogayo, Orevaoghene Ahia, Musie Meressa Berhe, Mofetoluwa Adeyemi, Masabata Mokgesi-Selinga, Lawrence Okegbemi, Laura Martinus, Kolawole Tajudeen, Kevin Degila, Kelechi Ogueji, Kathleen Siminyu, Julia Kreutzer, Jason Webster, Jamiil Toure Ali, Jade Abbott, Iroro Orife, Ignatius Ezeani, Idris Abdulkadir Dangana, Herman Kamper, Hady Elsahar, Goodness Duru, Ghollah Kioko, Murhabazi Espoir, Elan van Biljon, Daniel Whitenack, Christopher Onyefuluchi, Chris Chinenye Emezue, Bonaventure F. P. Dossou, Blessing Sibanda, Blessing Bassey, Ayodele Olabiyi, Arshath Ramkilowan, Alp Öktem, Adewale Akinfaderin, Abdallah Bashir
| Challenge: | 'Low-resourced'-ness is a complex problem that goes beyond data availability and reflects systemic problems in society. |
| Approach: | They propose to use machine translation to scale to low-resourced languages by using a dataset and a benchmarking system to measure their resource use. |
| Outcome: | The proposed approach allows participants without formal training to make a unique scientific contribution. |
Unsupervised Aspect-Based Multi-Document Abstractive Summarization (D19-54)
Copied to clipboard
| Challenge: | Existing methods for opinion summarization are expensive and do not deal with contradictory statements. |
| Approach: | They propose an unsupervised abstractive summarization neural system that generates short summaries of reviews in a vector space. |
| Outcome: | The proposed system can generate short summaries of user-generated reviews in a short paragraph, while nobody reads all reviews. |
Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types (N18-1)
Copied to clipboard
| Challenge: | Existing factoid question answering systems rely on annotated datasets such as SimpleQuestions to generate questions from knowledge graphs. |
| Approach: | They propose a neural model that generates questions from knowledge graphs triples in a “zero-shot” setup. |
| Outcome: | The proposed model outperforms state-of-the-art on this task. |
Learning to Generate Wikipedia Summaries for Underserved Languages from Wikidata (N18-2)
Copied to clipboard
Lucie-Aimée Kaffee, Hady Elsahar, Pavlos Vougiouklis, Christophe Gravier, Frédérique Laforest, Jonathon Hare, Elena Simperl
| Challenge: | Existing Wikipedia content is unevenly distributed among 287 languages . authors propose a neural network architecture that generates textual summaries from Wikidata triples . |
| Approach: | They propose an automated approach to generate Wikipedia summaries from Wikidata triples using structured data. |
| Outcome: | The proposed approach is tested on Arabic and Esperanto languages with limited editors and content in the most under-resourced Wikipedias. |
Self-Supervised and Controlled Multi-Document Opinion Summarization (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing unsupervised methods for summarizing reviews are based on bootstrapping and require a combination of loss functions or hierarchical latent variables to ensure that the generated summaries remain on-topic. |
| Approach: | They propose a self-supervised setup that considers an individual document as a target summary for a set of similar documents. |
| Outcome: | The proposed setup makes training simpler than previous approaches by relying only on standard log-likelihood loss and mainstream models. |
To Annotate or Not? Predicting Performance Drop under Domain Shift (D19-1)
Copied to clipboard
| Challenge: | Performance drop due to domain-shift is an endemic problem for NLP models in production. |
| Approach: | They propose to use H-divergence, reverse classification accuracy and confidence measures to predict performance drop under domain-shift without any target domain labels. |
| Outcome: | The proposed method predicts performance drops with an error rate as low as 2.15% and 0.89% for sentiment analysis and POS tagging respectively. |