Bootstrapping Semantic Parsers from Conversations

By Yoav Artzi, Luke S. Zettlemoyer. 2011

147 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

Semantic Parsing on Freebase from Question-Answer Pairs (2013, background): “Recent developments aim to lift these limitations, either by reducing the amount of supervision (Clarke et al., 2010; Liang et al., 2011; Goldwasser et al., 2011; Artzi and Zettlemoyer, 2011) or by increasing the number of logical Occidental College, Columbia University”
Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning (2017, background): “Other work in semantic parsing has focused on learning parsers without relying on annotated logical forms by leveraging conversational logs [Artzi and Zettlemoyer, 2011], demonstrations [Artzi and Zettlemoyer, 2013], distant supervision [Cai and Yates, 2013, Reddy et al.”
Learning to Automatically Solve Algebra Word Problems (2014, background): “This approach is related to Artzi and Zettlemoyer (2013). Word problem”
Learning Dependency-Based Compositional Semantics (2011, background): “In accordance with 17 U.S.C. 105, no copyright protection is available for such works under U.S. law.”
Weakly Supervised Learning of Semantic Parsers for Mapping Instructions to Actions (2013, methodology): “Step 2: Parameter Update We use a variant of a loss-driven perceptron (Singh-Miller & Collins, 2007; Artzi & Zettlemoyer, 2011) for parameter updates.”
Scaling Semantic Parsers with On-the-Fly Ontology Matching (2013, methodology): “, 2011), from conversational logs (Artzi and Zettlemoyer, 2011), with distant supervision (Krishnamurthy and Mitchell, 2012; Cai and Yates, 2013b), and from sentences paired with system behavior (Goldwasser and Roth, 2011; Chen and Mooney, 2011; Artzi and Zettlemoyer, 2013).”
Language to Logical Form with Neural Attention (2016, background): “Other work learns semantic parsers without relying on logical-from annotations, e.g., from sentences paired with conversational logs (Artzi and Zettlemoyer, 2011), system demonstrations (Chen and Mooney, 2011; Goldwasser and Roth, 2011; Artzi and Zettle-moyer, 2013), question-answer pairs (Clarke…”
Building a Semantic Parser Overnight (2015, neutral): “, 2011) and to weaker forms (Artzi and Zettlemoyer, 2011; Reddy et al., 2014).”
Search-based Neural Structured Learning for Sequential Question Answering (2017, methodology): “Another dataset of travel booking conversations is used by Artzi and Zettlemoyer (2011) to learn a semantic parser for complicated queries given user clarifications.”
Learning Knowledge Graphs for Question Answering through Conversational Dialog (2015, methodology): “work to address more open dialog includes bootstrapping a semantic parser from unlabeled dialogs (Artzi and Zettlemoyer, 2011), extracting potential user goals and system responses from backend databases (Hixon and Passonneau, 2013), and inducing slots and slot-fillers from a corpus of humanhuman di”
Naturalizing a Programming Language via Interactive Learning (2017, background): “…– (some steps omitted) Figure 1: Some examples of users building structures using a naturalized language in Voxelurn: http://www.voxelurn.com guage, which has been the subject of work in semantic parsing (Zettlemoyer and Collins, 2005; Artzi and Zettlemoyer, 2011, 2013; Pasupat and Liang, 2015).”
Natural Language to Structured Query Generation via Meta-Learning (2018, background): “Semantic Parsing Mapping natural language to logic forms has been actively studied in natural language processing research (Zettlemoyer and Collins, 2005; Giordani and Moschitti, 2010; Artzi and Zettlemoyer, 2011; Berant et al., 2013; Vlachos and Clark, 2014; Yih et al., 2014, 2015; Wang et al., 201”
Learning Rewards from Linguistic Feedback (2020, background): “Dialogue systems (Artzi and Zettlemoyer 2011; Li et al. 2016) learn to interpret user queries in the context of the ongoing interaction, while robots and assistants (Thomason et al. 2015; Wang et al. 2019; Thomason et al. 2020; Szlam et al. 2019) ground language in their physical surroundings.”
Using Semantic Unification to Generate Regular Expressions from Natural Language (2013, background): “For example, Artzi and Zettlemoyer (2011) estimate semantic equivalence using a heuristic loss function.”
Learning Adaptive Language Interfaces through Decomposition (2020, background): “s” have been identiﬁed, they are parsed into corresponding code blocks that can then be executed. Other work leverages conversations to learn new concepts, generating queries for users to respond to (Artzi and Zettlemoyer, 2011;Thomason et al.,2019). Notably,Thomason et al.(2019) used this conversat”
Large-scale Semantic Parsing via Schema Matching and Lexicon Extension (2013, background): “Semantic parsing is the task of translating natural language utterances to a formal meaning representation language (Chen et al., 2010; Liang et al., 2009; Clarke et al., 2010; Liang et al., 2011; Artzi and Zettlemoyer, 2011).”
Executing Instructions in Situated Collaborative Interactions (2019, methodology): “Interactions were also used for semantic parser induction (Artzi and Zettlemoyer, 2011; Thomason et al., 2015; Wang et al., 2016).”
Statistical learning for semantic parsing: A survey (2019, background): “A possible way to learn ﬂexibly is weak supervision [5,6] , which only requires executing logical forms within a system and evaluating the result [45,46] .”