Automatic Discovery of Part-Whole Relations

By Roxana Girju, Adriana Badulescu, Dan I. Moldovan. International Conference on Computational Logic, 2006

318 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/966f28e435e6a5315e3d7918d3cdf2269f7fa3c8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Distributional Memory: A General Framework for Corpus-Based Semantics (2010, unknown): “Our first test pertains to the seven relations between nominals in Task 4 of SEMEVAL 2007 (Girju et al. 2007): Cause–Effect, Instrument–Agency, Product– Producer, Origin–Entity, Theme–Tool, Part–Whole, Content–Container. For each relation, the data set includes 140 training and about 80 test items. ”
Spatial role labeling with convolutional neural networks (2015, unknown): “Most existing approaches target either a single relation, e.g., PART-WHOLE [11], or relations that hold be-tween arguments following some syntactic construction.”
The Tradeoffs Between Open and Traditional Relation Extraction (2008, methodology): “…extraction patterns is used to seed a bootstrapping process that automatically acquires additional patterns for is-a or part-whole relations (Etzioni et al., 2005; Snow et al., 2005; Girju et al., 2006), It is quite natural then to consider whether the same can be done for all binary relationships.”
Deriving a Large-Scale Taxonomy from Wikipedia (2007, methodology): “We assume that patterns used for identifying meronymic relations (Berland & Charniak, 1999; Girju et al., 2006) indicate that the relation is not an isa relation.”
BabelNet: The automatic construction, evaluation and application of a wide-coverage multilingual semantic network (2012, methodology): “These include proposals to extract semantic information from dictionaries [21,38,115, inter alia], approaches using lexico-syntactic patterns [49,23,43,96], heuristic methods based on lexical and semantic regularities [47], taxonomy-based ontologization [96,103,122].”
Espresso: Leveraging Generic Patterns for Automatically Harvesting Semantic Relations (2006, methodology): “• GI03 : The algorithm by Girju et al. (2006) described in Section 2.”
Extracting and Ranking Product Features in Opinion Documents (2010, background): “There are many phrase or sentence patterns representing this type of semantic relation which was studied in (Girju et al, 2006).”
Deriving a Web-Scale Common Sense Fact Database (2011, background): “Since then, a large range of approaches have built upon these ideas, extending them to other relationships like PartOf (Girju, Badulescu, and Moldovan 2006) as well as factual knowledge like birth dates of people and capital cities (Cafarella et al. 2005).”