Baseball: an automatic question-answerer

By B. Green, A. K. Wolf, C. Chomsky, Kenneth Laughery. 1899

Subfields: 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 Question Answering & Reading Comprehension

Citations in the corpus

Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering (2017, background): “Open Domain Question Answering The task of open domain question answering dates back to as early as (Green Jr et al., 1961) and was popularized by TREC-8 (Voorhees, 1999).”
Multi-step Retriever-Reader Interaction for Scalable Open-domain Question Answering (2019, background): “For example the B ASEBALL system (Green Jr et al., 1961) aimed at answering open domain question albeit for a speciﬁc domain.”
Denoising Distantly Supervised Open-Domain Question Answering (2018, background): “Open-domain QA has been ﬁrst proposed by (Green Jr et al., 1961).”
R3: Reinforced Reader-Ranker for Open-Domain Question Answering (2017, background): “The task of Open domain question answering dates back to as early as (Green Jr et al., 1961) and was popularized with TREC-8 (Voorhees, 1999).”
MKQA: A Linguistically Diverse Benchmark for Multilingual Open Domain Question Answering (2020, background): “Open Domain QA, pioneered by Green et al. (1986), is the task of answering open questions using external knowledge sources.”
Social-IQ: A Question Answering Benchmark for Artificial Social Intelligence (2019, background): “Intelligent question answering, one of the most ambitious goals of AI, has roots in decades of research in ar-tiﬁcial intelligence [17, 54].”
Learning Semantic Parsers: An Important but Under-Studied Problem (2004, background): “From the very early days of natural-language processing (NLP) research, answering natural-language questions in a particular domain was a key task (Green et al. 1963; Simmons 1965; 1970).”
Comparing BERT against traditional machine learning text classification (2020, background): “t study by Khurana [14], it was not until the 1960s when work in uenced by the Articial Intelligence community started to collaborate with the NLP community, concretely with the BASEBALL Q-A systems [10]. Since those remote years, NLP methodologies have ourished and lots of papers solving dierent ta”
Question Answering on Knowledge Bases and Text using Universal Schema and Memory Networks (2017, background): “These attracted research ever since the early days of computer science, e.g., BASEBALL (Green Jr et al., 1961).”
Book Review: Spoken Dialogue Technology: Toward the Conversational User Interface, by Michael F. McTear (2002, background): “BASEBALL was an early question–answering system that could answer questions about the dates, locations, teams and scores of baseball games (Green et al., 1963).”
Understanding natural language (1972, background): “Some examples are: BASEBALL (Green et al., 1963), which stored tables of baseball results and interpreted questions as “specification lists” requesting data from those tables; SAD SAM (Lindsay, 1963), which interpreted sentences as simple relationship facts about people, and stored these in a networ”
AVA: an Automatic eValuation Approach to Question Answering Systems (2020, background): “QA has been traditionally studied early in literature (Green et al., 1961).”
Natural language question answering: the view from here (2001, background): “In this regard BASEBALL was the (cid:12)rst of a series of programs designed as ‘natural language front-ends to databases’.”
Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering (2021, background): “The earliest QA system, as is widely acknowledged, is the Baseball [1], which was designed in 1961 to answer questions about American baseball games, such as game time, location and team name.”
R3: Reinforced Ranker-Reader for Open-Domain Question Answering (2018, background): “Very recently, IR plus machine reading comprehension ( SR-QA ) showed promise for open-domain QA, especially after datasets created speciﬁcally for the multiple-passage RC setting (Nguyen et al. 2016; Chen et al. 2017a; Joshi et al. 2017; Dunn et al. 2017; Dhingra, Mazaitis, and Cohen 2017).”
Natural Language Processing Advancements By Deep Learning: A Survey (2020, background): “1) Rule-based Question Answering: Baseball [142] is one of the early works (1961) on QA where an effort was made to answer questions related to baseball games by using a game database.”