A persistent question in the SLA (second language acquisition) research concerns the status of the involvement of the native language (i.e. L1 transfer). Inquiry into the question has been made on the basis of a variety of linguistic frameworks, such as contrastive analysis (Lado, 1957), L2 (second language) generative parametric approach (Flynn, 1987; White, 1989; Schwartz, 1996), and the more...

We present a lemma induction scheme on a target language through minimally supervised alignment and transfer methods utilizing English-to-German parallel corpora. Compared to previous alignment and transfer approaches, the approach outlined here increases computational efficiency and significantly reduces the level of supervision necessary in inducing clusters of inflectional forms. Furthermore...

At the risk of stating the obvious to an audience such as this, I should like to remind you that translation can be defined as the transfer of meaning from one language to another. This is essentially an intellectual process because to be able to transfer meaning reliably, I would contend that the translator must first understand the source text and then, based on that understanding, express th...

We present our work on semi-supervised parsing of natural language sentences, focusing on multi-source crosslingual transfer of delexicalized dependency parsers. We first evaluate the influence of treebank annotation styles on parsing performance, focusing on adposition attachment style. Then, we present KLcpos3 , an empirical language similarity measure, designed and tuned for source parser we...

We propose a path-based transfer model for machine translation. The model is trained with a word-aligned parallel corpus where the source language sentences are parsed. The training algorithm extracts a set of transfer rules and their probabilities from the training corpus. A rule translates a path in the source language dependency tree into a fragment in the target dependency tree. The problem...

Issues revolving around transportability and technology transfer have been of growing interest to natural language processing development. This paper describes an experiment performed to test the modularity of the Martin Marietta EQUAL natural language processor, by adapting this database interface system to English-Korean machine translation task. The methodology included altering the applicat...

In the dark ages of machine translation, it is said that researchers at tempted a Direct Approach--word-for-word substitution. But this could not have survived much beyond the first inspection of the output. The most common approach adopted in working machine translation systems is the Transfer Approach illustrated in Figure 1. A text in a source language is analyzed to some depth, producing, f...

We prove that every recursively enumerable language can be generated by a programmed grammar with context-free core rules using unconditional transfer with leftmost derivation of type 3 or type 2. We show that every recursively enumerable tally language can be generated by a programmed grammar with context-free core rules using unconditional transfer or by some k-limited ET0L system, where k 2 ...

The paper focuses on the issues of language structures disambiguation in machine translation.The moodel for establishing semantic content of syntactic structures in the English and Russian languages is proposed. Particular attention is given to syntactic polysemy and ambiguity, and the mechanisms of disambiguation. The phenomenon of syntactic polysemy determines the possible multiple transfer s...

This paper describes the transfer component of a syntax-based Example-based Machine Translation system. The source sentence parse tree is matched in a bottom-up fashion with the source language side of a parallel example treebank, which results in a target forest which is sent to the target language generation component. The results on a 500 sentences test set are compared with a top-down appro...