StructVAE: Tree-structured Latent Variable Models for Semi-supervised Semantic Parsing (2018-06-01T00:00:00.000000Z)

TL;DR

StructVAE is introduced, a variational auto-encoding model for semi-supervised semantic parsing, which learns both from limited amounts of parallel data, and readily-available unlabeled NL utterances, and outperforms strong supervised models.

Abstract

Semantic parsing is the task of transducing natural language (NL) utterances into formal meaning representations (MRs), commonly represented as tree structures. Annotating NL utterances with their corresponding MRs is expensive and time-consuming, and thus the limited availability of labeled data often becomes the bottleneck of data-driven, supervised models. We introduce StructVAE, a variational auto-encoding model for semi-supervised semantic parsing, which learns both from limited amounts of parallel data, and readily-available unlabeled NL utterances. StructVAE models latent MRs not observed in the unlabeled data as tree-structured latent variables. Experiments on semantic parsing on the ATIS domain and Python code generation show that with extra unlabeled data, StructVAE outperforms strong supervised models.

Authors

Graham Neubig

38 papers

Chunting Zhou

5 papers

Junxian He

5 papers

TL;DR

Abstract

Authors

References64 items

Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing

Semi-supervised Structured Prediction with Neural CRF Autoencoder

Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

Transfer Learning for Neural Semantic Parsing

Python Software Foundation

Learning a Neural Semantic Parser from User Feedback

Neural AMR: Sequence-to-Sequence Models for Parsing and Generation

From Language to Programs: Bridging Reinforcement Learning and Maximum Marginal Likelihood

Cross-domain Semantic Parsing via Paraphrasing

Multi-space Variational Encoder-Decoders for Semi-supervised Labeled Sequence Transduction

Abstract Syntax Networks for Code Generation and Semantic Parsing

Learning Structured Natural Language Representations for Semantic Parsing

Variational Autoencoder for Semi-Supervised Text Classification

Neural Shift-Reduce CCG Semantic Parsing

Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

Semantic Parsing with Semi-Supervised Sequential Autoencoders

Language as a Latent Variable: Discrete Generative Models for Sentence Compression

Sequence-based Structured Prediction for Semantic Parsing

Neural Enquirer: Learning to Query Tables in Natural Language

Semantic Parsing to Probabilistic Programs for Situated Question Answering

Semi-Supervised Learning for Neural Machine Translation

Data Recombination for Neural Semantic Parsing

Latent Predictor Networks for Code Generation

Incorporating Copying Mechanism in Sequence-to-Sequence Learning

Language to Logical Form with Neural Attention

Generating Sentences from a Continuous Space

Neural Variational Inference for Text Processing

Neural Programmer: Inducing Latent Programs with Gradient Descent

Learning to Generate Pseudo-Code from Source Code Using Statistical Machine Translation (T)

Effective Approaches to Attention-based Neural Machine Translation

Compositional Semantic Parsing on Semi-Structured Tables

Semantic Parsing via Staged Query Graph Generation: Question Answering with Knowledge Base

Building a Semantic Parser Overnight

Pointer Networks

Adam: A Method for Stochastic Optimization

Large-scale Semantic Parsing without Question-Answer Pairs

Morpho-syntactic Lexical Generalization for CCG Semantic Parsing

Recurrent Neural Network Regularization

Neural Machine Translation by Jointly Learning to Align and Translate

Semi-supervised Learning with Deep Generative Models

Semantic Parsing on Freebase from Question-Answer Pairs

Grounded Unsupervised Semantic Parsing

Abstract Meaning Representation for Sembanking

Semi-Supervised Recursive Autoencoders for Predicting Sentiment Distributions

Semi-Supervised Frame-Semantic Parsing for Unknown Predicates

Learning Dependency-Based Compositional Semantics

Driving Semantic Parsing from the World’s Response

Unsupervised Semantic Parsing

Unlabeled data: Now it helps, now it doesn't

Online Learning of Relaxed CCG Grammars for Parsing to Logical Form

Semi-Supervised Learning for Semantic Parsing using Support Vector Machines

Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

Using Multiple Clause Constructors in Inductive Logic Programming for Semantic Parsing

The Zephyr Abstract Syntax Description Language

Learning to Parse Database Queries Using Inductive Logic Programming

Unsupervised Word Sense Disambiguation Rivaling Supervised Methods

Syntactic Processing

AUTO-ENCODING VARIATIONAL BAYES

A syntactic neural model for general-purpose code generation

Python abstract grammar

Language to Code: Learning Semantic Parsers for If-This-Then-That Recipes

Type-logical semantics

Semi-Supervised Learning Literature Survey

Simple Statistical Gradient-Following Algorithms for Connectionist Reinforcement Learning

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names