Joint Neural Entity Disambiguation with Output Space Search

In this paper, we present a novel model for entity disambiguation that combines both local contextual information and global evidences through Limited Discrepancy Search (LDS). Given an input document, we start from a complete solution constructed by a local model and conduct a search in the space of possible corrections to improve the local solution from a global view point. Our search utilizes a heuristic function to focus more on the least confident local decisions and a pruning function to score the global solutions based on their local fitness and the global coherences among the predicted entities. Experimental results on CoNLL 2003 and TAC 2010 benchmarks verify the effectiveness of our model.

[1]  Thomas Hofmann,et al.  Deep Joint Entity Disambiguation with Local Neural Attention , 2017, EMNLP.

[2]  Ben Hachey,et al.  Overview of TAC-KBP2014 Entity Discovery and Linking Tasks , 2015 .

[3]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[4]  Nevena Lazic,et al.  Plato: A Selective Context Model for Entity Resolution , 2015, TACL.

[5]  Dan Roth,et al.  Relational Inference for Wikification , 2013, EMNLP.

[6]  Jennifer Widom,et al.  Scaling personalized web search , 2003, WWW '03.

[7]  Avirup Sil,et al.  One for All: Towards Language Independent Named Entity Linking , 2016, ACL.

[8]  Xianpei Han,et al.  A Generative Entity-Mention Model for Linking Entities with Knowledge Base , 2011, ACL.

[9]  Alan Fern,et al.  Structured prediction via output space search , 2014, J. Mach. Learn. Res..

[10]  Fernando Pereira,et al.  Collective Entity Resolution with Multi-Focal Attention , 2016, ACL.

[11]  Robert J. Gaizauskas,et al.  Graph Ranking for Collective Named Entity Disambiguation , 2014, ACL.

[12]  Paolo Ferragina,et al.  TAGME: on-the-fly annotation of short text fragments (by wikipedia entities) , 2010, CIKM.

[13]  Doug Downey,et al.  Local and Global Algorithms for Disambiguation to Wikipedia , 2011, ACL.

[14]  Hiroyuki Shindo,et al.  Joint Learning of the Embedding of Words and Entities for Named Entity Disambiguation , 2016, CoNLL.

[15]  Houfeng Wang,et al.  Learning Entity Representation for Entity Disambiguation , 2013, ACL.

[16]  Ian H. Witten,et al.  Learning to link with wikipedia , 2008, CIKM '08.

[17]  Gourab Kundu,et al.  Neural Cross-Lingual Entity Linking , 2017, AAAI.

[18]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[19]  Xiaolong Wang,et al.  Modeling Mention, Context and Entity with Neural Networks for Entity Disambiguation , 2015, IJCAI.

[20]  Yifan He,et al.  Personalized Page Rank for Named Entity Disambiguation , 2015, NAACL.

[21]  Heng Ji,et al.  Overview of TAC-KBP2015 Tri-lingual Entity Discovery and Linking , 2015, TAC.

[22]  Gerhard Weikum,et al.  Robust Disambiguation of Named Entities in Text , 2011, EMNLP.

[23]  Heng Ji,et al.  Overview of the TAC 2010 Knowledge Base Population Track , 2010 .