Concept Mention Grounding Task
A concept mention grounding task is a mention grounding task that can map a concept mention to a grounded concept mention (with a canonical referencer).
- AKA: Concept Mention Normalization, Concept Mention Linking, Concept Mention Reference Resolution.
- Context:
- It can be solved by a Concept Mention Grounding System (that implements a Concept Mention Grounding algorithm).
- It can range from being a Heuristic Concept Mention Grounding Task to being a Data-Driven Concept Mention Grounding Task.
- It can be, depending on the knowledge base:
- It can be, depending on the Mention Type:
- a Word Mention Reference Resolution Task, if the Concept Mention is restricted to Word Mention.
- an Entity Mention Normalization Task, if the Concept Mentions is restricted to Entity Mention.
- It can support a Concept Mention Annotation Task.
- It can be supported by a Concept Mention Recognition Task.
- …
- Example(s):
- a Wikipedia-based Concept Mention Grounding Task.
- an Ontology-based Concept Mention Grounding Task.
- a Word Mention to Word Sense Resolution Task.
- a Term Mention Resolution Task (i.e. restricted to Term Mentions).
- a Named Entity Mention Grounding Task, such as a Gene Mention Normalization Task.
- a Hyperlinking Task.
- [math]\displaystyle{ f }[/math](
The [articles in Wikipedia] were related to the topic of [grounding the textual entity to a unique database entry]
) ⇒The articles in Wikipedia were related to the topic of grounding the textual entity to a unique database entry
- [math]\displaystyle{ f }[/math](
- Counter-Example(s):
- See: Semantic Annotation Task, Concept Data Record, Word Mention Disambiguation Task.
References
1992
- (Webber et al., 1992) ⇒ Bonnie L. Webber, Norman I. Badler, F. Breckenridge Baldwin, Welton Becket, Barbara Di Eugenio, Christopher W. Geib, Moon Ryul Jung, Libby Levison, Michael B. Moore, and Michael White. (1992). “Doing What You're Told: Following Task Instructions in Changing, but Hospitable Environments." Technical Report, University of Pennsylvania
- QUOTE: Because multi-clause instruction steps may evoke more than one situational context [56], part of an agent's cognitive task in understanding an instruction step is to determine that situation in which he is meant to find a referent for each of its referring expressions. This is the process of grounding referring expressions. … When given this instruction (or similar ones such as "Open the box and hand me the yellow block", which one of the authors (Webber) has publically tested on several individuals), agents appear to develop an expectation that after they perform the action, they will be in a context in which it makes sense to try to ground the expression and determine its referent.
The second instruction (". ..and wash out the coffee urn") is different: if the agent sees a coffee urn in the current context, prior to acting, he will happily ground the referring expression "the coffee urn" against that object. If he doesn't see a coffee urn prior to acting, he develops the same expectation as in the first example, that when he gets into the kitchen, he will be able to ground the expression then. The fact that agents will look around when they get to the kitchen if a coffee urn isn't immediately visible, opening cabinets until they find one, shows the strength of this expectation and the behavior it leads to.
This decision as to the context to use in grounding a referring expression is based on distinguishing the information (and assumptions) used to resolve a referring expression from that used to ground it. Reference resolution precedes reference grounding (cf. Figure 2) and involves using information from the interpretation of the current utterance (i.e., the explicit description), information from the previous discourse (i.e., the existence of a salient discourse entity with that description in the agent's discourse model) [26, 54, 551, and hypotheses about the intended relationship between actions.
- QUOTE: Because multi-clause instruction steps may evoke more than one situational context [56], part of an agent's cognitive task in understanding an instruction step is to determine that situation in which he is meant to find a referent for each of its referring expressions. This is the process of grounding referring expressions. … When given this instruction (or similar ones such as "Open the box and hand me the yellow block", which one of the authors (Webber) has publically tested on several individuals), agents appear to develop an expectation that after they perform the action, they will be in a context in which it makes sense to try to ground the expression and determine its referent.