Semantic Role Labeling: An Introduction to the Special Issue

Abstract

Semantic role labeling, the computational identification and labeling of arguments in text, has become a leading task in computational linguistics today. Although the issues for this task have been studied for decades, the availability of large resources and the development of statistical machine learning methods have heightened the amount of effort in this field. This special issue presents selected and representative work in the field. This overview describes linguistic background of the problem, the movement from linguistic theories to computational practice, the major resources that are being used, an overview of steps taken in computational systems, and a description of the key issues and results in semantic role labeling (as revealed in several international evaluations). We assess weaknesses in semantic role labeling and identify important challenges facing the field. Overall, the opportunities and the potential for useful further research in semantic role labeling are considerable.

Semantic Role Labeling of Emotions in Tweets

“…Semantic role labeling (SRL) identifies semantic arguments and roles with regard to a predicate 2 http://www.purl.org/net/NRCEmotionLexicon http://csea.phhp.ufl.edu/media/anewmessage.html in a sentence (Gildea and Jurafsky, 2002;Màrquez et al, 2008;Palmer et al, 2010). More recently, there has also been some work on semantic role labeling of tweets for verb and nominal predicates (Liu et al, 2012;Liu et al, 2011).…”

Generalized Framework for Syntax-Based Relation Mining

“…This makes it possible to mine dependencies between words which are located in distant sentence positions. Such goal can be achieved with very high accuracy, as shown by recent SRL works [3,16].…”

“…The automatically extracted patterns can be eventually used to discover new relations as well as to access the encoded information more conveniently. [3] and more recently [16] present good overviews on state-of-the-art systems for SRL.…”

Detecting Life Events in Feeds from Twitter

“…Hence, we did not run experiments with POS tags. b) Semantic Role Labeling (SRL): For targeted advertising, it is very important to know "who does what": SRL [14] assigns roles to the semantic arguments associated with the predicate. E.g., according to PropBank [15], for marry Arg0 is the causer, whereas Arg1 and Arg2 represent the two married people.…”