Stage-oe-small.jpg

Inproceedings3760: Unterschied zwischen den Versionen

Aus Aifbportal
Wechseln zu:Navigation, Suche
(Die Seite wurde neu angelegt: „{{Publikation Erster Autor |ErsterAutorNachname=Färber |ErsterAutorVorname=Michael }} {{Publikation Author |Rank=2 |Author=Alexander Thiemann }} {{Publikation…“)
 
 
Zeile 20: Zeile 20:
 
}}
 
}}
 
{{Publikation Details
 
{{Publikation Details
|Abstract=Recommending citations for scientific texts and othertexts such as news articles has recently attracted considerable amount of attention. However, typically, the existing approaches for citation recommendation do not explicitly incorporate the question of whether a given context (e.g., a sentence), for which citations are to be recommended, actually "deserves" citations. Determining the “cite-worthiness” for each potential citation context as a step before the actual citation recommendation is beneficial, as (1) it can reduce the number of costly recommendation computations to a minimum, and (2) it can more closely approximate human-citing behavior, since neither too many nor too few recommendations are provided to the user. In this paper, we present a method based on a convolutional recurrent neural network for classifying potential citation contexts. Our experiments showthat we can significantly outperform the baseline solution [1] and reduce the number of citation recommendations to about 1/10.
+
|Abstract=Recommending citations for scientific texts and other texts such as news articles has recently attracted a considerable amount of attention. However, typically, the existing approaches for citation recommendation do not explicitly incorporate the question of whether a given context (e.g., a sentence), for which citations are to be recommended, actually "deserves" citations. Determining the "cite-worthiness" for each potential citation context as a step before the actual citation recommendation is beneficial, as (1) it can reduce the number of costly recommendation computations to a minimum, and (2) it can more closely approximate human-citing behavior, since neither too many nor too few recommendations are provided to the user. In this paper, we present a method based on a convolutional recurrent neural network for classifying potential citation contexts. Our experiments show that we can significantly outperform the baseline solution [1] and reduce the number of citation recommendations to about 1/10.
 
|Download=ToCite_ECIR2018.pdf
 
|Download=ToCite_ECIR2018.pdf
 
|Link=https://link.springer.com/chapter/10.1007%2F978-3-319-76941-7_50
 
|Link=https://link.springer.com/chapter/10.1007%2F978-3-319-76941-7_50

Aktuelle Version vom 17. November 2019, 20:46 Uhr


To Cite, or Not to Cite? Detecting Citation Contexts in Text


To Cite, or Not to Cite? Detecting Citation Contexts in Text



Published: 2018

Buchtitel: Proceedings of the 40th European Conference on Information Retrieval (ECIR 2018)
Seiten: 598--603
Verlag: Springer

Referierte Veröffentlichung

BibTeX

Kurzfassung
[[Abstract::Recommending citations for scientific texts and other texts such as news articles has recently attracted a considerable amount of attention. However, typically, the existing approaches for citation recommendation do not explicitly incorporate the question of whether a given context (e.g., a sentence), for which citations are to be recommended, actually "deserves" citations. Determining the "cite-worthiness" for each potential citation context as a step before the actual citation recommendation is beneficial, as (1) it can reduce the number of costly recommendation computations to a minimum, and (2) it can more closely approximate human-citing behavior, since neither too many nor too few recommendations are provided to the user. In this paper, we present a method based on a convolutional recurrent neural network for classifying potential citation contexts. Our experiments show that we can significantly outperform the baseline solution [1] and reduce the number of citation recommendations to about 1/10.]]

Download: Media:ToCite_ECIR2018.pdf
Weitere Informationen unter: Link



Forschungsgruppe

Web Science


Forschungsgebiet

Information Retrieval, Natürliche Sprachverarbeitung, Künstliche Intelligenz