English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Topic models represent groups of documents as a list of words (the topiclabels). This work asks whether an alternative approach to topic labeling canbe developed that is closer to a natural language description of a topic than aword list. To this end, we present an approach to generating human-like topiclabels using abstractive multi-document summarization (MDS). We investigate ourapproach with an exploratory case study. We model topics in citation sentencesin order to understand what further research needs to be done to fullyoperationalize MDS for topic labeling. Our case study shows that in addition tomore human-like topics there are additional advantages to evaluation by usingclustering and summarization measures instead of topic model measures. However,we find that there are several developments needed before we can design awell-powered study to evaluate MDS for topic modeling fully. Namely, improvingcluster cohesion, improving the factuality and faithfulness of MDS, andincreasing the number of documents that might be supported by MDS. We present anumber of ideas on how these can be tackled and conclude with some thoughts onhow topic modeling can also be used to improve MDS in general.

Moving beyond word lists: towards abstractive topic labels for human-like topics of scientific documents