H
Hany Hassan
Researcher at Microsoft
Publications - 61
Citations - 2439
Hany Hassan is an academic researcher from Microsoft. The author has contributed to research in topics: Machine translation & Language model. The author has an hindex of 22, co-authored 59 publications receiving 2165 citations. Previous affiliations of Hany Hassan include Dublin City University & Airbnb.
Papers
More filters
Posted Content
Achieving Human Parity on Automatic Chinese to English News Translation
Hany Hassan,Anthony Aue,Chang Chen,Vishal Chowdhary,Jonathan H. Clark,Christian Federmann,Xuedong Huang,Marcin Junczys-Dowmunt,William Lewis,Mu Li,Shujie Liu,Tie-Yan Liu,Renqian Luo,Arul Menezes,Tao Qin,Frank Seide,Xu Tan,Fei Tian,Lijun Wu,Shuangzhi Wu,Yingce Xia,Dongdong Zhang,Zhirui Zhang,Ming Zhou +23 more
TL;DR: It is found that Microsoft's latest neural machine translation system has reached a new state-of-the-art, and that the translation quality is at human parity when compared to professional human translations.
ReportDOI
A Statistical Model for Multilingual Entity Detection and Tracking
Radu Florian,Hany Hassan,Abraham Ittycheriah,Hongyan Jing,Nanda Kambhatla,Xiaoqiang Luo,H. Nicolov,Salim Roukos +7 more
TL;DR: This paper presents a statistical language-independent framework for identifying and tracking named, nominal and pronominal references to entities within unrestricted text documents, and chaining them into clusters corresponding to each logical entity present in the text.
Proceedings ArticleDOI
Universal Neural Machine Translation for Extremely Low Resource Languages
TL;DR: The proposed approach utilizing a transfer-learning approach to share lexical and sentence level representations across multiple source languages into one target language is able to achieve 23 BLEU on Romanian-English WMT2016 using a tiny parallel corpus of 6k sentences.
Patent
Method and system for extracting and visualizing graph-structured relations from unstructured text
Hany Hassan,Hala Mostafa +1 more
TL;DR: In this paper, a system, method and computer program for automatically extracting and mining relations and related entities from unstructured text is presented, where relations and entities are extracted by automatically inducting pattern and second by applying these induced patterns to the text data.
Proceedings ArticleDOI
Language Model Based Arabic Word Segmentation
TL;DR: This work approximate Arabic's rich morphology by a model that a word consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme).