The role of veridicality and factivity in clause selection *

By Aaron Steven White, Kyle Rawlins. 2017

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

Right for the Wrong Reasons: Diagnosing Syntactic Heuristics in Natural Language Inference (2019, background): “Several past works (Pavlick and Callison-Burch, 2016; Rudinger et al., 2018; White et al., 2018; White and Rawlins, 2018) have studied such behavior for verbs (e.g., He knows it is raining entails It is raining , while He believes it is raining does not).”
Inherent Disagreements in Human Textual Inferences (2019, methodology): “In the third example, from DNC and derived from the MegaVerdicality dataset (White and Rawlins, 2017), there appears to be disagreement about the”
Commonsense Reasoning for Natural Language Understanding: A Survey of Benchmarks, Resources, and Approaches (2019, unknown): “While binary-choice tasks should have a 50% majority class baseline, the MegaVeridicality task within DNC (Poliak et al., 2018a) has a 67% majority-class baseline due to unevenly distributed class labels, leaving significantly less room for incremental improvement than tasks with lower-performing ba”
Collecting Diverse Natural Language Inference Problems for Sentence Representation Evaluation (2018, unknown): “Even though we categorize VerbNet, MegaVeridicality, and VerbCorner as lexicosyntatic inference, we train and evaluate models separately on these three datasets because we use different strategies to individually recast them.”
Lexicosyntactic Inference in Neural Models (2018, methodology): “To do this, we substantially extend the MegaVeridicality1 dataset (White and Rawlins, 2018) to cover all English clause-embedding verbs in a variety of the syntactic contexts covered by recent psycholinguistic work (White and Rawl-ins, 2016), and we use the resulting dataset – MegaVeridicality2 –…”