Resolving Complex Cases of Definite Pronouns: The Winograd Schema Challenge

By Altaf Rahman, Vincent Ng. 2012

216 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

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer (2019, methodology): “[2019] we also include the Definite Pronoun Resolution (DPR) dataset [Rahman and Ng, 2012] in the combined SuperGLUE task.”
A Simple Method for Commonsense Reasoning (2018, background): “In particular, Rahman and Ng [25] employ human annotators to build more supervised training data.”
A Surprisingly Robust Trick for the Winograd Schema Challenge (2019, methodology): “Here, we refer to the most popular collection of such sentences as W SC 273, to avoid confusion with other slightly modiﬁed datasets, such as P DP 60, (Davis et al., 2017) and the Deﬁnite Pronoun Resolution dataset (Rahman and Ng, 2012), denoted W SC R in the sequel.”
Finetuned Language Models Are Zero-Shot Learners (2021, neutral): “DPR (Rahman & Ng, 2012) 2.”
Hypothesis Only Baselines in Natural Language Inference (2018, methodology): “The DPR dataset targets an NLI model’s ability to perform anaphora resolution (Rahman and Ng, 2012).”
Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods (2018, methodology): “This dataset follows the winograd format (Hirst, 1981; Rahman and Ng, 2012; Peng et al., 2015b), and contains references to people using a vocabulary of 40 occupations.”
What do you learn from context? Probing for sentence structure in contextualized word representations (2019, methodology): “We use the version of the Deﬁnite Pronoun Resolution (DPR) dataset (Rahman & Ng, 2012) employed by White et al. (2017), which contains balanced positive and negative pairs.”
Cosmos QA: Machine Reading Comprehension with Contextual Commonsense Reasoning (2019, background): “…common-sense, such as CommonsenseQA (Talmor et al., 2018) and Social IQa (Sap et al., 2019), and various other types of commonsense inferences (Levesque et al., 2012; Rahman and Ng, 2012; Gordon, 2016; Rashkin et al., 2018; Roemmele et al., 2011; Mostafazadeh et al., 2017; Zellers et al., 2018).”
Intermediate-Task Transfer Learning with Pretrained Language Models: When and Why Does It Work? (2020, background): “The Definite Pronoun Resolution dataset (Rahman and Ng, 2012) (EPDPR) is a task that tests a model’s ability to handle coreference, and differs from OntoNotes in that it focuses on difficult cases of definite pronouns.”
Solving Hard Coreference Problems (2019, methodology): “A lot of recent work has attempted to utilize similar types of resources to improve coreference resolution (Rahman and Ng, 2011a; Ratinov and Roth, 2012; Bansal and Klein, 2012; Rahman and Ng, 2012).”
Language Models are General-Purpose Interfaces (2022, background): “• Coreference Resolution is to determine if two expressions refer to the same entity in a text: DPR (Rahman and Ng, 2012), Winogrande (Sakaguchi et al., 2020), WSC (Levesque et al., 2012).”
How Reasonable are Common-Sense Reasoning Tasks: A Case-Study on the Winograd Schema Challenge and SWAG (2018, unknown): “For example, in “The lions ate the zebras because they are predators” (Rahman and Ng, 2012), the pronoun they can be resolved to lions on the basis of a much stronger association of lions with predators than of zebras with predators.”
Commonsense Reasoning for Natural Language Understanding: A Survey of Benchmarks, Resources, and Approaches (2019, methodology): “…coreference resolution are typically handcrafted or handpicked (Morgenstern, Davis, & Ortiz, 2016; Rahman & Ng, 2012; Rudinger et al., 2018a), there exists a small magnitude of data for this skill, and it remains an unsolved problem (Rahman & Ng, 2012; Davis, Morgenstern, & Ortiz, 2017).”
WinoWhy: A Deep Diagnosis of Essential Commonsense Knowledge for Answering Winograd Schema Challenge (2020, methodology): “In our experiments, we evaluate the combination of different pre-trained models and ﬁne-tuning datasets, and denote them as BERT (base/large) + WSCR/Grande and RoBERTa (base/large) + WSCR/Grande respectively.”