J
Jun-Ping Ng
Researcher at National University of Singapore
Publications - 13
Citations - 360
Jun-Ping Ng is an academic researcher from National University of Singapore. The author has contributed to research in topics: Automatic summarization & Multi-document summarization. The author has an hindex of 10, co-authored 13 publications receiving 298 citations. Previous affiliations of Jun-Ping Ng include Bloomberg L.P..
Papers
More filters
Proceedings ArticleDOI
Better Summarization Evaluation with Word Embeddings for ROUGE
Jun-Ping Ng,Viktoria Abrecht +1 more
TL;DR: In this article, instead of measuring lexical overlaps, word embeddings are used to compute the semantic similarity of the words used in summaries instead, which is able to achieve better correlations with human judgements when measured with the Spearman and Kendall rank coefficients.
Proceedings Article
Mining Scientific Terms and their Definitions: A Study of the ACL Anthology
TL;DR: DefMiner is presented, a supervised sequence labeling system that identifies scientific terms and their accompanying definitions and achieves 85% F1 on a Wikipedia benchmark corpus, significantly improving the previous state-of-the-art by 8%.
Proceedings Article
Exploiting Category-Specific Information for Multi-Document Summarization
TL;DR: This work operationalizes the computation CSI of sentences through the introduction of two new features that can be computed without needing any external knowledge, and incorporates these features into a simple, freely available, open-source extractive summarization system, called SWING.
Proceedings ArticleDOI
Exploiting Timelines to Enhance Multi-document Summarization
TL;DR: TIMEMMR is proposed, a modification to Maximal Marginal Relevance that promotes temporal diversity by way of computing time span similarity, and its utility in summarizing certain document sets is shown.
Posted Content
QANUS: An Open-source Question-Answering Platform.
Jun-Ping Ng,Min-Yen Kan +1 more
TL;DR: The need for a publicly available, generic software framework for question-answering (QA) systems is motivated and an open-source QA framework QANUS is presented which researchers can leverage on to build new QA systems easily and rapidly.