The NomBank Project: An Interim Report

By Adam Meyers, Ruth Reeves, Catherine Macleod, Rachel Szekely, Veronika Zielinska, Brian Young, Ralph Grishman. FCP@NAACL-HLT, 2004

384 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/255d6867cb5c57810c909d5e488c9ae86e0d6d3e

How researchers see this paper

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

Citations in the corpus

A Joint Model for Extended Semantic Role Labeling (2011, methodology): “In the literature, semantic role extraction has been studied mostly in the context of verb predicates, us-ing the Propbank annotation of Palmer et al. (2005), and also for nominal predicates, using the Nombank corpus of Meyers et al. (2004).”
The First Multilingual Surface Realisation Shared Task (SR’18): Overview and Evaluation Results (2018, methodology): “Edge labels were generalised into predicate/argument labels, in the PropBank/NomBank (Palmer et al., 2005; Meyers et al., 2004) fashion.”
Question Answering as Global Reasoning Over Semantic Abstractions (2018, unknown): “Many SRL systems have been designed (Gildea and Jurafsky 2002; Punyakanok, Roth, and Yih 2008) using linguistic resources such as FrameNet (Baker, Fillmore, and Lowe 1998), PropBank (Kingsbury and Palmer 2002), and NomBank (Meyers et al. 2004).”
Special Issue Introduction: Semantic Role Labeling: An Introduction to the Special Issue (2008, unknown): “Recently, medium-to-large corpora have been manually annotated with semantic roles in FrameNet (Fillmore, Ruppenhofer, and Baker 2004), PropBank (Palmer, Gildea, and Kingsbury 2005), and NomBank (Meyers et al. 2004), enabling the development of statistical approaches speciﬁcally for SRL.”
CogCompNLP: Your Swiss Army Knife for NLP (2018, unknown): “, 2004) NomBank (Meyers et al., 2004) F1 – 66.”
Greedy, Joint Syntactic-Semantic Parsing with Stack LSTMs (2016, methodology): “, 2005) and NomBank (Meyers et al., 2004).”
A Latent Variable Model of Synchronous Parsing for Syntactic and Semantic Dependencies (2008, methodology): “…the CoNLL 2008 shared task sets the challenge of learning jointly both syntactic dependencies (extracted from the Penn Treebank (Marcus et al., 1993) ) and semantic dependencies (extracted both from PropBank (Palmer et al., 2005) and NomBank (Meyers et al., 2004) under a uni-ﬁed representation.”
Abstract Meaning Representation for Sembanking (2013, methodology): “It would be reasonable in such cases to use a NomBank (Meyers et al., 2004) noun frame with appropriate slots.”
The CoNLL-2009 Shared Task: Syntactic and Semantic Dependencies in Multiple Languages (2009, methodology): “• NomBank - NomBank annotation (Meyers et al., 2004) uses essentially the same framework as PropBank to annotate arguments of nouns.”
The CoNLL 2008 Shared Task on Joint Parsing of Syntactic and Semantic Dependencies (2008, methodology): “NomBank annotation (Meyers et al., 2004) uses essentially the same framework as PropBank to annotate arguments of nouns.”
A Discourse Commitment-Based Framework for Recognizing Textual Entailment (2007, methodology): “In our system, text-hypothesis ( t-h ) pairs are initially submitted to a Preprocessing module which (1) syntactic parses each passage (using an implementation of the (Collins, 1999) parser), (2) iden-tiﬁes semantic dependencies (using a semantic dependency parser trained on PropBank (Palmer et al.,”
Crowdsourcing Question-Answer Meaning Representations (2017, methodology): “…structure are well-developed for verbs (e.g. Prop-Bank (Palmer et al., 2005) and FrameNet (Baker et al., 1998)) and there have been efforts to study other parts of speech (e.g. NomBank (Meyers et al., 2004)) and introduce whole-sentence structures (e.g. AMR (Banarescu et al., 2013)).”
Semantic Frame Identification with Distributed Word Representations (2014, result): “Second, we present results on PropBank-style semantic role labeling (Palmer et al., 2005; Meyers et al., 2004; M`arquez et al., 2008), that approach strong baselines, and are on par with prior state of the art (Punyakanok et al., 2008).”
FORGe at SemEval-2017 Task 9: Deep sentence generation based on a sequence of graph transducers (2017, methodology): “For this task, we use a valency (subcategorization) lexicon built automatically from PropBank (Kingsbury and Palmer, 2002) and NomBank (Meyers et al., 2004); see (Mille and Wanner, 2015).”
Resource Interoperability for Sustainable Benchmarking: The Case of Events (2018, background): “Section 4 reviews metadata-level interoperability across these corpora and shows their overlap in documents, after which we focus on a subset: PropBank/NomBank (PB/NB), FactBank (FB) and TempEval-3 (TE3).”
The First Surface Realisation Shared Task: Overview and Evaluation Results (2011, methodology): “The resulting dependency bank was then merged with the Nombank (Meyers et al., 2004) and Propbank (Palmer et al., 2005) corpora.”
Semantic Role Labeling (2010, unknown): “However, this chapter may still be considered incomplete as some architectures exploiting advanced machine learning techniques, for example, kernel methods (Moschitti 2004), are not reported.”
Unsupervised Entity Linking with Abstract Meaning Representation (2015, methodology): “We combined two systems (Chen and Ji, 2011; Cheng and Roth, 2013) Human SRL using human annotated core semantic roles deﬁned in Prop-Bank (Palmer et al., 2005) and NomBank (Meyers et al., 2004) context coherence method is used where possible (i.e., those 215 mentions that are members of coherent set”
FactBank: a corpus annotated with event factuality (2009, background): “For example, the agreement of identifying semantic roles of nominal predicates is about 85% for argument roles, lower for adjuncts (Meyers et al. 2004); identifying both argument and adjunct roles for verbs leads to js&c 1⁄4 0:91 (Palmer et al.”