2016 · 51 citations · 23 references
ComputingComputer ScienceComputational LinguisticsMachine LearningNatural Language ProcessingMeaning RepresentationNatural Language UnderstandingParsingRelation ExtractionSentence ParsingSyntactic AnalysisAbstract Meaning RepresentationAbstract Syntax Tree RepresentationError PropagationJoint Relation ExtractionSemantic Relations Extraction
To alleviate the error propagation in the traditional pipelined models for Abstract Meaning Representation (AMR) parsing, we formulate AMR parsing as a joint task that performs the two subtasks: concept identification and relation identification simultaneously. To this end, we first develop a novel componentwise beam search algorithm for relation identification in an incremental fashion, and then incorporate the decoder into a unified framework based on multiple-beam search, which allows for the bi-directional information flow between the two subtasks in a single incremental model. Experiments on the public datasets demonstrate that our joint model significantly outperforms the previous pipelined counterparts, and also achieves better or comparable performance than other approaches to AMR parsing, without utilizing external semantic resources.
23
Discriminative training methods for hidden Markov models
Michael Collins · 2002 · 1.9K citations · Full text
Abstract Meaning Representation for Sembanking
Laura Banarescu, Claire Bonial, Shu Cai et al. · Edinburgh Research Explorer (University of Edinburgh) · 2013 · 1.1K citations · Full text
Incremental Joint Extraction of Entity Mentions and Relations
Algorithms for Deterministic Incremental Dependency Parsing
Joakim Nivre · Computational Linguistics · 2008 · 449 citations · Full text
Incremental parsing with the perceptron algorithm
Michael Collins, Brian Roark · 2004 · 386 citations · Full text