Difference between revisions of "KBP at TAC"
| Line 1: | Line 1: | ||
Knowledge Base Population (KBP) is a evaluation track at [http://www.nist.gov/tac/ Text Analysis Conference (TAC)], with the goal of explore extraction ability of automated systems to discover information about named entities with reference to an external knowledge source. | Knowledge Base Population (KBP) is a evaluation track at [http://www.nist.gov/tac/ Text Analysis Conference (TAC)], with the goal of explore extraction ability of automated systems to discover information about named entities with reference to an external knowledge source. | ||
| − | + | The evaluation will provide an initial (or reference) knowledge base, along with a document collection that systems are to use to learn from. Attributes (a.k.a., “slots”) derived from [[Wikipedia]] infoboxes are used to create the reference knowledge base, as the evaluation [[Category::dataset]]. | |
== Task Description == | == Task Description == | ||
| + | |||
| + | [http://nlp.cs.qc.cuny.edu/kbp/2011/KBP2011_TaskDefinition.pdf Task Description for Knowledge-Base Population at TAC 2011] | ||
| + | |||
=== Entity Linking === | === Entity Linking === | ||
Align names to entities in the knowledge. | Align names to entities in the knowledge. | ||
=== Slot Filling === | === Slot Filling === | ||
| − | + | Slot Filling task requires mining information about entities from free text. It can be viewed as more traditional Information Extraction (IE), or alternatively, as a Question Answering (QA) task, where the questions are static but the targets change. | |
== Relevant Papers == | == Relevant Papers == | ||
Revision as of 00:22, 30 September 2011
Knowledge Base Population (KBP) is a evaluation track at Text Analysis Conference (TAC), with the goal of explore extraction ability of automated systems to discover information about named entities with reference to an external knowledge source.
The evaluation will provide an initial (or reference) knowledge base, along with a document collection that systems are to use to learn from. Attributes (a.k.a., “slots”) derived from Wikipedia infoboxes are used to create the reference knowledge base, as the evaluation dataset.
Task Description
Task Description for Knowledge-Base Population at TAC 2011
Entity Linking
Align names to entities in the knowledge.
Slot Filling
Slot Filling task requires mining information about entities from free text. It can be viewed as more traditional Information Extraction (IE), or alternatively, as a Question Answering (QA) task, where the questions are static but the targets change.
