Jointly identifying predicates, arguments and senses using Markov logic
Published 1 January 2009Open access
Iván Meza, Sebastian Riedel
Citations64
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
A Markov Logic Network for Semantic Role Labelling that jointly performs predicate identification, frame disambiguation, argument identification and argument classification for all predicates in a sentence is presented.
Abstract
In this paper we present a Markov Logic Network for Semantic Role Labelling that jointly performs predicate identification, frame disambiguation, argument identification and argument classification for all predicates in a sentence. Empirically we find that our approach is competitive: our best model would appear on par with the best entry in the CoNLL 2008 shared task open track, and at the 4th place of the closed track---right behind the systems that use significantly better parsers to generate their input features. Moreover, we observe that by fully capturing the complete SRL pipeline in a single probabilistic model we can achieve significant improvements over more isolated systems, in particular for out-of-domain data. Finally, we show that despite the joint approach, our system is still efficient.
Keywords
Computer Science
Machine LearningMarkov logic networks
2,678 Citations2006Matthew Richardson, Pedro Domingos
Experiments with a real-world database and knowledge base in a university domain illustrate the promise of this approach to combining first-order logic and probabilistic graphical models in a single representation.
A maximum-entropy-inspired parser
1,496 Citations2000Eugene Charniak
A new parser for parsing down to Penn tree-bank style parse trees that achieves 90.1% average precision/recall for sentences of length 40 and less and 89.5% when trained and tested on the previously established sections of the Wall Street Journal treebank is presented.
Natural Language EngineeringMaltParser: A language-independent system for data-driven dependency parsing
805 Citations2007Joakim Nivre, Johan Hall +6 more
Experimental evaluation confirms that MaltParser can achieve robust, efficient and accurate parsing for a wide range of languages without language-specific enhancements and with rather limited amounts of training data.
The CoNLL-2008 shared task on joint parsing of syntactic and semantic dependencies
499 Citations2008Mihai Surdeanu, Richard Johansson +3 more
This shared task not only unifies the shared tasks of the previous four years under a unique dependency-based formalism, but also extends them significantly: this year's syntactic dependencies include more information such as named-entity boundaries; the semantic dependencies model roles of both verbal and nominal predicates.
Calibrating Features for Semantic Role Labeling
320 Citations2004Nianwen Xue, Martha Palmer
A critical look at the features used in the semantic role tagging literature is taken and it is shown that the information in the input, generally a syntactic parse tree, has yet to be fully exploited.
Lecture notes in computer scienceUltraconservative Online Algorithms for Multiclass Problems
221 Citations2001Koby Crammer, Yoram Singer
This paper designs and analyzes online classification algorithms for multiclass problems in the mistake bound model and describes a family of additive ultraconservative algorithms where each algorithm in the family updates its prototypes by finding a feasible solution for a set of linear constraints that depend on the instantaneous similarity-scores.
Lifted first-order belief propagation
218 Citations2008Parag Singla, Pedro Domingos
This paper proposes the first lifted version of a scalable probabilistic inference algorithm, belief propagation, based on first constructing a lifted network, where each node represents a set of ground atoms that all pass the same messages during belief propagation.
Joint unsupervised coreference resolution with Markov logic
211 Citations2008Hoifung Poon, Pedro Domingos
This paper presents the first unsupervised approach that is competitive with supervised ones, made possible by performing joint inference across mentions, in contrast to the pairwise classification typically used in supervised methods, and by using Markov logic as a representation language.
Joint learning improves semantic role labeling
182 Citations2005Kristina Toutanova, Aria Haghighi +1 more
This work shows how to build a joint model of argument frames, incorporating novel features that model these interactions into discriminative log-linear models, achieving error reduction of 22% on all arguments and 32% on core arguments over a state-of-the art independent classifier for gold-standard parse trees on PropBank.
Synthesis lectures on human language technologiesSemantic Role Labeling
171 Citations2010Martha Palmer, Daniel Gildea +1 more
This book is aimed at providing an overview of several aspects of semantic role labeling, including the use of joint inference to take advantage of context sensitivities, and attempts to improve performance by closer integration of the syntactic parsing task with semantic roles labeling.
arXiv (Cornell University)Improving the Accuracy and Efficiency of MAP Inference for Markov Logic
163 Citations2012Sebastian Riedel
Generalized inference with multiple semantic role labeling systems
130 Citations2005P. Koomen, Vasin Punyakanok +2 more
An approach to semantic role labeling (SRL) that takes the output of multiple argument classifiers and combines them into a coherent predicate-argument output by solving an optimization problem is presented.
Dependency-based semantic role labeling of PropBank
105 Citations2008Richard Johansson, Pierre Nugues
This work presents a PropBank semantic role labeling system for English that is integrated with a dependency parser and is the first dependency-based semantic role labeler for PropBank that rivals constituent-based systems in terms of performance.
Collective semantic role labelling with Markov logic
56 Citations2008Sebastian Riedel, Iván Meza
This paper presents the system for the Open Track of the CoNLL 2008 Shared Task in Joint Dependency Parsing and Semantic Role Labelling using Markov Logic to define a joint SRL model and achieves a semantic F-score of 74.59%, the second best in the Open track.
Parsing syntactic and semantic dependencies with two single-stage maximum entropy models
41 Citations2008Hai Zhao, Chunyu Kit
It is illustrated that both syntactic parsing and semantic parsing can be transformed into a word-pair classification problem and implemented as a single-stage system with the aid of maximum entropy modeling.
Applying sentence simplification to the CoNLL-2008 shared task
13 Citations2008David Vickrey, Daphne Koller
A high-level overview of the sentence simplification system, which first simplifies each sentence to be labeled using a set of hand-constructed rules to generate simplifications which are as useful as possible for semantic role labeling.