Phrase

About: Phrase is a research topic. Over the lifetime, 12580 publications have been published within this topic receiving 317823 citations. The topic is also known as: syntagma & phrases.

Chunk-level reordering of source language sentences with automatically learned rules for statistical machine translation

Abstract: In this paper, we describe a source-side reordering method based on syntactic chunks for phrase-based statistical machine translation. First, we shallow parse the source language sentences. Then, reordering rules are automatically learned from source-side chunks and word alignments. During translation, the rules are used to generate a reordering lattice for each sentence. Experimental results are reported for a Chinese-to-English task, showing an improvement of 0.5%--1.8% BLEU score absolute on various test sets and better computational efficiency than reordering during decoding. The experiments also show that the reordering at the chunk-level performs better than at the POS-level.

Connectivity in specificational sentences

Abstract: This paper is concerned with the relationship between the semantics of specificational and predicational sentences and the Connectivity effects they display. It discusses the advantages and disadvantages of semantic and syntactic approaches to Connectivity (the ‘unconstrained-be theory’, the ‘question-in-disguise theory’, and the ‘unclefting theory’), concluding that a semantic theory of Connectivity is not only preferable, but necessary. The paper also discusses the implications of such a move regarding Binding phenomena (i.e., Principle A, B, and C effects): adopting a semantic theory of Connectivity requires a theory of Binding which is different from the standard GB Binding Theory.

Morphology-Aware Statistical Machine Translation Based on Morphs Induced in an Unsupervised Manner

Abstract: In this paper, we apply a method of unsupervised morphology learning to a state-of-the-art phrase-based statistical ma chine translation (SMT) system. In SMT, words are traditionally used as the smallest units of translation. Such a system generalizes poorl y to word forms that do not occur in the training data. In particular, this is problematic for languages that are highly compounding, highly inflecting, or both. An alternative way is to use sub-word units, such as morphemes. We use the Morfessor algorithm to find statistical mo rphemelike units (called morphs) that can be used to reduce the size of the lexicon and improve the ability to generalize. Transl ation and language models are trained directly on morphs instead of words. The approach is tested on three Nordic languages (Danish, Finnish, and Swedish) that are included in the Europarl corpus consisting of the Proceedings of the European Parliament. However, in our experiments we did not obtain higher BLEU scores for the morph model than for the standard word-based approach. Nonetheless, the proposed morph-based solution has clear benefits, as morpho logically well motivated structures (phrases) are learned , and the proportion of words left untranslated is clearly reduced.

The parser doesn't ignore intransitivity, after all

Abstract: Several previous studies (B. C. Adams, C. Clifton, & D. C. Mitchell, 1998; D. C. Mitchell, 1987; R. P. G. van Gompel & M. J. Pickering, 2001) have explored the question of whether the parser initially analyzes a noun phrase that follows an intransitive verb as the verb's direct object. Three eye-tracking experiments examined this issue in more detail. Experiment 1 replicated the finding that readers experience difficulty on this noun phrase in normal reading and found that this difficulty occurs even with intransitive verbs for which a direct object is categorically prohibited. Experiment 2, however, demonstrated that this effect is not due to syntactic misanalysis but to disruption that occurs when a comma is absent at a subordinate clause/main clause boundary. Experiment 3 replicated the finding (M. J. Pickering & M. J. Traxler, 2003; M. J. Traxler & M. J. Pickering, 1996) that when a noun phrase "filler" is an implausible direct object for an optionally transitive relative clause verb, processing difficulty results; however, there was no evidence for such difficulty when the relative clause verb was strictly intransitive. Taken together, the 3 experiments undermine the support for the claim that the parser initially ignores a verb's subcategorization restrictions.