Learn More
This article presents an algorithm for translating the Penn Treebank into a corpus of Combinatory Categorial Grammar (CCG) derivations augmented with local and long-range word–word dependencies. The resulting corpus,CCGbank,includes 99.4% of the sentences in the Penn Treebank. It is available from the Linguistic Data Consortium,and has been used to train(More)
"Two weeks later, Bonadea had already been his lover for a fortnight."-Robert Musil, Der Mann ohne Eigenschaften. A semantics of temporal categories in language and a theory of their use in defining the temporal relations between events both require a more complex structure on the domain underlying the meaning representations than is commonly assumed. This(More)
This paper addresses the problem of learning to map sentences to logical form, given training data consisting of natural language sentences paired with logical representations of their meaning. Previous approaches have been designed for particular natural languages or specific meaning representations; here we present a more general method. The approach(More)
We present an algorithm which translates the Penn Treebank into a corpus of Combinatory Categorial Grammar (CCG) derivations. To do this we have needed to make several systematic changes to the Treebank which have to effect of cleaning up a number of errors and inconsistencies. This process has yielded a cleaner treebank that can potentially be used in any(More)
We consider the problem of learning fac-tored 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(More)
We describe an implemented system which <italic>automatically</italic> generates and animates conversations between multiple human-like agents with appropriate and synchronized speech, intonation, facial expressions, and hand gestures. Conversation is created by a dialogue planner that produces the text as well as the intonation of the utterances. The(More)
This paper compares a number of gen-erative probability models for a wide-coverage Combinatory Categorial Grammar (CCG) parser. These models are trained and tested on a corpus obtained by translating the Penn Treebank trees into CCG normal-form derivations. According to an evaluation of unlabeled word-word dependencies, our best model achieves a performance(More)
We present an annotation scheme for information status (IS) in dialogue, and validate it on three Switchboard dialogues. We show that our scheme has good reproducibility, and compare it with previous attempts to code IS and related features. We eventually apply the scheme to 147 dialogues, thus producing a corpus that contains nearly 70,000 NPs annotated(More)
This paper shows how to construct semantic representations from the derivations produced by a wide-coverage CCG parser. Unlike the dependency structures returned by the parser itself , these can be used directly for semantic interpretation. We demonstrate that well-formed semantic representations can be produced for over 97% of the sentences in unseen WSJ(More)
Part-of-speech (POS) induction is one of the most popular tasks in research on unsuper-vised NLP. Many different methods have been proposed, yet comparisons are difficult to make since there is little consensus on evaluation framework, and many papers evaluate against only one or two competitor systems. Here we evaluate seven different POS induction systems(More)