We present in this paper the method of English-to-Korean(E-K) transliteration and back-transliteration. In Korean technical documents, many English words are transliterated into Korean words in various forms in diverse ways. As English words and Korean transliterations are usually technical terms and proper nouns, it is hard to nd a transliteration and its variations in a dictionary. Therefore ...

Efficient and versatile processing of any hierarchically structured information requires a learning mechanism that combines lower-level features into higher-level chunks. We investigated this chunking mechanism in humans with a visual pattern-learning paradigm. We developed an ideal learner based on Bayesian model comparison that extracts and stores only those chunks of information that are min...

Most existing systems for Chinese Semantic Role Labeling (SRL) make use of full syntactic parses. In this paper, we evaluate SRL methods that take partial parses as inputs. We first extend the study on Chinese shallow parsing presented in (Chen et al., 2006) by raising a set of additional features. On the basis of our shallow parser, we implement SRL systems which cast SRL as the classification...

This paper presents a template-based machine translation system that extracts templates from a given bilingual corpus, then uses these templates to perform bi-directional EnglishFilipino translations. The system extended the similarity template learning algorithm of Cicekli and Guvenir [2] by refining existing templates and deriving templates from previously learned chunks. Chunk alignment and ...

In this paper, we present a semantic role labeler (or chunker) that groups syntactic chunks (i.e. base phrases) into the arguments of a predicate. This is accomplished by casting the semantic labeling as the classification of syntactic chunks (e.g. NP-chunk, PP-chunk) into one of several classes such as the beginning of an argument (B-ARG), inside an argument (I-ARG) and outside an argument (O)...

This paper analyses the efficiency of different data structures for detecting overlap in digital documents. Most existing approaches use some hash function to reduce the space requirements for their indices of chunks. Since a hash function can produce the same value for different chunks, false matches are possible. In this paper we propose an algorithm that can be used for eliminating those fal...

Self-scheduling algorithms are useful tools for achieving load balance in heterogeneous computational systems. Therefore, they can be applied in computational Grids. In this work, we introduce two families of self-scheduling algorithms. The rst is de ned by methods looking for an explicit form for the chunks distribution function. The second corresponds to methods focusing in deriving an explic...

Sequence-to-sequence models with attention have been successful for a variety of NLP problems, but their speed does not scale well for tasks with long source sequences such as document summarization. We propose a novel coarse-to-fine attention model that hierarchically reads a document, using coarse attention to select top-level chunks of text and fine attention to read the words of the chosen ...

Dominant theories of implicit learning assume that implicit learning merely involves the learning of chunks of adjacent elements in a sequence. In the experiments presented here, participants implicitly learned a nonlocal rule, thus suggesting that implicit learning can go beyond the learning of chunks. Participants were exposed to a set of musical tunes that were all generated using a diatonic...

We report a way to build a series of GOMS-like cognitive user models representing a range of performance at different stages of learning. We use a spreadsheet task across multiple sessions as an example task; it takes about 20~30 min. to perform. The models were created in ACT-R using a compiler. The novice model has 29 rules and 1,152 declarative memory task elements (chunks)—it learns to crea...