Papers by Sebastian Joseph
InfoLossQA: Characterizing and Recovering Information Loss in Text Simplification (2024.acl-long)
Copied to clipboard
Jan Trienes, Sebastian Joseph, Jörg Schlötterer, Christin Seifert, Kyle Lo, Wei Xu, Byron Wallace, Junyi Jessy Li
| Challenge: | Text simplification aims to make technical texts more accessible to laypeople but often results in deletion of information and vagueness. |
| Approach: | They propose a framework to characterize and recover simplification-induced information loss in form of question-and-answer (QA) pairs. |
| Outcome: | The proposed framework characterizes and recovers simplification-induced information loss in form of question-and-answer (QA) pairs. |
Multilingual Simplification of Medical Texts (2023.emnlp-main)
Copied to clipboard
Sebastian Joseph, Kathryn Kazanas, Keziah Reina, Vishnesh Ramanathan, Wei Xu, Byron Wallace, Junyi Jessy Li
| Challenge: | Existing work on medical text simplification has focused on monolingual settings . important findings in medicine are typically presented in technical, jargon-laden language . text simulating models can generate viable simplified texts, but there are outstanding challenges . |
| Approach: | They propose a dataset for medical text simplification in four languages . they evaluate fine-tuned and zero-shot models across these languages based on human assessments and analyses . |
| Outcome: | The proposed dataset evaluates models in English, Spanish, French, and Farsi . it shows that the models can generate viable simplified texts, but there are challenges . |
Summarizing, Simplifying, and Synthesizing Medical Evidence using GPT-3 (with Varying Success) (2023.acl-short)
Copied to clipboard
| Challenge: | Large language models are capable of producing high quality summaries of general domain news articles in few- and zero-shot settings, but it is unclear whether they are similarly capable in more specialized domains such as biomedicine. |
| Approach: | They use GPT-3 to generate single- and multi-document summaries of biomedical articles, given no supervision, using a set of annotations. |
| Outcome: | The proposed model outperforms fully supervised models in generic news summarization, but struggles to synthesize evidence across multiple documents. |
Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning (2024.acl-long)
Copied to clipboard
Shivalika Singh, Freddie Vargus, Daniel D’souza, Börje Karlsson, Abinaya Mahendiran, Wei-Yin Ko, Herumb Shandilya, Jay Patel, Deividas Mataciunas, Laura O’Mahony, Mike Zhang, Ramith Hettiarachchi, Joseph Wilson, Marina Machado, Luisa Moura, Dominik Krzemiński, Hakimeh Fadaei, Irem Ergun, Ifeoma Okoh, Aisha Alaagib, Oshan Mudannayake, Zaid Alyafeai, Vu Chien, Sebastian Ruder, Surya Guthikonda, Emad Alghamdi, Sebastian Gehrmann, Niklas Muennighoff, Max Bartolo, Julia Kreutzer, Ahmet Üstün, Marzieh Fadaee, Sara Hooker
| Challenge: | Existing datasets in the English language are mostly in the realm of instruction fine-tuning . aya dataset, the Aya Collection, and the AYa Evaluation Suite are key resources . |
| Approach: | They aim to build a human-curated instruction-following dataset spanning 65 languages . they work with fluent speakers of languages from around the world to collect natural instances of instructions and completions . |
| Outcome: | The goal is to build a human-curated instruction-following dataset spanning 65 languages. |
FactPICO: Factuality Evaluation for Plain Language Summarization of Medical Evidence (2024.acl-long)
Copied to clipboard
Sebastian Joseph, Lily Chen, Jan Trienes, Hannah Göke, Monika Coers, Wei Xu, Byron Wallace, Junyi Jessy Li
| Challenge: | FactPICO is a factuality benchmark for plain language summarization of medical texts describing randomized controlled trials . existing metrics for factual summarizing medical evidence are poorly correlated with expert judgments on the instance level. |
| Approach: | They propose a factuality benchmark for plain language summarization of medical texts . they assess factuality of critical elements of RCTs in those summaries . |
| Outcome: | The proposed benchmark assesses the factuality of medical summaries using LLMs . the summary summators are based on 345 plain language summaires with fine-grained evaluation . |