--- title: "Roy Bar-Haim — papers and cards" description: "Roy Bar-Haim: 2 paper cards in the Research library (2005–2007), with what each paper is about, the ideas Mova took from it, and the co-authors." canonical: "https://research.elamur.ai/free/en/authors/roy-bar-haim/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/roy-bar-haim/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Roy Bar-Haim # Roy Bar-Haim 2 paper cards in the Research library · 2005–2007 Roy Bar-Haim wrote 2 of the papers Mova reads, in 2005–2007, most of them on [Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/); often with [Idan Szpektor](https://md.research.elamur.ai/free/en/authors/idan-szpektor/), Iddo Greental, [Ido Dagan](https://md.research.elamur.ai/free/en/authors/ido-dagan/). Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Roy+Bar-Haim) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Roy+Bar-Haim) · [dblp](https://dblp.org/search?q=Roy+Bar-Haim) · [ACL Anthology](https://aclanthology.org/search/?q=Roy+Bar-Haim) · [ORCID](https://orcid.org/orcid-search/search?searchQuery=Roy+Bar-Haim) Topics: [Part-of-speech tagging](https://md.research.elamur.ai/free/en/topics/part-of-speech-tagging/) 1 ## Papers 1. **[Semantic Inference at the Lexical-Syntactic Level for Textual Entailment Recognition](https://md.research.elamur.ai/free/en/papers/haim-2007-semantic-inference-lexical-syntactic-level/)** *(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… 2. **[Choosing an Optimal Architecture for Segmentation and POS-Tagging of Modern Hebrew](https://md.research.elamur.ai/free/en/papers/aclbulk-2005-haim-choosing-optimal-architecture-segmentation-pos/)** *(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… ## Co-authors (6) - [Idan Szpektor](https://md.research.elamur.ai/free/en/authors/idan-szpektor/) - Iddo Greental - [Ido Dagan](https://md.research.elamur.ai/free/en/authors/ido-dagan/) - [Khalil Sima'an](https://md.research.elamur.ai/free/en/authors/khalil-sima-an/) - Moshe Friedman - [Yoad Winter](https://md.research.elamur.ai/free/en/authors/yoad-winter/)