Procedures As A Representation For Data In A Computer Program For Understanding Natural Language

By Terry Winograd. 1971

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

The Next Decade in AI: Four Steps Towards Robust Artificial Intelligence (2020, background): “The classical AI "blocks world" system SHRLDU, designed by Terry Winograd (mentor to Google founders Larry Page and Sergey Brin) revolved around an internal, updatable cognitive model of the world, that represented the software's understanding of the locations and properties of a set of stacked phys”
Learning to Understand Goal Specifications by Modelling Reward (2018, background): “Indeed, programming rewards to teach robust and general instruction-following may ultimately be as challenging as writing a program to interpret language directly, an endeavour that is notoriously laborious (Winograd, 1971), and some say, ultimately futile (Winograd, 1972).”
Vision-and-Language Navigation: Interpreting Visually-Grounded Navigation Instructions in Real Environments (2017, background): “Navigation and language Natural language command of robots in unstructured environments has been a research goal for several decades [49].”
Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation (2011, background): “Beginning with SHRDLU (Winograd, 1970), many systems have exploited the compositional structure of language to statically generate a plan corresponding to a natural language command (Dzifcak et al., 2009; Hsiao et al., 2008; MacMahon, Stankiewicz, and Kuipers, 2006; Skubic et al., 2004).”
On the Binding Problem in Artificial Neural Networks (2020, background): “problems (Bobrow, 1964), or control simple virtual block worlds (Winograd, 1971).”
Multi-Agent Cooperation and the Emergence of (Natural) Language (2016, background): “ames without a pre-coded protocol. We pursue the same question, but further ask how we can change our environment to make the emergent language more interpretable. Others (e.g., the SHRLDU program of Winograd 1971 or the game in Wang et al. 2016) propose building a communicating AI by putting humans”
A Roadmap Towards Machine Intelligence (2015, background): “This received wisdom suggests that systems should be immediately exposed to real-world problems, so that they don’t get stuck into artificial “blocks worlds” (Winograd, 1971), whose experimenter-designed properties might differ markedly from those characterizing realistic setups.”
Listen, Attend, and Walk: Neural Mapping of Navigational Instructions to Action Sequences (2015, background): “pre-defined environment features and a set of actions [30, 20].”
A Planning Framework for Non-Prehensile Manipulation under Clutter and Uncertainty (2012, unknown): “The blocks-world problem (Winograd 1971) introduced this idea to the AI community.”
PHYRE: A New Benchmark for Physical Reasoning (2019, background): “Work on visual reasoning dates to SHRDLU [56] which probed scene understanding using natural language; more recent benchmarks require systems to answer natural-language questions about images [2, 20].”
Visual Coreference Resolution in Visual Dialog using Neural Module Networks (2018, background): “Though the origins of visual dialog can be traced back to [47,16], it was largely formalized by [13,44] who collected human annotated datasets for the same.”
A Survey of the Usages of Deep Learning for Natural Language Processing (2020, methodology): “Early applications of NLP included a well-acclaimed but simpleminded algebra word problem solver program called STUDENT [272], as well as interesting but severely constrained conversational systems such as Eliza, which acted as a “psychotherapist” [273], and another that conversed about manipulating”