Dragomir Radev · page 2
Papers
- Generating Natural Language Summaries from Multiple On-Line Sources (1998 · 78 citations)
Radev and McKeown tackle information overload in online news. Statistical extractors of the time summarized one article at a time by lifting sentences, so they could not relate sources to each other, and the extracted sentences often read poorly together. The authors propose SUMMONS, a knowledge-based system that… - Evaluating GPT-4 and ChatGPT on Japanese Medical Licensing Examinations (2023 · 77 citations)
LLMs are increasingly used by non-English speakers, yet most specialist benchmarks are English-only or translated from English. - Identifying Opinion Subgroups in Arabic Online Discussions (2013 · 77 citations)
The paper addresses how participants in an Arabic online debate split into camps with opposing views. The system takes a forum thread and outputs a subgroup label for every discussant. The pipeline has five components: - MACSum: Controllable Summarization with Mixed Attributes (2023 · 37 citations)
Readers often want summaries tailored to them, for example short ones, ones about a specific topic, or ones that stay close to the source wording.
This page in Markdown → https://md.research.elamur.ai/free/en/authors/dragomir-radev/page/2/