Semantic Role Labeling


Several Natural Language Processing (NLP) tasks, such as Information Extraction, Question Answering or Dialogue, require semantic interpretation of arbitrary texts. Paradigms proposed as meta-models of semantic structures include frame semantics (Fillmore, 1985). According to this theory, frames are linguistic predicates providing a semantic description of real world situations. A frame is evoked in a sentence through specific lexical units (lu), i.e. words (such as nouns or verbs). A frame characterizes the set of semantic roles, i.e. semantic arguments called Frame Elements (FE), describing all participants to the event. For example, the following sentence evokes the KILLING frame, through the lu “kill”, while four FEs, i.e. TIME (yesterday), KILLER (a robber), VICTIM (a guardian) and INSTRUMENT (with a knife), are emphasized in the underlying frame:

[Yesterday]TIME, [a robber]KILLER killed [a guardian]VICTIM [with a knife]INSTRUMENT .

The task of automatic recognizing predicates and FEs in sentences is called Semantic Role Labeling (SRL)(Gildea and Jurafsky, 2002) (Palmer et al, 2010), recently pushed by the FrameNet project that made available a large set of annotated sentences from the British National Corpus (BNC).

In our group we investigate two main Machine Learning approaches to SRL based on Structured Learning paradigms:

  • one approach is based on a novel formulation of Convolution Kernels, namely the Smoothed Partial Tree Kernel that models semantic roles by implicitly combining syntactic and lexical information of annotated examples.
  • one approach  realizes a flexible approach based on the Markovian formulation of the SVM learning algorithm, i.e. SVM-HMM by modeling the SRL problem a sequential tagging problem. A demo system called BABEL has been implemented on this latter approach and it is described in this page.

Results in line with the state-of-the-art have been achieved with both approaches both in English and Italian languages.


Roberto BasiliDanilo CroceGiuseppe CastellucciEmanuele Bastianelli


Fillmore, Charles J., Frames and the semantics of understanding. Quaderni di Semantica. 6: 222-254 (1985)

Gildea, D., Jurafsky, D.: Automatic Labeling of Semantic Roles. Computational Linguistics 28(3), 245–288 (2002)

Palmer, M., Gildea, D., Xue, N.: Semantic Role Labeling. Synthesis Lectures on Human Language Technologies, Morgan & Claypool Publishers (2010)

SAG Publications

Danilo Croce, Valerio Storch, Paolo Annesi, Roberto Basili (2012): Distributional Compositional Semantics and Text Similarity. In: ICSC, pp. 242-249, 2012.

Danilo Croce, Roberto Basili (2011): Structured Learning for Semantic Role Labeling. In: AI*IA, pp. 238-249, 2011.

Danilo Croce, Cristina Giannone, Paolo Annesi, Roberto Basili (2010): Towards Open-Domain Semantic Role Labeling. In: ACL, pp. 237-246, 2010.

Cristina Giannone, Danilo Croce, Roberto Basili (2009): Semantic Word Spaces for Robust Role Labeling. In: ICMLA, pp. 261-266, 2009.

Alessandro Moschitti, Daniele Pighin, Roberto Basili (2008): Tree kernels for semantic role labeling. In: Computational Linguistics, 34 (2), pp. 193–224, 2008.

Alessandro Moschitti, Ana-Maria Giuglea, Bonaventura Coppola, Roberto Basili (2005): Hierarchical semantic role labeling. In: Proceedings of the Ninth Conference on Computational Natural Language Learning, pp. 201–204, Association for Computational Linguistics 2005.