In this paper we present the MicroNeel system for Named Entity Recognition and Entity Linking on Italian microposts, which participated in the NEELIT task at EVALITA 2016. MicroNeel combines The Wiki Machine and Tint, two standard NLP tools, with comprehensive tweet preprocessing, the Twitter- DBpedia alignments from the Social Media Toolkit resource, and rule-based or supervised merging of produced annotations.
In this paper we present the MicroNeel system for Named Entity Recognition and Entity Linking on Italian microposts, which participated in the NEELIT task at EVALITA 2016. MicroNeel combines The Wiki Machine and Tint, two standard NLP tools, with comprehensive tweet preprocessing, the Twitter- DBpedia alignments from the Social Media Toolkit resource, and rule-based or supervised merging of produced annotations.
MicroNeel: Combining NLP Tools to Perform Named Entity Detection and Linking on Microposts / Corcoglioniti, Francesco; Palmero Aprosio, Alessio; Nechaev, Yaroslav; Giuliano, Claudio. - 1749:(2016). ( 3rd Italian Conference on Computational Linguistics, CLiC-it 2016 and 5th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian, EVALITA 2016 Napoli, Italia 5th-7th December 2016).
MicroNeel: Combining NLP Tools to Perform Named Entity Detection and Linking on Microposts
Corcoglioniti, Francesco;Palmero Aprosio, Alessio;Nechaev, Yaroslav;
2016-01-01
Abstract
In this paper we present the MicroNeel system for Named Entity Recognition and Entity Linking on Italian microposts, which participated in the NEELIT task at EVALITA 2016. MicroNeel combines The Wiki Machine and Tint, two standard NLP tools, with comprehensive tweet preprocessing, the Twitter- DBpedia alignments from the Social Media Toolkit resource, and rule-based or supervised merging of produced annotations.| File | Dimensione | Formato | |
|---|---|---|---|
|
paper_010 (1).pdf
accesso aperto
Tipologia:
Versione editoriale (Publisher’s layout)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
521.95 kB
Formato
Adobe PDF
|
521.95 kB | Adobe PDF | Visualizza/Apri |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione
