Text-based Relation Extraction Task
From GM-RKB
(Redirected from relation extraction)
Jump to navigation
Jump to search
A text-based relation extraction task is an text-based information extraction task that requires the extraction of semantic relations.
- AKA: TRET.
- Context:
- It can be supported by: Semantic Parsing from Text, Relation Mention Recognition, Relation Mention Classification, ...
- It can be solved by a Semantic Relation Mention Extraction System (that implements a semantic relation mention extraction algorithm).
- It can range from being a Manual Semantic Relation Extraction Task to being an Automated Semantic Relation Extraction Task.
- It can range from being a Heuristic Relation Mention Extraction Task to being a Data-Driven Relation Mention Extraction Task (such as a supervised relation mention extraction).
- It can range from being a Single-Sentence Textual Relation Extraction Task to being a Multi-Sentence Textual Relation Extraction Task.
- It can range from being a Domain-Specific Textual Relation Extraction Task to being a Common Knowledge-based Textual Relation Extraction Task.
- It can range from being a Simple Relation Extraction Task to being a Complex Relation Extraction Task.
- ...
- Example(s):
- report all of the relations in the 20 Newsgroups Corpus.
- TRET("...") ⇒ ...
- Synonym Extraction.
- Hypernym Extraction.
- ScienceIE-2017 Task, PPLRE Task, SDOI Task, ...
- ...
- Counter-Example(s):
- See: Canonical Record, Relation Mention Annotation, Annotated Text.
References
2006
- (Culotta et al., 2006) ⇒ Aron Culotta, Andrew McCallum, and Jonathan Betz. (2006). "Integrating Probabilistic Extraction Models and Data Mining to Discover Relations and Patterns in Text." In: Proceedings of HLT-NAACL 2006.
- Relation extraction is the task of discovering semantic connections between entities. In text, this usually amounts to examining pairs of entities in a document and determining (from local language cues) whether a relation exists between them. Common approaches to this problem include pattern matching (Brin, 1998; Agichtein and Gravano, 2000), kernel methods (Zelenko et al., 2003; Culotta and Sorensen, 2004; Bunescu and Mooney, 2006), logistic regression (Kambhatla, 2004), and augmented parsing (Miller et al., 2000).