Imitation Learning of Agenda-based Semantic Parsers

Semantic parsers conventionally construct logical forms bottom-up in a fixed order, resulting in the generation of many extraneous partial logical forms. In this paper, we combine ideas from imitation learning and agenda-based parsing to train a semantic parser that searches partial logical forms in a more strategic order. Empirically, our parser reduces the number of constructed partial logical forms by an order of magnitude, and obtains a 6x-9x speedup over fixed-order parsing, while maintaining comparable accuracy.

• Publication year

  2015

• Venue

  Transactions of the Association for Computational Linguistics

• Publication date

  2015-11-20

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.1162/tacl_a_00157
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

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

  2015influential reference
• Learning to Search Better than Your Teacher

  2015cited by this paper
• A* CCG Parsing with a Supertag-factored Model

  2014cited by this paper
• Joint Relational Embeddings for Knowledge-based Question Answering

  2014cited by this paper
• An Overview of Microsoft Deep QA System on Stanford WebQuestions Benchmark

  2014cited by this paper
• The Stanford CoreNLP Natural Language Processing Toolkit

  2014cited by this paper
• Semantic Parsing via Paraphrasing

  2014cited by this paper
• Knowledge-Based Question Answering as Machine Translation

  2014cited by this paper
• Information Extraction over Structured Data: Question Answering with Freebase

  2014cited by this paper
• Question Answering with Subgraph Embeddings

  2014cited by this paper
• Learning Distributions over Logical Forms for Referring Expression Generation

  2013cited by this paper
• Lambda Dependency-Based Compositional Semantics

  2013cited by this paper
• Training Deterministic Parsers with Non-Deterministic Oracles

  2013cited by this paper
• Scaling Semantic Parsers with On-the-Fly Ontology Matching

  2013cited by this paper
• Large-scale Semantic Parsing via Schema Matching and Lexicon Extension

  2013influential reference
• Semantic Parsing on Freebase from Question-Answer Pairs

  2013influential reference
• Learned Prioritization for Trading Off Accuracy and Speed

  2012influential reference
• A Joint Model of Language and Perception for Grounded Attribute Learning

  2012cited by this paper
• Weakly Supervised Training of Semantic Parsers

  2012cited by this paper
• Vine Pruning for Efficient Multi-Pass Dependency Parsing

  2012cited by this paper
• Efficient CCG Parsing: A* versus Adaptive Supertagging

  2011cited by this paper
• Learning Dependency-Based Compositional Semantics

  2011cited by this paper
• Adaptive Subgradient Methods for Online Learning and Stochastic Optimization

  2011cited by this paper
• Beam-Width Prediction for Efficient Context-Free Parsing

  2011cited by this paper
• Understanding Natural Language Commands for Robotic Navigation and Mobile Manipulation

  2011cited by this paper
• Inducing Probabilistic CCG Grammars from Logical Form with Higher-Order Unification

  2010cited by this paper
• Chart Pruning for Fast Lexicalised-Grammar Parsing

  2010cited by this paper
• Driving Semantic Parsing from the World’s Response

  2010cited by this paper
• Faster Parsing by Supertagger Adaptation

  2010cited by this paper
• A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

  2010cited by this paper
• Search-based structured prediction

  2009cited by this paper
• K-Best A* Parsing

  2009cited by this paper
• Forest Reranking: Discriminative Parsing with Non-Local Features

  2008cited by this paper
• Online Learning of Relaxed CCG Grammars for Parsing to Logical Form

  2007cited by this paper
• Forest Rescoring: Faster Decoding with Integrated Language Models

  2007cited by this paper
• Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus

  2007cited by this paper
• Learning to Map Sentences to Logical Form: Structured Classification with Probabilistic Categorial Grammars

  2005cited by this paper
• Better k-best Parsing

  2005cited by this paper
• Apprenticeship learning via inverse reinforcement learning

  2004cited by this paper
• A* Parsing: Fast Exact Viterbi Parse Selection

  2003cited by this paper
• Policy Gradient Methods for Reinforcement Learning with Function Approximation

  1999cited by this paper
• New Figures of Merit for Best-First Probabilistic Chart Parsing

  1998cited by this paper
• Learning to Parse Database Queries Using Inductive Logic Programming

  1996cited by this paper
• Algorithm schemata and data structures in syntactic processing

  1986cited by this paper

• AI Enabled Question Answering Systems: A Survey

  2025cites this paper
• Translating Between SQL Dialects for Cloud Migration

  2024cites this paper
• Efficient natural language classification algorithm for detecting duplicate unsupervised features

  2021cites this paper
• Comparative Study on “Sentence Rewriting for Semantic Parsing” and “Graph-Based Translation Via Graph Segmentation”

  2021cites this paper
• Learning Algebraic Recombination for Compositional Generalization

  2021cites this paper
• A Brief Survey of Question Answering Systems

  2021cites this paper
• Exploiting Rich Syntax for Better Knowledge Base Question Answering

  2021cites this paper
• ALGORITHM FOR NATURAL LANGUAGE CLASSIFICATION TO DETECT DUPLICATE UNSUPERVISED FEATURES

  2021cites this paper
• Knowledge-based question answering by tree-to-sequence learning

  2020cites this paper
• Temporal-Logic-Based Semantic Fault Diagnosis With Time-Series Data From Industrial Internet of Things

  2020influential citation
• Introducing External Knowledge to Answer Questions with Implicit Temporal Constraints over Knowledge Base

  2020cites this paper
• Answer Graph-based Interactive Attention Network for Question Answering over Knowledge Base

