I
Ilaria Bordino
Researcher at UniCredit
Publications - 34
Citations - 1740
Ilaria Bordino is an academic researcher from UniCredit. The author has contributed to research in topics: Sentiment analysis & Web query classification. The author has an hindex of 13, co-authored 34 publications receiving 1581 citations. Previous affiliations of Ilaria Bordino include Max Planck Society & Yahoo!.
Papers
More filters
Proceedings Article
Robust Disambiguation of Named Entities in Text
Johannes Hoffart,Mohamed Amir Yosef,Ilaria Bordino,Hagen Fürstenau,Manfred Pinkal,Marc Spaniol,Bilyana Taneva,Stefan Thater,Gerhard Weikum +8 more
TL;DR: A robust method for collective disambiguation is presented, by harnessing context from knowledge bases and using a new form of coherence graph that significantly outperforms prior methods in terms of accuracy, with robust behavior across a variety of inputs.
Journal ArticleDOI
Web search queries can predict stock market volumes.
Ilaria Bordino,Stefano Battiston,Guido Caldarelli,Guido Caldarelli,Matthieu Cristelli,Antti Ukkonen,Ingmar Weber +6 more
TL;DR: It is shown that daily trading volumes of stocks traded in NASDAQ-100 are correlated with daily volumes of queries related to the same stocks, and query volumes anticipate in many cases peaks of trading by one day or more.
Journal ArticleDOI
AIDA: an online tool for accurate disambiguation of named entities in text and tables
TL;DR: A Web-based online interface for AIDA is developed where different formats of inputs can be processed on the fly, returning proper entities and showing intermediate steps of the disambiguation process.
Proceedings ArticleDOI
Mining Large Networks with Subgraph Counting
TL;DR: Data-stream algorithms that approximate the number of all subgraphs of three and four vertices in directed and undirected networks are developed and achieve very good precision in clustering networks with similar structure.
Proceedings ArticleDOI
Query similarity by projecting the query-flow graph
TL;DR: The information present in query logs is exploited in order to develop a measure of semantic similarity between queries that captures a notion of semantic Similarity between queries and it is useful for diversifying query recommendations.