We propose several improvements to the hierarchical phrase-based MT model of Chiang (2005) and its syntax-based extension by Zollmann and Venugopal (2006). We add a source-span variance model that, for each rule utilized in a probabilistic synchronous context-free grammar (PSCFG) derivation, gives a confidence estimate in the rule based on the number of source words spanned by the rule and its ...

In a recent exchange, Moro (2014) and Pulvermüller (2014) re-open a longstanding debate in the language sciences. Ever since the 1975 Royaumont encounter that set the agenda for linguistics and the classical cognitive sciences, generative linguists, whose ultimate goal we take to be to shed light on the biological basis for language, have rejected any attempt of a rapprochement between natural ...

A central assumption in generative grammar research on the relationship between syntax and the lexicon is that syntax is a projection of the lexicon. The structure of sentences is a refl ection of the lexical properties of the individual lexical items they contain. In the standard view, each lexical item is associated with a lexical entry that contains three kinds of information, as indicated i...

We present a syntax-based language model for use in noisy-channel machine translation. In particular, a language model based upon that described in (Cha01) is combined with the syntax based translation-model described in (YK01). The resulting system was used to translate 347 sentences from Chinese to English and compared with the results of an IBM-model-4-based system, as well as that of (YK02)...

In this paper a learning system is presented that is able to learn both the syntax (from an over-generalized grammar) and semantic rules (containing threshold values and relations) of an ECG grammar. These rules are used to direct the classiication of QRS complexes and to distinquish between QRS and non-QRS patterns. The system demonstrates how theory revision method can be used to reene large ...

This paper presents recent natural language work on HARC, the BBN Spoken Language System. The HARC system incorporates the Byblos system [6] as its speech recognition component and the natural language system Delphi, which consists of a bottom-up parser paired with an integrated syntax/semantics unification grammar, a discourse module, and a database question-answering backend. The paper focuse...

Kawâkib is a tool allowing feedback between arabic corpus and grammar. As far as methodology is concerned, this interactive online software implements and illustrates the grammar variation method that aims to determine the optimal algorithm, either for morphology – which is essential in semitic languages or for syntax. The software also permits the search for criteria for text filtering. Mots-c...

The structure of a choice-driven interactive story can be modeled as a syntax tree, generated by a player from a grammar, which in turn was generated by a game author. Using this grammar metaphor, “Boswell”, a web-based Integrated Development Environment, was developed for writing, testing, playing and sharing choice-based interactive fiction scripts. The system includes a domain-specific langu...

Models based on Chomskyan grammar are not as pervasive in certain NLP applications as might be expected from their status in linguistics, comparing to, e.g., statistical n-gram models or vector space models. In contrast, here grammar inference is approached from the viewpoint of constructionist theories of language, which avoid the separation of morphology, syntax, semantics and pragmatics. We ...

In an ordinary syntactic parser, the input is a string, and the grammar ranges over strings. This paper explores generalizations of ordinary parsing algorithms that allow the input to consist of string tuples and/or the grammar to range over string tuples. Such algorithms can infer the synchronous structures hidden in parallel texts. It turns out that these generalized parsers can do most of th...