Understanding natural language

By Terry Winograd. 1972

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

A large annotated corpus for learning natural language inference (2015, background): “Some of these examples have qualities reminiscent of Winograd schemas (Winograd, 1972; Levesque, 2013).”
Experience Grounds Language (2020, background): “Many of the phenomena in Winograd (1972)’s Understanding Natural Language require representation of concepts derivable from perception, such as color, counting, size, shape, spatial reasoning, and stability.”
TTTTTackling WinoGrande Schemas (2020, neutral): “While it is certainly true that datasets over-estimate the commonsense reasoning capabilities of modern models [6], there are alternative and complementary explanations as well: It has been a fundamental assumption of the research community that commonsense reasoning is difficult because it comprise”
The Natural Language Decathlon: Multitask Learning as Question Answering (2018, methodology): “Our final task is based on Winograd schemas (Winograd, 1972), which require pronoun resolution: "Joan made sure to thank Susan for the help she had [given/received].”
Teaching Machines to Read and Comprehend (2015, background): “Historically, however, many similar approaches in Computational Linguistics have failed to manage the transition from synthetic data to real environments, as such closed worlds inevitably fail to capture the complexity, richness, and noise of natural language [5].”
A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016, background): “Story understanding is an extremely challenging task in natural language understanding with a long-running history in AI (Charniak, 1972; Winograd, 1972; Turner, 1994; Schubert and Hwang, 2000).”
CommonsenseQA: A Question Answering Challenge Targeting Commonsense Knowledge (2019, background): “Early work sought programs that could reason about an environment in natural language (McCarthy, 1959), or leverage a world-model for deeper language understanding (Winograd, 1972).”
Grounded Language Learning in a Simulated 3D World (2017, background): “Beginning with Winograd (1972), early attempts to ground language understanding in a physical world were constrained by their reliance on the laborious hard-coding of linguistic and physical rules.”
CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning (2016, methodology): “SHRDLU performed simple, interactive visual reasoning with the goal of moving specific objects in the visual scene [40]; this study was one of the first to demonstrate the brittleness of manually programmed semantic understanding.”
Learning Through Dialogue Interactions (2016, background): “The direction of interactive language learning through language games has been explored in the early seminal work of Winograd (Winograd, 1972), and in the recent SHRDLURN system (Wang et al.”
What can the brain teach us about building artificial intelligence? (2016, background): “s in other areas of research explicitly referenced human cognition, and even published papers in cognitive psychology journals (e.g., 6 Bobrow & Winograd, 1977; Hayes-Roth & Hayes-Roth, 1979; Winograd, 1972). For example, Schank (1972), writing in the journal Cognitive Psychology, declared t”
Learning to Understand Goal Specifications by Modelling Reward (2018, methodology): “We experiment with AGILE in a grid world environment that we call GridLU, short for Grid Language Understanding and after the famous SHRDLU world (Winograd, 1972).”
Do As I Can, Not As I Say: Grounding Language in Robotic Affordances (2022, background): “A significant body of work has focused on grounding language [28, 29].”
UNICORN on RAINBOW: A Universal Commonsense Reasoning Model on a New Multitask Benchmark (2021, methodology): “W INO G RANDE (Sakaguchi et al. 2020) takes inspiration from winograd schemas (Winograd 1972; Levesque, Davis, and Morgenstern 2011) to create a large-scale dataset of coreference resolution problems requiring both physical and social common sense.”
Explain Yourself! Leveraging Language Models for Commonsense Reasoning (2019, background): “For example, the Winograd Schemas (Winograd, 1972) and challenges derived from that format (Levesque et al., 2012; McCann et al., 2018; Wang et al., 2018) have proven difﬁcult for even the most modern machine learning methods (Trinh and Le, 2018) to achieve near-human performance, but the emphasis o”
Imitating Interactive Intelligence (2020, background): “Progress towards this goal could greatly expand the scope and naturalness of human-computer interaction (Winograd, 1972; Card et al., 1983; Branwen, 2018) to the point that interacting with a computer or a robot would be much like interacting with another human being – through shared attention, gest”
Unsupervised Question Decomposition for Question Answering (2020, background): “Examples include classical QA systems like SHRDLU (Winograd, 1972) and LUNAR (Woods et al.”
ReferItGame: Referring to Objects in Photographs of Natural Scenes (2014, background): “Referring Expression Generation: There has been a long history of research on understanding how people generate referring expressions, dating back to the 1970s (Winograd, 1972).”
Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions (2013, background): “Finally, the topic of executing instructions in non-learning settings has received significant attention (e.g., Winograd (1972), Di Eugenio and White (1992), Webber et al. (1995), Bugmann et al. (2004), MacMahon et al. (2006) and Dzifcak et al. (2009)).”