Roy Bar-Haim

2 paper cards in Mova's library · 2005–2007

Roy Bar-Haim wrote 2 of the papers Mova reads, in 2005–2007, most of them on Part-of-speech tagging; often with Idan Szpektor, Iddo Greental, Ido Dagan.

Papers

Semantic Inference at the Lexical-Syntactic Level for Textual Entailment Recognition (2007)
The paper proposes a proof system for textual entailment that works directly on dependency trees. Entailment rules, manual or acquired from WordNet and from DIRT-style paraphrase data, rewrite the text tree step by step towards the hypothesis, and a cost function measures the remaining distance when no full proof is…
Choosing an Optimal Architecture for Segmentation and POS-Tagging of Modern Hebrew (2005)
Bar-Haim et al. build an HMM segmenter and POS tagger for Modern Hebrew from a morphological analyser and a very small tagged corpus (the Hebrew Treebank, from Ha'aretz, with under 30K words per training fold), plus about 340K untagged words. They compare two tokenisations: a word-level model, where each tag is a…