Proceedings of the 55th Annual Meeting of the Association For Computational Linguistics (Volume 1: Long Papers) 2017
DOI: 10.18653/v1/p17-1192
|View full text |Cite
|
Sign up to set email alerts
|

Identifying 1950s American Jazz Musicians: Fine-Grained IsA Extraction via Modifier Composition

Abstract: We present a method for populating fine-grained classes (e.g., "1950s American jazz musicians") with instances (e.g., Charles Mingus). While stateof-the-art methods tend to treat class labels as single lexical units, the proposed method considers each of the individual modifiers in the class label relative to the head. An evaluation on the task of reconstructing Wikipedia category pages demonstrates a >10 point increase in AUC, over a strong baseline relying on widely-used Hearst patterns.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
5
0

Year Published

2018
2018
2022
2022

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 6 publications
(5 citation statements)
references
References 28 publications
0
5
0
Order By: Relevance
“…Most approaches start with a pre-processing step of extracting joint occurrences of the constituents from a corpus to generate a list of candidate paraphrases. Unsupervised methods apply information extraction techniques to find and rank the most meaningful paraphrases (Kim and Nakov, 2011;Xavier and Lima, 2014;Pasca, 2015;Pavlick and Pasca, 2017), while supervised approaches learn to rank paraphrases using various features such as co-occurrence counts (Wubben, 2010;Li et al, 2010;Surtani et al, 2013;Versley, 2013) or the distributional representations of the nouncompounds ( Van de Cruys et al, 2013).…”
Section: Noun-compound Paraphrasingmentioning
confidence: 99%
“…Most approaches start with a pre-processing step of extracting joint occurrences of the constituents from a corpus to generate a list of candidate paraphrases. Unsupervised methods apply information extraction techniques to find and rank the most meaningful paraphrases (Kim and Nakov, 2011;Xavier and Lima, 2014;Pasca, 2015;Pavlick and Pasca, 2017), while supervised approaches learn to rank paraphrases using various features such as co-occurrence counts (Wubben, 2010;Li et al, 2010;Surtani et al, 2013;Versley, 2013) or the distributional representations of the nouncompounds ( Van de Cruys et al, 2013).…”
Section: Noun-compound Paraphrasingmentioning
confidence: 99%
“…Second, previous studies proposed tasks for predicting the semantic properties of predetermined concepts [64] or named entities [52]. However, they assume that particular semantic senses for target concepts or entities are presented in the training set.…”
Section: Related Tasks In Natural Language Processingmentioning
confidence: 99%
“…Finally, there is an enormous body of work aimed at modelling lexical entailment using textonly training data, recently (Shwartz et al, 2016;Chang et al, 2017;Vulić and Mrkšić, 2017;Pavlick and Pasca, 2017;Pavlick et al, 2015). Such work often treats lexical entailment as a supervised learning problem, or at least as a task to which we should tune directly.…”
Section: Related Workmentioning
confidence: 99%