Automatic Labeling of Semantic Roles

  title={Automatic Labeling of Semantic Roles},
  author={Daniel Gildea and Dan Jurafsky},
  journal={Computational Linguistics},
We present a system for identifying the semantic relationships, or semantic roles, filled by constituents of a sentence within a semantic frame. Given an input sentence and a target word and frame, the system labels constituents with either abstract semantic roles, such as Agent or Patient, or more domain-specific semantic roles, such as Speaker, Message, and Topic. The system is based on statistical classifiers trained on roughly 50,000 sentences that were hand-annotated with semantic roles by… 
Automatic Semantic Role Assignment for a Tree Structure
An automatic semantic roles labeling system for structured trees of Chinese sentences that achieves 92.71% accuracy in labeling the semantic roles for pre-structurebracketed texts which is considerably higher than the simple method using probabilistic model of head-modifier relations.
Robust semantic role labeling
This thesis primarily addresses three issues: improving performance on the standard data sets, by using a better machine learning strategy and by incorporating novel features, extending this work to parse arguments of nominal predicates, which also play an important role in conveying the semantics of a passage, and investigating methods to improve the robustness of the classifier across different genre of text.
Semantic role induction in Persian: An unsupervised approach by using probabilistic models
A Bayesian model for learning argument structure from un-annotated text and estimate the model parameters using expectation maximization method is presented and the system in both small and large training datasets works better than a strong baseline proposed by Lang and Lapata 2010.
Labeling Chinese Predicates with Semantic Roles
In this article we report work on Chinese semantic role labeling, taking advantage of two recently completed corpora, the Chinese PropBank, a semantically annotated corpus of Chinese verbs, and the
Methods for seMantic role labeling of russian texts
The paper introduces two methods for semantic role labeling of Russian texts based on semantic dictionary that contains information about predicates, roles and syntaxeme features that correspond to the roles and data-driven semantic-syntactic parsing, which was implemented using MaltParser.
A New Shallow Semantic Parser for Describing the Concept Structure of Text
A shallow semantic parser is developed to add a new layer of semantic annotation of natural language sentences as an extension of SRL, and preliminary evaluation on a manual dataset shows that relations can be extracted with good performance.
A Survey on Semantic Role Labeling and Dependency Parsing
This document attempts to give a brief survey on Dependency Grammar and Parsing which give binary relationships between the words of a text giving clues to their semantic relations.
Semantic Role Labeling Approach for Evaluation of Text Coherence
  • M. Haggag
  • Computer Science
    Int. J. Inf. Retr. Res.
  • 2013
Results proved good capability of the modelling of contextual pattern, addressing semantic roles, to accurately evaluate text coherence and both contextual patterns labeling and coherence evaluation algorithm proposed here are generic, topic free and semantically arbitrated by the global concept within context.
Thematic Role Extraction Using Shallow Parsing
This paper developed a rule based shallow parser to chunk Persian sentences and developed a knowledge-based system to assign 16 selected thematic roles to the chunks to extract semantic roles from Persian sentences.
Generative models for syntactic and semantic structure prediction using latent variables
This work proposes generative models for dependency parsing and semantic role classification, which use inter-connected latent variables to encode the parsing history in the first model, and role correlations in the second model.


The Berkeley FrameNet Project
This report will present the project's goals and workflow, and information about the computational tools that have been adapted or created in-house for this work.
Thematic proto-roles and argument selection
As a novel attack on the perennially vexing questions of the theoretical status of thematic roles and the inventory of possible roles, this paper defends a strategy of basing accounts of roles on
Assigning Function Tags to Parsed Text
This work presents a statistical algorithm for assigning function tags indicating semantic roles and other related information not easily encapsulated in the simple constituent labels that achieves an F-measure of 87%, which rises to 99% when considering 'no tag' as a valid choice.
Understanding natural language
A computer system for understanding English that contains a parser, a recognition grammar of English, programs for semantic analysis, and a general problem solving system based on the belief that in modeling language understanding, it must deal in an integrated way with all of the aspects of language—syntax, semantics, and inference.
Valence Induction with a Head-Lexicalized PCFG
This paper addresses the problem of constructing a lexicon of complementation frames or valences for open-class words by means of a learning tech on probabilistic lexicalized context free grammars and the expectation-maximi~";ation (EM) algorithm.
An Empirical Approach to Conceptual Case Frame Acquisition
A corpus-based algorithm for acquiring conceptual case frames empirically from unannotated text that learns semantic preferences for each extraction pattern and merges the syntactically compatible patterns to produce multi-slot case frames with selectional restrictions.
Head-Driven Statistical Models for Natural Language Parsing
Three statistical models for natural language parsing are described, leading to approaches in which a parse tree is represented as the sequence of decisions corresponding to a head-centered, top-down derivation of the tree.
English Verb Classes and Alternations: A Preliminary Investigation
Beth Levin shows how identifying verbs with similar syntactic behavior provides an effective means of distinguishing semantically coherent verb classes, and isolates these classes by examining verb behavior with respect to a wide range of syntactic alternations that reflect verb meaning.
Statistical Decision-Tree Models for Parsing
SPATTER is described, a statistical parser based on decision-tree learning techniques which constructs a complete parse for every sentence and achieves accuracy rates far better than any published result.
WordNet : an electronic lexical database
The lexical database: nouns in WordNet, Katherine J. Miller a semantic network of English verbs, and applications of WordNet: building semantic concordances are presented.