Ruochen Xu

About

Hello! I am a 5th-year Ph.D. student working with Professor Yiming Yang in the Language Technologies Institute , School of Computer Science at Carnegie Mellon University . Prior to CMU, I received my B.E. from Department of Electronic Engineering at Tsinghua University

Research Interests

I am interested in Machine Learning and the applications in Human Language Technologies. My current research mainly focuses on Cross-lingual NLP, Transfer Learning and Deep Learning.

Resume[clik to download]

Publication

Ruochen Xu , Tao Ge, Furu Wei "Formality Style Transfer with Hybrid Textual Annotations" arXiv preprint arXiv:1902.08899 (2019) [PDF] [Code]

Ruochen Xu, Yiming Yang, Naoki Otani, Yuexin Wu. "Unsupervised Cross-lingual Transfer of Word Embedding Spaces" Conference on Empirical Methods on Natural Language Processing (EMNLP), 2018 [PDF] [Code] [Supplementary]

Aldrian Obaja Muis, Naoki Otani, Nidhi Vyas, Ruochen Xu, Yiming Yang, Teruko Mitamura, Eduard Hovy "Low-resource Cross-lingual Event Type Detection in Documents via Distant Supervision with Minimal Efforts"   International Conference on Computational Linguistics (COLING) 2018.  [PDF]

Littell, P., Tian, T., Xu, R., Sheikh, Z., Mortensen, D., Levin, L., Tyers, F., Hayashi, H., Horwood, G., Sloto, S., Tagtow, E., Black, A., Yang, Y., Mitamura, T., and Hovy, E. "The ARIEL-CMU situation frame detection pipeline for LoReHLT16: a model translation approach"  Machine Translation.  [PDF]

Ruochen Xu, Yiming Yang "Cross-lingual Distillation for Text Classification"  Annual meeting of the Association for Computational Linguistics (ACL), 2017   [PDF] [Data] [Code]

Ian Gorton, Ruochen Xu, Yiming Yang, Hanxiao Liu, Guoqing Zheng "Experiments in Curation:
Towards Machine-Assisted Construction of Software Architecture Knowledge Bases"
IEEE International Conference on Software Architecture (ICSA), 2017 [PDF] 

Andrew Hsi, Yiming Yang, Jaime G. Carbonell, Ruochen Xu: "Leveraging Multilingual Training for Limited Resource Event Extraction." International Conference on Computational Linguistics (COLING), 2016   [PDF]

Ruochen Xu, Yiming Yang, Hanxiao Liu, and Andrew Hsi. "Cross-lingual Text Classification via
Model Translation with Limited Dictionaries."
ACM International on Conference on Information and Knowledge Management (CIKM), 2016 [PDF]

Gang Zhao, Ping Lv, Ruochen Xu, Qiyu Zhi, Ji Wu. "MSIIPL THU at TAC 2014 Entity Discovery
and Linking track."
In Proc. Text Analysis Conference (TAC) 2014

Professional Activities

Reviewer:
NAACL 2019; COLING 2018; SIGIR 2017;
ACM Transactions on Information Systems; IEEE Access;

Projects

Machine-Assisted Construction of Technical Software Engineering Knowledge Bases

Applied new supervised machine learning algorithms to recommend relevant Web pages to streamline the curation process of knowledge bases. Developed a novel optimization framework which enables the simultaneous learning of the classification model as well as the sentence weights in both labeled and unlabeled documents based on partially observed multi-scope(sentence and document) labels.

TAC KBP (Knowledge Base Population) 2014 Entity Linking Track

Built end-to-end Entity Linking system with query expansion, knowledge base retrieval, feature extraction and supervised ranking. Reached the top three performance among 20 participants in most of the evaluations

Ruochen Xu