About "Towards Better Text Understanding and Retrieval through Kernel Entity Salience Modeling"
0 likes58 views
The document discusses the exploration of entity salience modeling to improve text understanding and document retrieval, emphasizing that word frequency does not necessarily equate to salience. It introduces a kernel interaction model that combines textual information and semantic data from knowledge bases to enhance document search capabilities. Experimental results indicate that this approach can improve the modeling of salience, particularly for short documents and ad hoc search scenarios.
About "Towards Better Text Understanding and Retrieval through Kernel Entity Salience Modeling"
- 1. Reading Group 17.10.2018 Towards Better Text Understanding and Retrieval through Kernel Entity Salience Modeling Xiong, Liu, Callan, and Liu SIGIR 2018
- 2. Motivation • Interest in knowing how salient (important and central) a term (word, entity) is in a document • Word frequency largely exploited for document retrieval • But frequency is not necessarily same as salience • Entity salience is still a young task • Effectiveness of salience for ad hoc search is not explored yet
- 3. Main Messages • They represent an entity combining the textual information and semantics from knowledge base • They obtain a better modeling of salience, beyond frequency, by entity interactions • They can improve web document search with salience, generalizing from news corpus
- 4. Knowledge Enriched Embedding • Adds to the textual embedding the semantics from the knowledge graph
- 11. Experimental Setup • Two datasets • New York Times (~ 500k articles with summaries) • e in article is salient if it's also in summary • Semantic Scholar (~ 1m abstracts) • e in abstract is salient if it's also in title • Ranking-focused metrics: P@1, P@5, R@1, R@5 • Well documented parameter settings
- 13. Analysis VS. Frequency • KESM is able to model salience of tail entities • KESM is more reliable on short documents
- 14. Salience for Ad hoc Search • Entity salience should model a better text understanding • So it should hep for document search • Ranking uses the salience of the query entities in a candidate document • End-to-end training with sufficient relevance labels, or using model pre-trained on salience
- 16. Results: Ad hoc Search
- 20. • Figures taken from these slides: http://www.cs.cmu.edu/~cx/slides/KESM-slides.pdf