Antal van den Bosch

3 paper cards in Mova's library · 1997–2012

Antal van den Bosch wrote 3 of the papers Mova reads, in 1997–2012, most of them on Part-of-speech tagging, Machine translation; often with Abdelhadi Soudi, Emiel Krahmer, Erwin Marsi.

The profile is the library's match of the name; two people with one name are not always told apart.

Papers

Sentence Simplification by Monolingual Machine Translation (2012)
The paper simplifies sentences with an off-the-shelf phrase-based statistical MT system (Moses), trained on aligned Wikipedia and Simple Wikipedia sentences.
Memory-Based Morphological Analysis Generation and Part-of-Speech Tagging of Arabic (2005)
The paper applies memory-based learning (k-nearest neighbours, TiMBL) to two tasks on unvowelised Arabic from the Arabic Treebank 1: generating all vocalised analyses of a word, and tagging the part of speech.
IGTree: Using Trees for Compression and Classification in Lazy Learning Algorithms (1997) measured
The paper introduces IGTree, a compressed approximation of memory-based (nearest-neighbour) learning. Features are ordered once by information gain, and the training instances are stored as a decision tree in which every level tests the next most informative feature. Each node keeps its default (most frequent) class…