Introduction to "This is Watson"

By David A. Ferrucci. 2012

518 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Information Systems, Question Answering & Reading Comprehension

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

In Information Systems

In Question Answering & Reading Comprehension

Citations in the corpus

Autoregressive Entity Retrieval (2020, background): “The ability to retrieve the correct entity from large Knowledge Bases (KBs) given a textual input is a fundamental building block for several applications (Ferrucci, 2012; Slawski, 2015; Yang et al., 2018a).”
DeepStack: Expert-level artificial intelligence in heads-up no-limit poker (2017, background): “, backgammon (1), checkers (2), chess (3), Jeopardy! (4), Atari video games (5), and go (6).”
Making Neural QA as Simple as Possible but not Simpler (2017, background): “Traditional statistical QA systems (e.g., Ferrucci (2012)) relied on linguistic pre-processing pipelines and extensive exploitation of external resources, such as knowledge bases for feature-engineering.”
Neural Text Generation from Structured Data with Application to the Biography Domain (2016, background): “An infobox is a fact table describing a person, similar to a person subgraph in a knowledge base (Bollacker et al., 2008; Ferrucci, 2012).”
Learning Answer-Entailing Structures for Machine Comprehension (2015, background): “Many approaches in QA (Moldovan et al., 2003; Ferrucci, 2012) solve this by having a top-level classifier that categorizes the complex task into a variety of sub-tasks.”
Cognitive Science in the era of Artificial Intelligence: A roadmap for reverse-engineering the infant language-learner (2016, positive): “In recent years, artificial intelligence (AI) has been hitting the headlines with impressive achievements at matching or even beating humans in complex cognitive tasks (playing go or video games: Mnih et al., 2015; Silver et al., 2016; processing speech and natural language: Amodei et al., 2016; Fer”
Science Question Answering using Instructional Materials (2016, background): “Retrieval and answer selection are usually designed as isolated or loosely connected components in QA systems (Ferrucci, 2012) leading to loss in performance – our approach mit-”
Learning Natural Language Generation with Truncated Reinforcement Learning (2022, unknown): “2012).”
Measuring the Occupational Impact of AI: Tasks, Cognitive Abilities and AI Benchmarks (2020, background): “1 In the end, breakthroughs in some particular challenges and benchmarks have been identified as landmarks of the field (Campbell et al., 2002; Ferrucci, 2012; Mnih et al., 2015; Silver et al., 2016; Brown and Sandholm, 2019; Brown et al., 2020) and used as illustrations of what AI can do.”
SLiQA-I: Towards Cold-start Development of End-to-end Spoken Language Interface for Question Answering (2019, background): “Question answering thrived with IBM Watson [11] and attracted rising research attentions over knowledge graphs.”
It Takes Two to Tango: Towards Theory of AI's Mind (2017, background): “We find that subjects expect Vicki to answer questions whose answers are numbers (e.g., counting questions) correctly quite often.”
Question Answering Using Enhanced Lexical Semantic Models (2013, background): “In contrast, the Jeopardy! TV quiz show provides another open-domain question answering setting, in which IBM’s Watson system famously beat the two highest ranked players (Ferrucci, 2012).”
Information Retrieval: A Biomedical and Health Perspective (2020, background): “In one study [262], researchers (from the manufacturer) omitted 6 months of data because they believed it was invalid [263].”
Overview of Todai Robot Project and Evaluation Framework of its NLP-based Problem Solving (2014, methodology): “For example, the Halo project (Angele et al., 2003) targeted Chemistry tests, while IBM’s Deep QA (Ferrucci, 2012)”