Master of Science (MSc) @
Sheffield Hallam University
I focus on extracting actionable insights from data and build models for automated planning and decision making. I have diverse experience of applying machine learning algorithms in a wide range of domains with a particular emphasis on natural language processing. At different times, I have wore the hats of applied machine learner, applied research scientist, software engineer,
I focus on extracting actionable insights from data and build models for automated planning and decision making. I have diverse experience of applying machine learning algorithms in a wide range of domains with a particular emphasis on natural language processing. At different times, I have wore the hats of applied machine learner, applied research scientist, software engineer, hands-on prototyper, data miner, and product manager.
• 12+ years’ hands-on experience in building Natural Language Processing (NLP) systems using Machine Learning techniques. led a group of computational linguists engineers worldwide and successfully research and deliver all projects participated.
• Senior research scientist at VoiceBox Technologies, responsible for the research and development of the Spoken Language Understanding system running on the mobile platform, providing Siri-like personal assistant via Voice Search for one of the largest global mobile phone manufacturer.
• Gained inside-out knowledge and applied the machine learning algorithms on unstructured data for tasks like formation extraction, sentiment analysis, document classification and clustering, at the world-renowned NLP research group, University of Sheffield. Published more than 20 research papers on renowned journals and international conferences.
• Lead and mentor team members on various technical issues. Proved track records for fast conceiving and testing solutions to the technical challenges, enjoy working with BIG data problems. Possessed excellent team-work and communications skills.
• Machine learning algorithms: SVM, Random Forrest, Conditional Random Fields, Logistic Regression, Latent Dirichlet Allocation, k-means clustering, sparse filtering and Active Learning. Feature Engineering and model selection.
• Natural Language Processing: Stanford NLP package, NLTK, GATE, NetOwl (rule-based system)
• Programming language: Python, Perl, Java and Unix Shell scripting
Data Scientist Lead, Senior Manager @ From August 2015 to Present (5 months) London, United KingdomSenior Research Data Scientist @ Being research sceintist at VoiceBox Technologies, responsible for the research and development of the conversational agent running on the mobile platform, providing Siri-like personal assistant solutions for one of the largest global mobile phone manufacturers.
Statistical modelling to solve spoken language understanding problem: building statistical models to predict customers' intent and extract relevant entities from huge amount Automatic Speech Recognition data.
Modelling human-machine dialog interactive using supervised/unsupervised machine learning techniques. From September 2013 to August 2015 (2 years) Senior Computational Linguist Consultant (Contract) @ Designed, implemented and tested the Information Extraction Systems using the cutting edge NLP technology to enrich LN's vast legal contents. The system has been integrated into the LexisAdvance product and is part of LN's next generation Content System Architecture to facilitate legal research.
Worked closely with Subject Matter Experts to derive, document and implement product requirements for information extraction and coding logic across multiple medical specialties.
Pursued the development and testing of new ideas, defined development goals and provided guidance on selecting and validating the best approaches to resolve problems.
Applied agile development practices and rigorous quality assurance testing to ensure high quality results that meet product requirements.
Also been responsible for software maintenance and enhancement. From September 2010 to July 2013 (2 years 11 months) London, United KingdomResearch Associate @ Design, implement and testing supervised and unsupervised machine learning techniques (SVM, Naïve Bayes, Clustering, HMM) applied to a wide arrange of Natural Language Processing problems, such as Word Sense Disambiguation, Information Extraction, Document Classification and Filtering, and NLP-based Information Retrieval.
Published more than 20 research papers on renowned journals and international conferences. From 2002 to 2010 (8 years) Sheffield, United Kingdom
Master of Science (MSc), Business Intelligence, Postgraduate Certificate with Merit @ Sheffield Hallam University From 2009 to 2010 Doctor of Philosophy (Ph.D.), Natural Language Process, Information Retrieval @ Fudan University From 1999 to 2002 Master of Science (MSc), Computer Science @ Fudan University From 1996 to 1999 BSc., Electrical Engineering @ Tsinghua University From 1992 to 1996 Yikun Guo is skilled in: Information Retrieval, Natural Language Processing, Machine Learning, Information Extraction, Data Mining, Text Mining, Software Development, Word Sense Disambiguation, Python, GATE, NLTK, Perl, C++, