Thomas Scialom

24 papers · 2019–2024 · 8 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+7 more ↓

🗺️ Taxonomy Completionist (49) 🏃 Academic Marathon · Sprint 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Silver 🐣 Hot Topic Early Bird

🤝 Dynamic Duo (14) 🏆 Keyword Champion 🌈 Renaissance Researcher (6) 🔥 Unstoppable · Bronze ⚡ Prolific Year · Productive 💎 Century Club · Bronze 🗃️ Keyword Collector (100)

Venues

EMNLP (10) ACL (4) NeurIPS (3) ICLR (2) ICML (2) COLING (1) EACL (1) NAACL (1)

Top co-authors

Jacopo Staiano (14) Benjamin Piwowarski (11) Sylvain Lamprier (8) Paul-Alexis Dray (5) Or Honovich (3) Roee Aharoni (2) Hagai Taitelbaum (2) Idan Szpektor (2) Jonathan Herzig (2) Avinatan Hassidim (2)

Research topics

Natural Language Processing (18) Machine Learning (16) Generation (13) Learning Types · Machine Learning (12) Artificial Intelligence (10) Applications (10) Core AI (9) Deep Learning (8) Application Areas (5) Learning Types · Deep Learning (5) Resources & Methods (5) Architectures (2) Core Methods (2) Computer Vision (1) Interdisciplinary (1)

Keywords

question generation (8) text generation (7) reinforcement learning (5) language generation (4) natural language inference (4) large language model (3) evaluation metric (3) question answering (3) zero-shot learning (3) generative adversarial network (3) reference-less metric (2) abstractive summarization (2) summarization evaluation (2) text summarization (2) multimodal learning (2) instruction tuning (2) reference-free evaluation (2) stance detection (1) attention mechanism (1) self-attention mechanism (1)

Papers

GAIA: a benchmark for General AI Assistants ICLR 2024 Nougat: Neural Optical Understanding for Academic Documents ICLR 2024 LoRaLay: A Multilingual and Multimodal Dataset for Long Range and Layout-Aware Summarization EACL 2023 RQUGE: Reference-Free Metric for Evaluating Question Generation by Answering the Question ACL 2023 Toolformer: Language Models Can Teach Themselves to Use Tools NeurIPS 2023 Unnatural Instructions: Tuning Language Models with (Almost) No Human Labor ACL 2023 A Multifaceted Framework to Evaluate Evasion, Content Preservation, and Misattribution in Authorship Obfuscation Techniques EMNLP 2022 Fine-tuned Language Models are Continual Learners EMNLP 2022 Generative Cooperative Networks for Natural Language Generation ICML 2022 TRUE: Re-evaluating Factual Consistency Evaluation ACL 2022 TRUE: Re-evaluating Factual Consistency Evaluation NAACL 2022 Data-QuestEval: A Referenceless Metric for Data-to-Text Semantic Evaluation EMNLP 2021 QACE: Asking Questions to Evaluate an Image Caption EMNLP 2021 QuestEval: Summarization Asks for Fact-based Evaluation EMNLP 2021 Skim-Attention: Learning to Focus via Document Layout EMNLP 2021 Synthetic Data Augmentation for Zero-Shot Cross-Lingual Question Answering EMNLP 2021 To Beam Or Not To Beam: That is a Question of Cooperation for Language GANs NeurIPS 2021 Ask to Learn: A Study on Curiosity-driven Question Generation COLING 2020 ColdGANs: Taming Language GANs with Cautious Sampling Strategies NeurIPS 2020 Discriminative Adversarial Search for Abstractive Summarization ICML 2020 MLSUM: The Multilingual Summarization Corpus EMNLP 2020 Toward Stance-based Personas for Opinionated Dialogues EMNLP 2020 Answers Unite! Unsupervised Metrics for Reinforced Summarization Models EMNLP 2019 Self-Attention Architectures for Answer-Agnostic Neural Question Generation ACL 2019