Broad-coverage CCG Semantic Parsing with AMR

By Yoav Artzi, Kenton C. T. Lee, Luke S. Zettlemoyer. 2015

157 citations recorded by the source corpus.

We propose a grammar induction technique for AMR semantic parsing. While previous grammar induction techniques were designed to re-learn a new parser for each target application, the recently annotated AMR Bank provides a unique opportunity to induce a single model for understanding broad-coverage newswire text and support a wide range of applications. We present a new model that combines CCG parsing to recover compositional aspects of meaning and a factor graph to model non-compositional phenomena, such as anaphoric dependencies. Our approach achieves 66.2 Smatch F1 score on the AMR bank, significantly outperforming the previous state of the art.

Subfields: Artificial Intelligence, Natural Language Processing

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 Natural Language Processing

Citations in the corpus

Joint Concept Learning and Semantic Parsing from Natural Language Explanations (2017, methodology): “For this work, we use CCG based semantic parsing, a popular semantic parsing approach (Zettlemoyer and Collins, 2005; Artzi et al., 2015) that couples syntax with semantics.”
Latent Predictor Networks for Code Generation (2016, methodology): “Finally, a considerable effort in this task has focused on semantic parsing (Wong and Mooney, 2006; Jones et al., 2012; Lei et al., 2013; Artzi et al., 2015; Quirk et al., 2015).”
Learning a Neural Semantic Parser from User Feedback (2017, background): “Although diverse meaning representation languages have been used with semantic parsers – such as regular expressions (Kushman and Barzi-lay, 2013; Locascio et al., 2016), Abstract Meaning Representations (AMR) (Artzi et al., 2015; Misra and Artzi, 2016), and systems of equations (Kushman et al., 201”
Learning executable semantic parsers for natural language understanding (2016, methodology): “Multiple AMR parsers have been developed, including one based on CCG [1].”
Neural Enquirer: Learning to Query Tables (2015, background): “…ﬁrst line of research resorts to the power of grammatical formalisms (e.g., Combinatory Categorial Grammar) to parse NL queries and generate corresponding logical forms, which requires curated/learned lexicons deﬁning the correspondence between NL phrases and symbolic constituents [17, 7, 1, 18].”
A Natural Proof System for Natural Language (2017, unknown): “These results seem quite desperate for producing adequate semantic representations from CCG trees, but the situation is still encouraging as the parsers displayed promising results in several semantic tasks (Bjerva et al., 2014; Beltagy and Erk, 2015; Artzi et al., 2015).”
Learning from Explanations with Neural Execution Tree (2019, unknown): “We use Combinatory Categorial Grammar (CCG) based semantic parsing (Zettlemoyer & Collins, 2012; Artzi et al., 2015), an approach that couples syntax with semantics, to convert each NL explanation ej to a logical form fj .”
Sequence-to-Action: End-to-End Semantic Graph Generation for Semantic Parsing (2018, background): “…2016) 5 Related Work Semantic parsing has received signiﬁcant attention for a long time (Kate and Mooney, 2006; Clarke et al., 2010; Krishnamurthy and Mitchell, 2012; Artzi and Zettlemoyer, 2013; Berant and Liang, 2014; Quirk et al., 2015; Artzi et al., 2015; Reddy et al., 2017; Chen et al., 2018).”
Semantic Parsing for Task Oriented Dialog using Hierarchical Representations (2018, background): “These approaches can represent complex constructions that are beyond the scope of our approach, but with signiﬁcantly challenging parsing (Artzi et al., 2015).”
Transforming Dependency Structures to Logical Forms for Semantic Parsing (2016, methodology): “, 2007) and CCG (Baldridge and Kruijff, 2002; Bos et al., 2004; Steedman, 2012; Artzi et al., 2015).”
Statistical learning for semantic parsing: A survey (2019, background): “Below is an example of a CCG derivation [2] : A CCG can be deﬁned by lexicons and a set of combinators [30] .”
Neural AMR: Sequence-to-Sequence Models for Parsing and Generation (2017, methodology): “Artzi et al. (2015) use a grammar induction approach with Combinatory Categorical Grammar (CCG), which relies on pretrained CCGBank categories, like Bjerva et al. (2016).”
AMR-to-text Generation with Synchronous Node Replacement Grammar (2017, background): “…literature so far on text-to-AMR parsing (Flanigan et al., 2014; Wang et al., 2015; Peng et al., 2015; Vander-wende et al., 2015; Pust et al., 2015; Artzi et al., 2015; Groschwitz et al., 2015; Goodman et al., 2016; Zhou et al., 2016), there has been little work on AMR-to-text generation (Flanigan…”
A Corpus and Semantic Parser for Multilingual Natural Language Querying of OpenStreetMap (2016, background): “Newer research attempts to close the gap between lexical variability and structural complexity (Vlachos and Clark, 2014; Artzi et al., 2015; Pasupat and Liang, 2015), however, answer retrieval accuracy is low if semantic parsers cannot be bootstrapped from a corpus of queries and MRLs (Wang et al.,…”
Linguistic realisation as machine translation: Comparing different MT models for AMR-to-text generation (2017, background): “Most earlier studies on AMRs have focused on text understanding, i.e. processing texts in order to produce AMRs (Flanigan et al., 2014; Artzi et al., 2015).”
Learning to Annotate: Modularizing Data Augmentation for Text Classifiers with Natural Language Explanations (2019, methodology): “We use Combinatory Categorial Grammar (CCG) based semantic parsing (Zettlemoyer and Collins, 2012; Artzi et al., 2015), an approach that couples syntax with semantics, to convert each NL explanation ej to a logical form fj .”
Discourse Representation Structure Parsing (2018, background): “However, see Bos (2016) and Artzi et al. (2015) for translations to ﬁrst-order logic.”
Broad-Coverage Semantic Parsing as Transduction (2019, background): “Grammar-based parsers leverage external semantic resources to derive AMRs compositionally based on CCG rules (Artzi et al., 2015), or SHRG rules (Peng et al., 2015).”
Probabilistic Models for Learning a Semantic Parser Lexicon (2016, unknown): “Artzi et al. (2015) combine templates with top-down splitting.”