Semantic Parsing with Semi-Supervised Sequential Autoencoders

By Tomás Kociský, Gábor Melis, Edward Grefenstette, Chris Dyer, Wang Ling, Phil Blunsom, Karl Moritz Hermann. 2016

79 citations recorded by the source corpus.

We present a novel semi-supervised approach for sequence transduction and apply it to semantic parsing. The unsupervised component is based on a generative model in which latent sentences generate the unpaired logical forms. We apply this method to a number of semantic parsing tasks focusing on domains with limited access to labelled training data and extend those datasets with synthetically generated logical forms.

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

SPoC: Search-based Pseudocode to Code (2019, background): “Partial parses can be constructed by combining smaller partial parses in a bottom-up fashion [58, 28, 27], adding the next token to the sequence [10, 22, 51, 11, 25], or creating a new node in a tree structure [10, 26, 54, 39].”
The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables (2016, methodology): “Still, reasoning about discrete computation comes naturally to humans, and so, despite the difficulty associated, many modern architectures incorporate discrete stochasticity (Mnih et al., 2014; Xu et al., 2015; Kočiský et al., 2016).”
Speaker-Follower Models for Vision-and-Language Navigation (2018, methodology): “our work is the SEQ4 model [26], which applies semi-supervision to a navigation task by sampling new environments and maps (in synthetic domains without vision), and training an autoencoder to reconstruct routes, using language as a latent variable.”
Coarse-to-Fine Decoding for Neural Semantic Parsing (2018, background): “Several ideas have been explored to enhance the performance of these models such as data augmentation (Kočiský et al., 2016; Jia and Liang, 2016), transfer learning (Fan et al.”
StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing (2018, methodology): “…from recent success in applying variational auto-encoding (VAE) models in semisupervised sequence-to-sequence learning (Miao and Blunsom, 2016; Kociský et al., 2016), and propose STRUCTVAE — a principled deep generative approach for semi-supervised learning with tree-structured latent…”
Latent Intention Dialogue Models (2017, background): “This is critical for NLP tasks, especially where additional supervision and external knowledge can be utilized for bootstrapping (Faruqui et al., 2015; Miao & Blunsom, 2016; Kočiský et al., 2016).”
Few-Shot Semantic Parsing for New Predicates (2021, background): “…et al., 2017; Herzig and Berant, 2018; Chang et al., 2019; Lee, 2019; Zhang et al., 2019a; Guo et al., 2019; Wang et al., 2019), semantic features in different domains (Dadashkarimi et al., 2018; Li et al., 2020), or unlabeled data (Yin et al., 2018; Koˇcisk`y et al., 2016; Sun et al., 2019).”
Learning a Natural Language Interface with Neural Programmer (2016, unknown): “Recently, Kocisky et al. (2016) develop a semi-supervised semantic parsing method that uses question-program pairs as supervision.”
Learning an Executable Neural Semantic Parser (2017, unknown): “…Bahdanau, Cho, and Bengio 2015) to a variety of NLP tasks has provided strong impetus to treat semantic parsing as a sequence transduction problem where an utterance is mapped to a target meaning representation in string format (Dong and Lapata 2016; Jia and Liang 2016; Koˇcisk´y et al. 2016).”
Building a Neural Semantic Parser from a Domain Ontology (2018, background): “Subsequent work of Koˇcisk´y et al. (2016) attempts to explore the meaning representation space with a generative autoencoder.”
Constrained Language Models Yield Few-Shot Semantic Parsers (2021, background): “, 2013), semantic parsing has recently been driven by encoder-decoder neural architectures (starting with Dong and Lapata, 2016; Jia and Liang, 2016; Kočiský et al., 2016).”
Learning Structured Natural Language Representations for Semantic Parsing (2017, background): “, 2014) to a variety of NLP tasks has provided strong impetus to treat semantic parsing as a sequence transduction problem where an utterance is mapped to a target meaning representation in string format (Dong and Lapata, 2016; Jia and Liang, 2016; Kočiský et al., 2016).”