[PDF][PDF] Supervised noun phrase coreference research: The first fifteen years
V Ng - Proceedings of the 48th annual meeting of the …, 2010 - aclanthology.org
The research focus of computational coreference resolution has exhibited a shift from
heuristic approaches to machine learning approaches in the past decade. This paper …
heuristic approaches to machine learning approaches in the past decade. This paper …
Machine learning for entity coreference resolution: A retrospective look at two decades of research
V Ng - Proceedings of the aaai conference on artificial …, 2017 - ojs.aaai.org
Though extensively investigated since the 1960s, entity coreference resolution, a core task
in natural language understanding, is far from being solved. Nevertheless, significant …
in natural language understanding, is far from being solved. Nevertheless, significant …
[PDF][PDF] Resolving complex cases of definite pronouns: the winograd schema challenge
We examine the task of resolving complex cases of definite pronouns, specifically those for
which traditional linguistic constraints on coreference (eg, Binding Constraints, gender and …
which traditional linguistic constraints on coreference (eg, Binding Constraints, gender and …
[PDF][PDF] Extracting aspect-evaluation and aspect-of relations in opinion mining
The technology of opinion extraction allows users to retrieve and analyze people's opinions
scattered over Web documents. We define an opinion unit as a quadruple consisting of the …
scattered over Web documents. We define an opinion unit as a quadruple consisting of the …
Targeting sentiment expressions through supervised ranking of linguistic configurations
J Kessler, N Nicolov - Proceedings of the International AAAI Conference …, 2009 - ojs.aaai.org
User generated content is extremely valuable for mining market intelligence because it is
unsolicited. We study the problem of analyzing users' sentiment and opinion in their blog …
unsolicited. We study the problem of analyzing users' sentiment and opinion in their blog …
[PDF][PDF] A cross-lingual ILP solution to zero anaphora resolution
We present an ILP-based model of zero anaphora detection and resolution that builds on
the joint determination of anaphoricity and coreference model proposed by Denis and …
the joint determination of anaphoricity and coreference model proposed by Denis and …
[BOOK][B] Practical structured learning techniques for natural language processing
HC Daume, D Marcu - 2006 - Citeseer
I present an efficient, theoretically justified learning algorithm for structured prediction that
achieves state-of-the-art performance in a wide range of natural language processing …
achieves state-of-the-art performance in a wide range of natural language processing …
Narrowing the modeling gap: A cluster-ranking approach to coreference resolution
Traditional learning-based coreference resolvers operate by training the mention-pair model
for determining whether two mentions are coreferent or not. Though conceptually simple and …
for determining whether two mentions are coreferent or not. Though conceptually simple and …
A new approach to animacy detection
Animacy is a necessary property for a referent to be an agent, and thus animacy detection is
useful for a variety of natural language processing tasks, including word sense …
useful for a variety of natural language processing tasks, including word sense …
[PDF][PDF] Intra-sentential subject zero anaphora resolution using multi-column convolutional neural network
This paper proposes a method for intrasentential subject zero anaphora resolution in
Japanese. Our proposed method utilizes a Multi-column Convolutional Neural Network …
Japanese. Our proposed method utilizes a Multi-column Convolutional Neural Network …