• Corpus ID: 17050243

Contextual Semantic Parsing using Crowdsourced Spatial Descriptions

  title={Contextual Semantic Parsing using Crowdsourced Spatial Descriptions},
  author={Kais Dukes},
  • Kais Dukes
  • Published 1 May 2014
  • Computer Science
  • ArXiv
We describe a contextual parser for the Robot Commands Treebank, a new crowdsourced resource. In contrast to previous semantic parsers that select the most-probable parse, we consider the different problem of parsing using additional situational context to disambiguate between different readings of a sentence. We show that multiple semantic analyses can be searched using dynamic programming via interaction with a spatial planner, to guide the parsing process. We are able to parse sentences in… 

Figures and Tables from this paper

SemEval-2014 Task 6: Supervised Semantic Parsing of Robotic Spatial Commands

The SemEval-2014 Task 6 task focuses on contextual parsing of robotic commands, in which the additional con- text of spatial scenes can be used to guide a parser to control a robot arm.

Semantic Role Labelling for Robot Instructions using Echo State Networks

This work proposes an efficient Echo State Network-based parser for robotic commands and only relies on the training data, which generates a single semantic tree structure in real-time which can be executed by a robot arm manipulating objects.

UW-MRS: Leveraging a Deep Grammar for Robotic Spatial Commands

A handbuilt rule-based solution based on a preexisting broad coverage deep grammar of English, backed up by a off-the-shelf datadriven PCFG parser, and achieves the best score reported among the task participants.



From language towards formal spatial calculi

This work considers mapping unrestricted natural language to formal spatial representations and describes ongoing work on a two-level machine learning approach that deals with the extraction of spatial information from natural language sentences, called spatial role labeling.

A practical semantic representation for natural language parsing

This dissertation develops a statistical model to learn selectional restrictions from corpora and shows how it can be used to distinguish between acceptable and unacceptable verb-object pairs in data sets derived from the authors' lexicon and from the World Street Journal corpus.

Approaching the Symbol Grounding Problem with Probabilistic Graphical Models

The G3 framework dynamically instantiates a probabilistic graphical model for a natural language input, enabling a mapping between words in language and concrete objects, places, paths and events in the external world.

LOGICON: A System for Extracting Semantic Structure using Partial Parsing

LOGICON is presented, an endto-end system using partial parsing, which assigns novel semantic structures to natural language text, which is deterministic and fast.

Online Learning of Relaxed CCG Grammars for Parsing to Logical Form

A key idea is to introduce non-standard CCG combinators that relax certain parts of the grammar—for example allowing flexible word order, or insertion of lexical items— with learned costs.

Understanding natural language

A computer system for understanding English that contains a parser, a recognition grammar of English, programs for semantic analysis, and a general problem solving system based on the belief that in modeling language understanding, it must deal in an integrated way with all of the aspects of language—syntax, semantics, and inference.

Representation and Processing of Spatial Expressions

This volume contains a set of theoretical analyses as well as accounts of applications which deal with the problems of representing and processing spatial expressions, including dialogue understanding using mental images, and interfaces to CAD and multi-media systems.

Jointly Learning to Parse and Perceive: Connecting Natural Language to the Physical World

This paper introduces Logical Semantics with Perception (LSP), a model for grounded language acquisition that learns to map natural language statements to their referents in a physical environment and finds that LSP outperforms existing, less expressive models that cannot represent relational language.

An extended GHKM algorithm for inducing λ-SCFG

TheGHKM algorithm is extended, which is a state-of-the-art algorithm for learning synchronous grammars in statistical machine translation, to induce λ-SCFG from pairs of NL sentences and logical forms, and the theory behind GHKM is reformulate that gives formal semantics to the alignment between NL words and logical form tokens.

Inducing Probabilistic CCG Grammars from Logical Form with Higher-Order Unification

This paper uses higher-order unification to define a hypothesis space containing all grammars consistent with the training data, and develops an online learning algorithm that efficiently searches this space while simultaneously estimating the parameters of a log-linear parsing model.