In the framework of statistical machine translation (SMT), correspondences between the words in the source and the target language are learned from bilingual corpora on the basis of so-called alignment models. Many of the statistical systems use little or no linguistic knowledge to structure the underlying models. In this paper we argue that training data is typically not large enough to suÆcie...

The term incorporation canonically refers to cases of complementation in which a theme argument, lacking functional structure, is syntactically fused with the verb. In this pristine form incorporation appears to be a close kin of word-level compounding. Recently, however, the term has been extended to apply to structures in which the theme argument is realized as a full blown noun phrase and sh...

The paper presents WCCL, a new formalism and toolkit for constructing morpho-syntactic features, a crucial task for many natural language processing algorithms. One existing solution, JOSKIPI, is analysed from two perspectives: features of the formalism as well as software engineering-related issues. Then we propose its successor. A short case study follows, exemplifying the improvement enabled...

1 Abstract In this paper I shall propose an account of morphosyntactic phenomena like European Por-tuguese (hence: EP) cliticization in terms of interacting morphophonological and surface-syntactic constraints. In particular, I suggest that mor-phophonological constraints are partially under-speciied with respect to morpheme linearization, information that will be added monotonically by surface...

The aim of this article is to describe the morpho-syntactic alternations Old English verbs inaction. method includes analysis syntactic constructions in which inaction are found and themselves, described as argumenthood, morphological case, prepositional government structural complexity. Two types alternation identified on basis affected argument. dative reflexive involve both first second argu...

Research on first language (L1) acquisition has shown that typically developing children acquire a large part of morpho-syntax by the age of 4 (Guasti, 2002). Similarly, studies investigating how children process morpho-syntactic information have revealed that by the same age, their processing routines do not differ from those used by adults (Clahsen & Felser, 2006). However, there is one struc...

This paper introduces , an XML format developed to serialise the object model defined by the ISO Syntactic Annotation Framework SynAF. Basing on widespread best practices we adapt a popular XML format for syntactic annotations, TigerXML, with additional features to support a variety of syntactic phenomena including constituent and dependency structures, binding, and different node type...

This paper describes an unusual approach to the partial syntactic analysis of unrestricted German text. Unlike most other chunk parsers, which are specially designed and implemented for the single purpose of annotating syntactic structures, YAC is the result of a slow evolution from on-line to off-line analysis. As we formulated increasingly complex queries in the CQP query language, some of wh...

This paper presents two approaches to Portuguese anaphor resolution, one based on a morpho-syntactic information and other on semantic features. We present a corpus based evaluation, focusing especially on anaphoric definite descriptions, which includes direct, indirect and associative anaphors.

We investigated whether brain potentials of grammatical aspect processing resemble semantic or morpho-syntactic processing, or whether they instead are characterized by an entirely distinct pattern in the same individuals. We studied aspect from the perspective of agreement between the temporal information in the context (temporal adverbials, e.g., Right now) and a morpho-syntactic marker of gr...