We present a new approach to learning a semantic parser (a system that maps natural language sentences into logical form). Unlike previous methods, it exploits an existing syntactic parser to produce disambiguated parse trees that drive the compositional semantic interpretation. The resulting system produces improved results on standard corpora on natural language interfaces for database querying and simulated robot control. 1

In this paper, we report experiments that explore learning of syntactic and semantic representations. First, we extend a state-of-the-art statistical parser to produce a richly annotated tree that identifies and labels nodes with semantic role labels as well as syntactic labels. Secondly, we explore rule-based and learning techniques to extract predicate-argument structures from this enriched output. The learning method is competitive with previous single-system proposals for semantic role labelling, yields the best reported precision, and produces a rich output. In combination with other high recall systems it yields an F-measure of 81%. 1

This paper investigates a generative history-based parsing model that synchronises the derivation of non-planar graphs representing semantic dependencies with the derivation of dependency trees representing syntactic structures. To process non-planarity online, the semantic transition-based parser uses a new technique to dynamically reorder nodes during the derivation. While the synchronised derivations allow different structures to be built for the semantic non-planar graphs and syntactic dependency trees, useful statistical dependencies between these structures are modeled using latent variables. The resulting synchronous parser achieves competitive performance on the CoNLL-2008 shared task, achieving relative error reduction of 12 % in semantic F score over previously proposed synchronous models that cannot process non-planarity online. 1

To truly understand language, an intelligent system must be able to connect words, phrases, and sentences to its perception of objects and events in the world. Current natural language processing and computer vision systems make extensive use of machine learning to acquire the probabilistic knowledge needed to comprehend linguistic and visual input. However, to date, there has been relatively little work on learning the relationships between the two modalities. In this talk, I will review some of the existing work on learning to connect language and perception, discuss important directions for future research in this area, and argue that the time is now ripe to make a concerted effort to address this important, integrative AI problem.

We present a general framework and learning algorithm for the task of concept labeling: each word in a given sentence has to be tagged with the unique physical entity (e.g. person, object or location) or abstract concept it refers to. Our method allows both world knowledge and linguistic information to be used during learning and prediction. We show experimentally that we can learn to use world knowledge to resolve ambiguities in language, such as word senses or reference resolution, without the use of handcrafted rules or features. 1

Most question-answering systems contain a classifier module which determines a question category, based on which each question is assigned an answer type. However, setting up syntactic patterns for this classification is a big challenge. In addition, in the case of ontology-based systems, the answer type should be aligned to the queried knowledge structure. We present an approach for determining the answer type semi-automatically, by combining syntactic parsing with ontology reasoning. When this combination is not enough to make conclusions automatically, we engage the user into a dialog. User selections are saved and used for training the system in order to improve its performance over time. The answer type is used to show the feedback and the concise answer to the user. Our approach is evaluated using 250 questions from the Mooney Geoquery dataset. 1.

We consider the problem of learning factored probabilistic CCG grammars for semantic parsing from data containing sentences paired with logical-form meaning representations. Traditional CCG lexicons list lexical items that pair words and phrases with syntactic and semantic content. Such lexicons can be inefficient when words appear repeatedly with closely related lexical content. In this paper, we introduce factored lexicons, which include both lexemes to model word meaning and templates to model systematic variation in word usage. We also present an algorithm for learning factored CCG lexicons, along with a probabilistic parse-selection model. Evaluations on benchmark datasets demonstrate that the approach learns highly accurate parsers, whose generalization performance benefits greatly from the lexical factoring. 1

Language is sensitive to both semantic and pragmatic effects. To capture both effects, we model language use as a cooperative game between two players: a speaker, who generates an utterance, and a listener, who responds with an action. Specifically, we consider the task of generating spatial references to objects, wherein the listener must accurately identify an object described by the speaker. We show that a speaker model that acts optimally with respect to an explicit, embedded listener model substantially outperforms one that is trained to directly generate spatial descriptions. 1

Abstract. We seek to give everyday technical teams the capability to build robust natural language interfaces to their databases, for subsequent use by casual users. We present an approach to the problem which integrates and streamlines earlier work based on light annotation and authoring tools. We model queries in a higher-order version of Codd’s tuple calculus and we use synchronous grammars extended with lambda functions to represent semantic grammars. The results of configuration can be applied directly to SQL based databases with general n-ary relations. We have fully implemented our approach and we present initial empirical results for the Geoquery 250 corpus. 1

A semantic parser learning system learns to map natural language sentences into their domain-specific formal meaning representations, but if the constructs of the meaning representation language do not correspond well with the natural language then the system may not learn a good semantic parser. This paper presents approaches for automatically transforming a meaning representation grammar (MRG) to conform it better with the natural language semantics. It introduces grammar transformation operators and meaning representation macros which are applied in an error-driven manner to transform an MRG while training a semantic parser learning system. Experimental results show that the automatically transformed MRGs lead to better learned semantic parsers which perform comparable to the semantic parsers learned using manually engineered MRGs.