We report the results of experiments designed to investigate the effects of prosodic boundaries on resolving ambiguous syntactic clause boundaries in Japanese. The head-final, prodrop nature of this language generates abundant syntactic attachment ambiguity for sentences that contain relative clauses. Two types of sentences with differing head nouns modified by relative clauses were examined. S...

phrase with a single argument structure. Complex predicates of this sort are found in Japanese, Turkish, and Persian, among many others. Since complex predicates are so generally available, they must be the result of very general linguistic processes, which I will propose are part of syntax and the syntax/interpretative interface, or logical form. In this paper I consider two kinds of syntactic...

Reading disability in children with dyslexia has been proposed to reflect impairment in auditory timing perception. We investigated one aspect of timing perception--temporal grouping--as present in prosodic phrase boundaries of natural speech, in age-matched groups of children, ages 6-8 years, with and without dyslexia. Prosodic phrase boundaries are characterized by temporal grouping of functi...

In this paper we describe the results of experiments contrasting syntactic phrase indexing with statistical phrase indexing for Dutch texts. Our results showed that we at least need a compound splitting algorithm for good quality retrieval for Dutch texts. If we then add either syntactic or statistical phrases, performance generally improves, but this eeect is never statistically signiicant. If...

We improve the quality of paraphrases extracted from parallel corpora by requiring that phrases and their paraphrases be the same syntactic type. This is achieved by parsing the English side of a parallel corpus and altering the phrase extraction algorithm to extract phrase labels alongside bilingual phrase pairs. In order to retain broad coverage of non-constituent phrases, complex syntactic l...

Normally, the tense and aspect systems of natural languages do not coincide and the correct translation of the tense forms needs a semantic analysis of the text or sentence which uses these forms. The problem with semantic representations is that, often, ambiguities cannot be resolved, though a remarkable effort of inferencing has been invested to the effect that the analysis of the source text...

A key concern in building syntax-based machine translation systems is how to improve coverage by incorporating more traditional phrase-based SMT phrase pairs that do not correspond to syntactic constituents. At the same time, it is desirable to include as much syntactic information in the system as possible in order to carry out linguistically motivated reordering, for example. We apply an exte...

This paper presents a practical approach to statistical machine translation (SMT) based on syntactic transfer. Conventionally, phrase-based SMT generates an output sentence by combining phrase (multiword sequence) translation and phrase reordering without syntax. On the other hand, SMT based on tree-to-tree mapping, which involves syntactic information, is theoretical, so its features remain un...

ii Acknowledgements iii List of Abbreviations iv Section 1: Introduction 1 Section 2: The Spanish Present Subjunctive 3 2.1. Concordantia Temporum 3 2.2. The Present Subjunctive in Argentinean Spanish 5 2.3. Previous Accounts of Violations of Concordantia Temporum 7 Section 3: Time and Language 14 3.1. Tensed and Tenseless Languages 14 3.2. Reichenbach‟s Theory of Tense 18 3.3. Hornstein‟s Neo-...

This paper presents a method for verb phrase (VP) alignment in an English/French parallel corpus and its use for improving statistical machine translation (SMT) of verb tenses. The method starts from automatic word alignment performed with GIZA++, and relies on a POS tagger and a parser, in combination with several heuristics, in order to identify non-contiguous components of VPs, and to label ...