Association for the Advancement of Artificial Intelligence

By Matthew Crosby, Ronald P. A. Petrick. 2010

942 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

QuAC: Question Answering in Context (2018, background): “19 Dialog ﬁts into an increasing interest in open domain dialog, mostly studied in the context of social chit-chat (Li et al., 2016; Ritter et al., 2011; Fang et al., 2017; Ghazvininejad et al., 2018).”
Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AI (2019, background): “Walton (2004, 2007, 2011) Argues that explanation systems in AI need to be founded on the dialectical concept, that is, explanation is a process of dialog to achieve shared understanding.”
Information-Theoretic Bounded Rationality (2015, background): “…to be “close enough” to the optimum [Dixon, 2001]; metalevel rationality proposes optimizing a trade-oﬀ between utilities and computational costs [Zilberstein, 2008]; bounded optimality restricts the computational complexity of the programs implementing the optimal policy [Russell and…”
A review of feature selection methods based on mutual information (2013, background): “In the literature there are many definitions of relevance, including different levels of relevance [6, 4, 23, 31, 67, 46, 2, 1, 10, 15].”
Disambiguation and co-authorship networks of the U.S. patent inventor database (1975–2010) (2014, background): “One popular approach for making classifications based on pairwise computation feasible is blocking the records first, and restricting comparisons within blocks (On et al., 2006, Bilenko et al., 2006, Herzog et al., 2007, Smalheiser and Torvik 2009, Reuter and Cimiano, 2012).”
Learning Syntax from Naturally-Occurring Bracketings (2021, background): “Alternatively, one may use reinforcement learning to induce syntactic structures using rewards defined by end tasks (Yogatama et al., 2017; Choi et al., 2018; Havrylov et al., 2019).”
Code Mixing: A Challenge for Language Identification in the Language of Social Media (2014, methodology): “Hong et al. (2011), for example, applied an automatic language detection algorithm to over 62 million tweets to identify the top 10 most popular languages on Twitter.”
Tree-structured Parzen estimator: Understanding its algorithm components and their roles for better empirical performance (2023, background): “The second point is to include strong baselines if available as the basic principle of warm-starting methods (Feurer et al., 2015; Nomura et al., 2021; Hvarfner et al., 2022) is to start near known strong baselines.”
Automated Algorithm Selection: Survey and Perspectives (2018, methodology): “Speciﬁcally, the set of TSP instances was extended by clustered and morphed instances (Gent et al., 1999; Mersmann et al., 2012; Meisel et al., 2015), i.e., linear combinations of clustered and RUE instances 3 .”