Supervised Text-based Geolocation Using Language Models on an Adaptive Grid
By Stephen Roller, Michael Speriosu, Sarat Rallapalli, Benjamin Wing, Jason Baldridge. 2012
233 citations recorded by the source corpus.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Felix Wu
- Mohit Bansal
- Jacob Eisenstein
- Sebastian Ruder
- Tianyi Zhang
- Percy Liang
- Yoshua Bengio
- Kyunghyun Cho
Citations in the corpus
- Simplifying Graph Convolutional Networks (2019, methodology): “, 2010), TWITTERUS (Roller et al., 2012), and TWITTER-WORLD (Han et al.”
- Semi-supervised User Geolocation via Graph Convolutional Networks (2018, background): “…media (Eisen-stein et al., 2010; Hong et al., 2012; Ahmed et al., 2013); and (3) supervised models which are often framed as text classification (Serdyukov et al., 2009; Wing and Baldridge, 2011; Roller et al., 2012; Han et al., 2014) or text regression (Iso et al., 2017; Rahimi et al., 2017a).”
- Confounds and Consequences in Geotagged Twitter Data (2015, methodology): “, 2012), or multilevel grid structures (Cheng et al., 2010; Roller et al., 2012).”
- Frege in Space: A Program of Compositional Distributional Semantics (2014, background): “18An exciting new development that might be useful for these purposes is that of distributional methods to geo-locate documents (Roller et al. 2012): The John Smith referred to in a document from Bakersfield is relatively unlikely to be the same John Smith mentioned in an article from Hyderabad.”
- Text-Based Twitter User Geolocation Prediction (2014, methodology): “We experiment with two class representations: (1) the city-based class representation based on Geonames; and (2) the k-d tree based partitioning of Roller et al. (2012), which creates grid cells containing roughly even amounts of data of differing geographical sizes, such that higher-population area”
- Geolocation Prediction in Social Media Data by Finding Location Indicative Words (2012, methodology): “Recently, Roller et al. (2012) extend this idea using a KD-tree-based adaptive grid and grid centroids, achieving state-of-the-art geolocation prediction results.”