Learning Structured Natural Language Representations for Semantic Parsing

By Jianpeng Cheng, Siva Reddy, Vijay A. Saraswat, Mirella Lapata. 2017

75 citations recorded by the source corpus.

We introduce a neural semantic parser which is interpretable and scalable. Our model converts natural language utterances to intermediate, domain-general natural language representations in the form of predicate-argument structures, which are induced with a transition system and subsequently mapped to target domains. The semantic parser is trained end-to-end using annotated logical forms or their denotations. We achieve the state of the art on SPADES and GRAPHQUESTIONS and obtain competitive results on GEOQUERY and WEBQUESTIONS. The induced predicate-argument structures shed light on the types of representations useful for semantic parsing and how these are different from linguistically motivated ones.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, 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 Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

MathQA: Towards Interpretable Math Word Problem Solving with Operation-Based Formalisms (2019, background): “Learning logical forms has led to success in other areas of semantic parsing (Cheng et al., 2017; Zelle and Mooney, 1996; Zettlemoyer and Collins, 2007, 2005) and is a natural representation for math word problem-solving steps.”
Coarse-to-Fine Decoding for Neural Semantic Parsing (2018, methodology): “Cheng et al. (2017) use a transition system to generate variable-free queries.”
Discourse Representation Structure Parsing (2018, background): “…Rabi-novich et al., 2017; Buys and Blunsom, 2017) Most previous work focuses on building semantic parsers for question answering tasks, such as querying a database to retrieve an answer (Zelle and Mooney, 1996; Cheng et al., 2017), or conversing with a ﬂight booking system (Dahl et al., 1994).”
StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing (2018, methodology): “The inference model is trained to construct a tree-structured logical form using the transition actions defined in Cheng et al. (2017). We use a classical tri-gram Kneser-Ney language model as the prior.”
Building a Neural Semantic Parser from a Domain Ontology (2018, methodology): “Cheng et al. (2017a, 2017b), Yin and Neubig (2018), Gupta et al. (2018), Chen et al. (2018) all employ neural sequence-to-action models to generate structured meaning representations.”
Practical Semantic Parsing for Spoken Language Understanding (2019, methodology): “We extend the model of Cheng et al. (2017) by adding character-level embeddings and a copy mechanism.”
Weakly Supervised Semantic Parsing with Abstract Examples (2017, methodology): “, 2013), but recently denotations have been used to train neural semantic parsers (Liang et al., 2017; Krishnamurthy et al., 2017; Rabinovich et al., 2017; Cheng et al., 2017).”
Natural language to SQL: Where are we today? (2020, methodology): “GNN and IRNet use a grammar-based sequence-to-tree decoder [41, 9, 45, 34] which generates a derivation tree rather than a sequence of words.”
Semantic Parsing with Dual Learning (2019, background): “Cheng et al. (2017) and Dong and Lapata (2018) both try to decode in two steps, from a coarse rough sketch to a finer structure hierarchically.”
A Survey on Semantic Parsing (2018, methodology): “A two stage approach such as that employed by Cheng et al. [2017] aims to build intermediate structures that provide insight into what the model has learned.”
Learning an Executable Neural Semantic Parser (2017, unknown): “estructure-awareneuralnetwork models: it also generates tree-structured logical forms, however, following a transitionbased approach. Our semantic parser is a generalization of the model presented in Cheng et al. (2017); it generates logical forms recursively with a set of transition operations whos”
Statistical learning for semantic parsing: A survey (2019, methodology): “CHENG17 [73] ﬁrst mapped utterances to an intermediate representation containing natural language predicates.”
Deep Learning Inference in Facebook Data Centers: Characterization, Performance Optimizations and Hardware Implications (2018, methodology): “This approach has been successfully applied to many natural language processing tasks, such as summarization [17, 46], speech recognition [23], syntactic and semantic parsing [11, 69] as well as question answering and dialog systems [9, 52].”