Semantic Proto-Roles

By D. Reisinger, Rachel Rudinger, Francis Ferraro, Craig Harman, Kyle Rawlins, Benjamin Van Durme. 2015

93 citations recorded by the source corpus.

We present the first large-scale, corpus based verification of Dowty’s seminal theory of proto-roles. Our results demonstrate both the need for and the feasibility of a property-based annotation scheme of semantic relationships, as opposed to the currently dominant notion of categorical roles.

Subfields: Artificial Intelligence

How researchers see this paper

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

In Artificial Intelligence

Citations in the corpus

BERT Rediscovers the Classical NLP Pipeline (2019, background): “), semantic proto-roles (SPR; Reisinger et al., 2015), and relation classification (SemEval).”
Question-Answer Driven Semantic Role Labeling: Using Natural Language to Annotate Natural Language (2015, methodology): “In the future, we might try to induce the set of possible roles given each target verb, following the semantic role induction work of Titov and Klementiev (2012) and Lang and Lapata (2011), or use crowdsourcing to label proto-roles, following Reisinger et al. (2015).”
Emergent linguistic structure in artificial neural networks trained by self-supervision (2020, background): “‡‡ Results cover semantic dependencies (57), semantic role labeling, and semantic protoroles (58).”
A Survey of the Usages of Deep Learning for Natural Language Processing (2020, background): “None of the results were particularly strong, although they were strongest in SPR.”
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).”
Verb Physics: Relative Physical Knowledge of Actions and Objects (2017, background): “In this, our work can be seen as exploring predicate lexical semantics in the vein of semantic proto-roles (Dowty, 1991; Kako, 2006; Reisinger et al., 2015), but instead affording pairwise, physical relations between roles .”
Asking without Telling: Exploring Latent Ontologies in Contextual Representations (2020, methodology): “Other approaches based on Frame Semantics (Baker et al., 1998; Fillmore et al., 2006), Proto-Roles (Dowty, 1991; Reisinger et al., 2015), or Levin classes (Levin, 1993; Schuler, 2005) have more explicit ﬁne-grained roles.”
Inference is Everything: Recasting Semantic Resources into a Unified Evaluation Framework (2017, methodology): “The SPR dataset Semantic Proto-Role Labeling (SPRL) is the problem of assigning a likelihood value for a particular proto-role property holding of a particular argument of a particular predicate (Reisinger et al., 2015; White et al., 2016; Teichert et al., 2017).”
Crowdsourcing Question-Answer Meaning Representations (2017, methodology): “…also been applied to gather annotations of structure in the setup of multiple choice questions, for example, to recover Dowty’s semantic proto-roles (Reisinger et al., 2015; White et al., 2016) and for human-in-the-loop parsing and classiﬁcation (He et al., 2016; Duan et al., 2016; Werling et al.,…”
Event2Mind: Commonsense Inference on Events, Intents, and Reactions (2018, background): “…to events (Baker et al., 1998; Das et al., 2014; Schuler et al., 2009; Hartshorne et al., 2013, inter alia ), implicitly connoted by events (Reisinger et al., 2015; White et al., 2016; Greene, 2007; Rashkin et al., 2016), or sentiment polarities of events (Ding and Riloff, 2016; Choi and…”
Learning from others' mistakes: Avoiding dataset biases without modeling them (2020, methodology): “We evaluate on SciTail (Khot et al., 2018), GLUE benchmark’s diagnostic test (Wang et al., 2018), AddOneRTE (AddOne) Pavlick & Callison-Burch (2016), Deﬁ-nite Pronoun Resolution (DPR) (Rahman & Ng, 2012), FrameNet+ (FN+) (Pavlick et al., 2015) and Semantic Proto-Roles (SPR) (Reisinger et al., 2015).”
On the Evaluation of Semantic Phenomena in Neural Machine Translation Using Natural Language Inference (2018, background): “Sentence-pairs and labels were recast, i.e. automatically converted, from existing semantic annotations: FrameNet Plus (FN+) (Pavlick et al., 2015), Deﬁnite Pronoun Resolution (DPR) (Rahman and Ng, 2012), and Semantic Proto-Roles (SPR) (Reisinger et al., 2015).”