Phrase alignment is a crucial step in phrase-based statistical machine translation. We explore a way of improving phrase alignment by adding syntactic information in the form of chunks as soft constraints guided by an in-depth and detailed analysis on a hand-aligned data set. We extend a probabilistic phrase alignment model that extracts phrase pairs by optimizing phrase pair boundaries over th...

In this paper, I present a new nonderivational analysis of the so-called "floating" quantifiers (FQs, hereafter) in English and Korean within the framework of Head-Driven Phrase Structure Grammar (HPSG). 2 I show that FQs do not move from place to place, arguing that English FQs are adverbs modifying verb phrases whereas Korean FQs are complement NPs. I review a derivational approach to English...

In this paper, we discuss the internal structure of Chinese NP. We propose an analysis of Chinese NP in the framework of Head-Driven Phrase Structure Grammar (HPSG henceforth, Pollard and Sag 1994) with the DP conception (see e.g., Abney 1987) incorporated into the theory. Our analysis draws much insights from previous analyses, particularly from Tang (1990a, 1990b) and Gao (1993), though it di...

This paper discusses predicative resultative constructions in Korean and argues that they are actually a kind of clausal resultative construction (see the two types of resultatives in Wechsler and Noh, 2001). In particular, I propose the following hypotheses: (i) the resultative predicate, X-key, is morphosyntactically an adverb rather than an adjective, (ii) X-key forms a fully saturated claus...

Configurational approaches to weak crossover effects in Japanese and Korean have been proposed based on the notions such as c-command and reconstruction (e.g., [5], [25], and [26] among others). However, empirical problems arise from the approaches simply because they cannot fully account for the relevant Korean data. This paper proposes nonconfigurational operator binding conditions formulated...

Sustainable settlement is one of the key constituents of sustainable development, and sustainable urban development can be defined in this framework. Emergence of sustainable development as a commonly-used phrase has caused several controversies about urban forms. Today’s urban form is known as a source of environmental problems. Undoubtedly, this phrase has persuaded many of researchers to sea...

In this paper, we present a novel distortion model for phrase-based statistical machine translation. Unlike the previous phrase distortion models whose role is to simply penalize nonmonotonic alignments[1, 2], the new model assigns the probability of relative position between two source language phrases aligned to the two adjacent target language phrases. The phrase translation probabilities an...

Most statistical machine translation systems use phrase-to-phrase translations to capture local context information, leading to better lexical choice and more reliable local reordering. The quality of the phrase alignment is crucial to the quality of the resulting translations. Here, we propose a new phrase alignment method, not based on the Viterbi path of word alignment models. Phrase alignme...

Hierarchical phrase-based models provide a powerful mechanism to capture non-local phrase reorderings for statistical machine translation (SMT). However, many phrase reorderings are arbitrary because the models are weak on determining phrase boundaries for patternmatching. This paper presents a novel approach to learn phrase boundaries directly from word-aligned corpus without using any syntact...