Adding semantics to microblog posts

By Edgar Meij, Wouter Weerkamp, Maarten de Rijke. Web Search and Data Mining, 2012

327 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Communication, Information Systems

View Paper: https://www.semanticscholar.org/paper/7801fdb0aa7db9301c7363f7cd68b43f97adafef

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Ikuya Yamada
2. Hiroyuki Shindo
3. Hideaki Takeda
4. Jiawei Han
5. Ben Hachey
6. Heng Ji
7. Paolo Ferragina
8. Andrew Chisholm

In Communication

1. Marco Cornolti
2. Massimiliano Ciaramita
3. Ben Hachey
4. Andrew Chisholm
5. Ikuya Yamada
6. Leon Derczynski
7. Edgar Meij
8. Hiroyuki Shindo

In Information Systems

1. Jianyong Wang
2. Ben Hachey
3. Andrew Chisholm
4. Jiawei Han
5. Edgar Meij
6. Paolo Ferragina
7. Laura Dietz
8. Massimiliano Ciaramita

Citations in the corpus

• A framework for benchmarking entity-annotation systems (2013, methodology): “As C2W, but here each tag is assigned a score representing the likelihood that the annotation is correct.”
• Named Entity Disambiguation for Noisy Text (2017, background): “Recently, a number of Twitter-based datasets were compiled as well (Meij et al., 2012; From-reide et al., 2014).”
• Leveraging Deep Neural Networks and Knowledge Graphs for Entity Disambiguation (2015, methodology): “(Meij et al., 2012), which includes 502 tweets and 812 non-NIL mentions.”
• Entity Disambiguation with Web Links (2015, background): “For a more detailed survey of features in supervised systems, see Meij et al. (2012) and Radford (2014).”
• Implicit Entity Linking in Tweets (2016, background): “SVM shown to perform well in similar ranking problems, specifically it is able to provide best performance in ranking the top concept [12] which suits the characteristics of our problem.”
• Analysis of named entity recognition and linking for tweets (2014, background): “Recent Twitter-focused experiments uncovered problems in using state-of-the-art entity linking in tweets [32, 33, 34], again largely due to lack of sufficient context to aid disambiguation.”
• Entity Linking with a Knowledge Base: Issues, Techniques, and Solutions (2015, background): “Although some researchers have preliminarily addressed the entity linking task in web tables [119], web lists [92], and tweets [22], [56], [79], [96], [146],”
• Learning Distributed Representations of Texts and Entities from Knowledge Base (2017, methodology): “In addition, we optionally add features representing string similarities between the title of e and the surface of m (Meij et al., 2012; Yamada et al., 2016).”
• Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation (2016, methodology): “In particular, we use Gradient Boosted Regression Trees (GBRT) (Friedman, 2001), a stateof-the-art point-wise learning-to-rank algorithm widely used for various tasks, which has been recently adopted for the sort of tasks for which we employ it here (Meij et al., 2012).”
• Utilizing Knowledge Graphs in Text-centric Information Retrieval (2017, background): “In particular, with effective entity representation schemes [6], fast and accurate entity retrieval [11, 18] and linking [2, 10] methods as well as collections [5], bidirectional connections between text and KGs are readily available.”