Reference Grounding Task

A Reference Grounding Task is a coreference clustering task that is a multiclass classification task (that requires the classification of a referencer to a canonical referencer with the same referent).

• AKA: Symbol Resolution, Referencer Normalization, Referencer Disambiguation.
• Context:
  • Input:
    • a Referencer (along with Context Information/Reference Information).
    • a Canonical Referencer Sets.
  • output: a Grounded Referencer.
  • Task Performance: Accuracy, Precision, Recall, F-Measure.
  • It can range from being an Entity Reference Grounding Task to being a Relationship Reference Grounding Task.
  • It can be solved by a Reference Resolution System (that implements a reference resolution algorithm).
  • It can range from being a Heuristic Reference Grounding Task to being a Data-Driven Reference Grounding Task (such as supervised reference grounding).
  • It can support Semantic Annotation.
• Example(s):
  • an Entity Mention Grounding Task.
  • a Word Sense Disambiguation Task/Word Sense Normalization Task.
  • an Entity Record Normalization Task.
  • a Relation Mention Grounding Task.
  • a Pointing Reference Resolution Task.
  • an Image Reference Resolution Task.
  • a Taxonomy-based Grounding Task.
  • …
• Counter-Example(s):
  • a Coreference Resolution Task, because it is not being mapped to a canonical record..
  • a Referencer Detection Task.
  • an Entity Mention Recognition Task.
  • an Entity Record Deduplication Task.
• See: Shallow Semantic Analysis, Ground Fact, Grounding Task, Data Preparation.

---

---

References

2011

• (Bhattacharya & Getoor, 2011) ⇒ Indrajit Bhattacharya; Lise Getoor. (2011). “Entity Resolution.” In: (Sammut & Webb, 2011) p.321

2009

• (Wikipedia, 2009) ⇒ http://en.wikipedia.org/wiki/Symbol_grounding
  • The Symbol Grounding Problem is related to the problem of how words (symbols) get their meanings, and hence to the problem of what meaning itself really is. The problem of meaning is in turn related to the problem of consciousness, or how it is that mental states are meaningful. According to a widely held theory of cognition, “computationalism," cognition (i.e., thinking) is just a form of computation. But computation in turn is just formal symbol manipulation: symbols are manipulated according to rules that are based on the symbols' shapes, not their meanings. How are those symbols (e.g., the words in our heads) connected to the things they refer to? It cannot be through the mediation of an external interpreter's head, because that would lead to an infinite regress, just as my looking up the meanings of words in a (unilingual) dictionary of a language that I do not understand would lead to an infinite regress. The symbols in an autonomous hybrid symbolic+sensorimotor system -- a Turing-scale robot consisting of both a symbol system and a sensorimotor system that reliably connects its internal symbols to the external objects they refer to, so it can interact with them Turing-indistinguishably from the way a person does -- would be grounded. But whether its symbols would have meaning rather than just grounding is something that even the robotic Turing Test -- hence cognitive science itself -- cannot determine, or explain.
• (WordNet, 2009) ⇒ http://wordnetweb.princeton.edu/perl/webwn?s=resolve
  • S: (v) answer, resolve (understand the meaning of) "The question concerning the meaning of life cannot be answered"
  • S: (v) resolve (make clearly visible) "can this image be resolved?"
  • …

2008

• (Masse et al., 2008) ⇒ Blondin Masse, A, G. Chicoisne, Y. Gargouri, Stevan Harnad, O. Picard, and O. Marcotte. (2008). “How Is Meaning Grounded in Dictionary Definitions?.” In: TextGraphs-3 Workshop, 22nd International Conference on Computational Linguistics (Coling 2008).

2007

• (Witte et al., 2007) ⇒ René Witte, Thomas Kappler, and Christopher J. O. Baker. (2007). “Ontology Design for Biomedical Text Mining." Book Chapter in: Semantic Web". doi:10.1007/978-0-387-48438-9
  • As a final step in NE detection, many entities need to be grounded with respect to an external resource, like an database. This is especially important for most biological entities, which have corresponding entries in various databases, e.g., Swiss-Prot for proteins. When further information is needed for downstream analysis tasks, like the automatic processing of amino acid sequences, grounding the textual entity to a unique database entry (e.g., assigning a Swiss-Prot ID to a protein entity) is a mandatory prerequisite. Thus, even if an entity is correctly detected from an NLP perspective, it might still be ambiguous with respect to such an external resource (or not exist at all), which makes it useless for further automated processing until the entity has been grounded.

2005

• (Taddeo & Floridi, 2005) ⇒ Mariarosaria Taddeo, and Luciano Floridi (2005). “The symbol grounding problem: A critical review of fifteen years of research. Journal of Experimental and Theoretical Artificial Intelligence, 17(4), 419-445. Online version

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.

1991

• (Clark & Brennan, 1991) ⇒ Herberth H. Clark, and Susan E. Brennan. (1991). “Grouding in Communication.” In: L.B. Resnick, J.M. Levine, & S.D. Teasley (Eds.). Perspectives on socially shared cognition . Washington: APA Books.
  • QUOTE: Grounding is essential to communication. Once we have formulated a message, we must do more than just send it off. We need to assure ourselves that it has been understood as we intended it to be. Otherwise, we have little assurance that the discourse we are taking partin will proceed in an orderly way. For whatever we say, our goal is to reach the grounding criterion: that we and our addressees mutuallybelieve that they have understood what we meant well enought for current purposes. This is the process that we have called grounding.

1990

• (Harnad, 1990) ⇒ Stevan Harnad. (1990). “The Symbol Grounding Problem.” In: Physica D, 42.

1984

• (Pylyshin, 1984) ⇒ Z. W. Pylyshyn. (1984). “Computation and Cognition.” Cambridge MA: MIT/Bradford

1981

• (Clark & Marshall, 1981) ⇒ Herberth H. Clark & C. R. Marshall. (1981). “Definite Reference and Mutual Knowledge.” In: Aravind K. Joshi, B. L. Webber, & I. A. Sag (Eds.). “Elements of discourse understanding.” Cambridge University Press.

1980

• (Searle, 1980) ⇒ John R. Searle. (1980). “Minds, Brains, and Programs.” In: Behavioral and Brain Sciences, 3(3)

1975

• (Fodor, 1975) ⇒ J. A. Fodor. (1975). “The Language of Thought.” Thomas Y. Crowell

1969a

• (Lewis, 1969) ⇒ D. K. Lewis. (1969). “Convention: A philosophical study.” Harvard University Press.

1969b

• (Searle, 1969) ⇒ John R. Searle. (1969). “Speech Acts.” Cambridge University Press.

1917

• (Russell, 1917) ⇒ Bertrand Russell. (1917). “Knowledge by Acquaintance and Knowledge by Description.” In: Mysticism and Logic.

1905

• (Russell, 1905) ⇒ Bertrand Russell. (1905). “On Denoting.” In: Mind 14: 479-93.

1892

• (Frege, 1892) ⇒ Gottlob Frege. (1892). “On Sense and Reference.” In: Zeitschrift für Philosophie und philosophische Kritik, C: 25-50.

---