  2020cites this paper
• Iterative Utterance Segmentation for Neural Semantic Parsing

  2020cites this paper
• A survey on question answering systems over linked data and documents

  2019cites this paper
• DeepAssist: Deep Knowledge Grounding for Factual and Conversational Natural Language Interfaces

  2019influential citation
• Bidirectional Attentive Memory Networks for Question Answering over Knowledge Bases

  2019cites this paper
• Retrieving Relationships from a Knowledge Graph for Question Answering

  2019cites this paper
• A Hybrid Question Answering System

  2019cites this paper
• Learning natural language interfaces with neural models

  2019cites this paper
• Question answering over knowledge bases with continuous learning

  2019cites this paper
• Towards Democratizing Data Science with Natural Language Interfaces

  2019influential citation
• Enabling Efficient Question Answering over Hundreds of Linked Datasets

  2019cites this paper
• Open Domain Question Answering over Hundreds of Linked Open Datasets Eleftherios

  2019cites this paper
• Semi-Supervised Lexicon Learning for Wide-Coverage Semantic Parsing

  2018cites this paper
• Weakly-Supervised Neural Semantic Parsing with a Generative Ranker

  2018cites this paper
• ComQA: A Community-sourced Dataset for Complex Factoid Question Answering with Paraphrase Clusters

  2018cites this paper
• Novel knowledge-based system with relation detection and textual evidence for question answering research

  2018cites this paper
• Semantic parsing of automobile steering systems

  2018cites this paper
• Knowledge Base Question Answering via Encoding of Complex Query Graphs

  2018cites this paper
• Value-based Search in Execution Space for Mapping Instructions to Programs

  2018cites this paper
• New resources and ideas for semantic parser induction

  2018cites this paper
• Collection for Interactive Learning through the Dialog

  2018cites this paper
• Building a Neural Semantic Parser from a Domain Ontology

  2018cites this paper
• The Web as a Knowledge-Base for Answering Complex Questions

  2018cites this paper
• Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing

  2018cites this paper
• Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation

  2018cites this paper
• Interactive Semantic Parsing for If-Then Recipes via Hierarchical Reinforcement Learning

  2018cites this paper
• Neural architecture for question answering using a knowledge graph and web corpus

  2017influential citation
• Recovering Question Answering Errors via Query Revision

  2017influential citation
• Imitation Learning for Dynamic VFI Control in Large-Scale Manycore Systems

  2017cites this paper
• Learning to Paraphrase for Question Answering

  2017influential citation
• Learning Structured Natural Language Representations for Semantic Parsing

  2017cites this paper
• Learning to Prune: Exploring the Frontier of Fast and Accurate Parsing

  2017cites this paper
• AMUSE: Multilingual Semantic Parsing for Question Answering over Linked Data

  2017cites this paper
• Core techniques of question answering systems over knowledge bases: a survey

  2017cites this paper
• Macro Grammars and Holistic Triggering for Efficient Semantic Parsing

  2017cites this paper
• Learning an Executable Neural Semantic Parser

  2017cites this paper
• Universal Semantic Parsing

  2017influential citation
• HybQA: Hybrid Deep Relation Extraction for Question Answering on Freebase

  2017influential citation
• Neural Semantic Parsing over Multiple Knowledge-bases

  2017cites this paper
• Tackling Error Propagation through Reinforcement Learning: A Case of Greedy Dependency Parsing

  2017cites this paper
• Efficiency-aware Answering of Compositional Questions using Answer Type Prediction

  2017cites this paper
• More Accurate Entity Ranking Using Knowledge Graph and Web Corpus

  2017cites this paper
• Evaluating Semantic Parsing against a Simple Web-based Question Answering Model

  2017cites this paper
• Learning to Solve Geometry Problems from Natural Language Demonstrations in Textbooks

  2017cites this paper
• Machine Learning with World Knowledge: The Position and Survey

  2017cites this paper
• Argumentative Writing Support by means of Natural Language Processing

  2017cites this paper
• Syntax-mediated semantic parsing

  2017cites this paper
• Neural Sequence Prediction by Coaching

  2017cites this paper
• Question Vectors Scores Answer Question q : who created microsoft ?

  2017cites this paper
• On Generating Characteristic-rich Question Sets for QA Evaluation

  2016cites this paper
• Learning executable semantic parsers for natural language understanding

  2016cites this paper
• Question Answering on Freebase via Relation Extraction and Textual Evidence

  2016cites this paper
• Constraint-Based Question Answering with Knowledge Graph

  2016influential citation
• A Study of Imitation Learning Methods for Semantic Role Labeling

  2016cites this paper
• UCL+Sheffield at SemEval-2016 Task 8: Imitation learning for AMR parsing with an alpha-bound

  2016cites this paper
• Improving Semantic Parsing via Answer Type Inference

  2016influential citation
• Transforming Dependency Structures to Logical Forms for Semantic Parsing

  2016cites this paper
• Data Collection for Interactive Learning through the Dialog

  2016cites this paper
• Neural Shift-Reduce CCG Semantic Parsing

  2016cites this paper
• Enhancing Freebase Question Answering Using Textual Evidence

  2016influential citation
• CFO: Conditional Focused Neural Question Answering with Large-scale Knowledge Bases

  2016cites this paper
• Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision

  2016cites this paper
• Sentence Rewriting for Semantic Parsing

  2016cites this paper
• Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing

  2016cites this paper
• When a Knowledge Base Is Not Enough: Question Answering over Knowledge Bases with External Text Data

  2016influential citation
• Method for Complex Question Answering Based on Global and Local

  year unknowncites this paper