Semantic Role Labeling (SRL) Task

A Semantic Role Labeling (SRL) Task is a sentence-level shallow semantic parsing task to predict the predicate-argument structure (with semantic role arguments) associated with each sentence predicate.

• AKA: Thematic Case-Role Analysis, Semantic Frame Labeling,
• Context:
  • Input: A Sentence.
  • output: A set of Word Mention Tuples (one for each sentence predicate) with the Verb and Semantic Role Arguments identified and classified.
  • It can be solved by a Semantic Role Labeling System (that implements a semantic role labeling algorithm).
  • It can range from being a Heuristic SRL Task to being a Data-Driven SRL Task (such as supervised SRL).
  • It can be supported by a Predicate Identification Task (frame identification).
  • It has been shown applicable in several Semantic Role Labeling Applications.
  • It does not capture (higher-order semantic phenomena such as): Coreference, Quantification, ...
  • ...
• Example(s):
  • SRL("He is Swiss.”) ⇒ ([A0 He] [V is] [A1 Swiss]).
  • SRL("He is Swiss and she is Dutch.”) ⇒ ([A0 He] [V is] [A1 Swiss]); ([A0 she] [V is] [A1 Dutch]).
  • SRL("He wouldn't accept anything of value from those he was writing about.”) ⇒ ([A0 He] [AM-MOD would] [AM-NEG n't] [V accept] [A1 anything of value] from [A2 those he was writing about]).
    • where the roles (Rolesets) for the Predicate accept are defined in a PropBank Frame Scheme as: V-verb, A0:acceptor, A1:thing accepted, A2:accepted-from, A3:attribute, AM-MOD:modal, and AM-NEG:negation.
  • …
• Counter-Example(s):
  • an Extra-Propositional Semantic Parsing Task.
  • a Syntactic Sentence Parsing Task.
  • a Shallow Text Understanding Task.
• See: PropBank, Proposition, Target Verb, FrameNet.

---

---

References

2015

• (Wikipedia, 2015) ⇒ http://en.wikipedia.org/wiki/semantic_role_labeling Retrieved:2015-6-21.
  • Semantic role labeling, sometimes also called shallow semantic parsing, is a task in natural language processing consisting of the detection of the semantic arguments associated with the predicate or verb of a sentence and their classification into their specific roles. For example, given a sentence like "Mary sold the book to John", the task would be to recognize the verb "to sell" as representing the predicate, "Mary" as representing the seller (agent), "the book" as representing the goods (theme), and "John" as representing the recipient. This is an important step towards making sense of the meaning of a sentence. A semantic representation of this sort is at a higher-level of abstraction than a syntax tree. For instance, the sentence "The book was sold by Mary to John" has a different syntactic form, but the same semantic roles.

2010

• (Palmer et al., 2010) ⇒ Martha Palmer, Daniel Gildea, and Nianwen Xue. (2010). “Semantic Role Labeling." Morgan & Claypool Publishers. doi:10.2200/S00239ED1V01Y200912HLT006 ISBN:1598298313

2009

• (Poon & Domingos, 2009) ⇒ Hoifung Poon, and Pedro Domingos. (2009). “Unsupervised Semantic Parsing.” In: Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP 2009).
  • Semantic parsing maps text to formal meaning representations. This contrasts with semantic role labeling (Carreras and Marquez, 2004) and other forms of shallow semantic processing, which do not aim to produce complete formal meanings.

• http://www.essex.ac.uk/linguistics/clmt/MTbook/HTML/node98.html
  • A semantic role is a description of the relationship that a constituent plays with respect to the verb in the sentence.
  • The subject of an active sentence is often the agent or experiencer.
  • Other roles include instrumental, benefactive, patient: Peter (experiencer) died. The cat (agent) chased the dog (patient).
• http://verbs.colorado.edu/~mpalmer/projects/ace.html
• http://www.lsi.upc.edu/~srlconll/spec.html

2007

• 2007 SemEval Task #19: Frame Semantic Structure Extraction
  • http://framenet.icsi.berkeley.edu/semeval/FSSE.html

2005a

• (Moreda et al., 2005) ⇒ P. Moreda, B. Navarro, and M. Palomar. (2005). “Using Semantic Roles in Information Retrieval Systems.” In: Proceedings of 10th International Conference on Applications of Natural Language to Information Systems (NLDB-2005).

2005b

• (Palmer et al., 2005) ⇒ Martha Palmer, Daniel Gildea, and P. Kingsbury. (2005). “The Proposition Bank: A Corpus Annotated with Semantic Roles." Computational Linguistics Journal, 31:1.

2005c

• (Carreras & Màrquez, 2005) ⇒ Xavier Carreras, and Lluís Màrquez. (2005). “Introduction to the CoNLL-2005 Shared Task: Semantic role labeling.” In: Proceedings of the Ninth Conference on Computational Natural Language Learning.

2004a

• (Carreras & Marquez, 2004) ⇒ Xavier Carreras and Luis Marquez. (2004). “Introduction to the CoNLL-2004 shared task: Semantic role labeling”. In: Proceedings of the Eighth Conference on Computational Natural Language Learning.

2004b

• (Moschitti, 2004) ⇒ Alessandro Moschitti. (2004). “A Study on Convolution Kernels for Shallow Semantic Parsing.” In: Proceedings of the 42-nd Conference on Association for Computational Linguistic (ACL 2004).

2002

• (Gildea & Jurafsky, 2002) ⇒ Daniel Gildea, and Daniel Jurafsky. (2002). “Automatic Labeling of Semantic Roles.” In: Proceedings of the 38th Annual Conference of the Association for Computational Linguistics (ACL 2000).

2000a

• (Chierchia and McConnell-Ginet, 2000) ⇒ G. Chierchia and S. McConnell-Ginet. (2000). “Meaning and Grammar: An Introduction to Semantics, 2nd Ed." MIT Press.

2000b

• (Jurafsky & Martin, 2000) ⇒ Daniel Jurafsky, and J. H. Martin. (2000). “Speech and Language Processing. Prentice Hall Inc..

1997

• (Payne, 1997) ⇒ Thomas E. Payne. (1997). “Describing morphosyntax: A guide for field linguists.” Cambridge University Press
  • A semantic role is the underlying relationship that a participant has with the main verb in a clause.
  • Also known as: Semantic case, thematic role, theta role (generative grammar), and deep case (case grammar)
  • Discussion: Semantic role is the actual role a participant plays in some real or imagined situation, apart from the linguistic encoding of those situations.
  • Example: If, in some real or imagined situation, someone named John purposely hits someone named Bill, then John is the agent and Bill is the patient of the hitting event. Therefore, the semantic role of Bill is the same (patient) in both of the following sentences:
    • John hit Bill.
    • Bill was hit by John.
  • In both of the above sentences, John has the semantic role of agent.
  • Source http://www.sil.org/linguistics/GlossaryOfLinguisticTerms/WhatIsASemanticRole.htm

1968

• (Fillmore, 1968) ⇒ Charles J. Fillmore. (1968). “The Case for Case.” In: Bach & Harms, editors: "Universals in Linguistic Theory."

---