Relation Extraction Using Distant Supervision

By Alisa Smirnova, Philippe Cudré-Mauroux. 2018

103 citations recorded by the source corpus.

Relation extraction is a subtask of information extraction where semantic relationships are extracted from natural language text and then classified. In essence, it allows us to acquire structured knowledge from unstructured text. In this article, we present a survey of relation extraction methods that leverage pre-existing structured or semi-structured data to guide the extraction process. We introduce a taxonomy of existing methods and describe distant supervision approaches in detail. We describe, in addition, the evaluation methodologies and the datasets commonly used for quality assessment. Finally, we give a high-level outlook on the field, highlighting open problems as well as the most promising research directions.

Subfields: Artificial Intelligence

Citations in the corpus

• Knowledge Graphs (2020, unknown): “Other learning-based approaches again use bootstrapping [78, 148] and distant supervision [244, 355, 439, 486, 511, 565] to forgo the need for manual labelling; the former requires a subset of manually-labelled seed examples, while the latter finds sentences in a large corpus of text mentioning pair”