Stage-oe-small.jpg

Inproceedings3562: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
 
Zeile 16: Zeile 16:
 
|Year=2017
 
|Year=2017
 
|Month=April
 
|Month=April
|Booktitle=18th International Conference on Computational Linguistics and Intelligent Text Processing (Cicling)
+
|Booktitle=18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)
 
|Publisher=IJCLA
 
|Publisher=IJCLA
 
}}
 
}}
Zeile 22: Zeile 22:
 
|Abstract=Social media platforms have grown into an important medium
 
|Abstract=Social media platforms have grown into an important medium
 
to spread information about an event published by the traditional media, such as news articles. Grouping such diverse sources of information that discuss the same topic in varied perspectives provide new insights. But the gap in word usage between informal social media content such as tweets and diligently written content (e.g. news articles) make such assembling difficult. In this paper, we propose a transformation framework to bridge the word usage gap between tweets and online news articles across languages by leveraging their word embeddings. Using our framework, word embeddings extracted from tweets and news articles are aligned closer to each other across languages, thus facilitating the identification of similarity between news articles and tweets. Experimental results show a notable improvement over baselines for monolingual tweets and news articles comparison, while new findings are reported for cross-lingual comparison.
 
to spread information about an event published by the traditional media, such as news articles. Grouping such diverse sources of information that discuss the same topic in varied perspectives provide new insights. But the gap in word usage between informal social media content such as tweets and diligently written content (e.g. news articles) make such assembling difficult. In this paper, we propose a transformation framework to bridge the word usage gap between tweets and online news articles across languages by leveraging their word embeddings. Using our framework, word embeddings extracted from tweets and news articles are aligned closer to each other across languages, thus facilitating the identification of similarity between news articles and tweets. Experimental results show a notable improvement over baselines for monolingual tweets and news articles comparison, while new findings are reported for cross-lingual comparison.
|Download=CameraReady-CICLing-2017.pdf,  
+
|Download=CameraReady-CICLing-2017.pdf,
 
|Projekt=XLiMe
 
|Projekt=XLiMe
 
|Forschungsgruppe=Web Science
 
|Forschungsgruppe=Web Science
 
}}
 
}}

Aktuelle Version vom 16. Juni 2017, 12:00 Uhr


Linking Tweets with Monolingual and Cross-Lingual News using Transformed Word Embeddings


Linking Tweets with Monolingual and Cross-Lingual News using Transformed Word Embeddings



Published: 2017 April

Buchtitel: 18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing)
Verlag: IJCLA

Referierte Veröffentlichung

BibTeX

Kurzfassung
Social media platforms have grown into an important medium to spread information about an event published by the traditional media, such as news articles. Grouping such diverse sources of information that discuss the same topic in varied perspectives provide new insights. But the gap in word usage between informal social media content such as tweets and diligently written content (e.g. news articles) make such assembling difficult. In this paper, we propose a transformation framework to bridge the word usage gap between tweets and online news articles across languages by leveraging their word embeddings. Using our framework, word embeddings extracted from tweets and news articles are aligned closer to each other across languages, thus facilitating the identification of similarity between news articles and tweets. Experimental results show a notable improvement over baselines for monolingual tweets and news articles comparison, while new findings are reported for cross-lingual comparison.

Download: Media:CameraReady-CICLing-2017.pdf

Projekt

XLiMe



Forschungsgruppe

Web Science


Forschungsgebiet