Universal Conceptual Cognitive Annotation (UCCA)

By Omri Abend, Ari Rappoport. 2013

233 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

Citations in the corpus

Break It Down: A Question Understanding Benchmark (2020, background): “, 1994; Zelle and Mooney, 1996; Abend and Rappoport, 2013; Yu et al., 2018). Recent work has focused on cheaply eliciting quality annotations from nonexperts through crowdsourcing (He et al., 2016; Iyer et al., 2017; Michael et al., 2018). FitzGerald et al. (2018) facilitated non-expert annotation b”
Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language (2015, background): “The UCCA foundational layer does not distinguish semantic roles, so Frogs eat herons and Herons eat frogs will receive identical annotation — thereby discarding information which is potentially useful for translation or question answering.”
Results of the WMT16 Metrics Shared Task (2016, background): “UCCA (Abend and Rappoport, 2013) is an appealing candidate for semantic analysis, due to its crosslinguistic applicability, support for rapid annotation, and coverage of many fundamental semantic phenomena, such as verbal, nominal and adjectival argument structures and their interrelations.”
Results of the WMT17 Metrics Shared Task (2017, background): “UCCA (Abend and Rappoport, 2013) is an appealing candidate for semantic analysis, due to its cross-linguistic applicability, support for rapid annotation, and coverage of many fundamental semantic phenomena, such as verbal, nom-6 inal and adjectival argument structures and their inter-relations.”
A Survey on Semantic Parsing (2018, methodology): “Examples of graph based formalisms are AMR, Universal Conceptual Cognitive Annotation (UCCA) [Abend and Rappoport, 2013], Semantic Dependency Parsing [Oepen et al., 2015] etc. Recently, Kollar et al. [2018] introduced the Alexa Meaning Representation language that aims to capture the meaning of…”
Recent Advances in Natural Language Processing via Large Pre-trained Language Models: A Survey (2021, background): “Universal Conceptual Cognitive Annotation (Abend and Rappoport, 2013) (7)Abstract Meaning Representation (Banarescu et al.”
Syntactic Scaffolds for Semantic Structures (2018, methodology): “Contemporaneously with this work, Hershcovich et al. (2018) proposed a multitask learning setting for universal syntactic dependencies and UCCA semantics (Abend and Rappoport, 2013).”
Crowdsourcing Question-Answer Meaning Representations (2017, methodology): “Other linguistically motivated annotation schemes include UCCA (Abend and Rappoport, 2013), HSPG tree-banks (Flickinger et al., 2017), and the Groningen meaning bank (Basile et al., 2012).”
A Comprehensive Survey of Grammar Error Correction (2020, methodology): “Finally, based on UCCA scheme [134], 𝑈𝑆 𝐼𝑀 is a reference-less measure of semantic faithfulness which compares the differences between the UCCA structures of outputs and source sentences according to alignable but different tokens.”
Large-Scale QA-SRL Parsing (2018, background): “Some more recent semantic resources require less annotator training, or can be crowdsourced (Abend and Rappoport, 2013; Reisinger et al., 2015; Basile et al., 2012; Michael et al., 2018).”
Broad-Coverage Semantic Parsing as Transduction (2019, background): “Universal Conceptual Cognitive Annotation (UCCA; Abend and Rappoport, 2013) targets a level of semantic granularity that abstracts away from syntactic paraphrases in a typologically-motivated, cross-linguistic fashion.”
Where’s My Head? Definition, Data Set, and Models for Numeric Fused-Head Identification and Resolution (2019, methodology): “The UCCA semantic representation (Abend and Rappoport, 2013) explicitly marks missing information, including the REFERENCE NFH cases, but not the IMPLICIT ones.”
Controlled Crowdsourcing for High-Quality QA-SRL Annotation (2019, methodology): “Abend and Rappoport (2013). Overall consistency of the dataset is assessed by measuring agreement between different consolidated annotations, obtained by disjoint triplets of workers, which achieves F1 of 84.”
Practical Semantic Parsing for Spoken Language Understanding (2019, background): “, 2005), and general purpose meaning representations (Banarescu et al., 2013; Abend and Rappoport, 2013).”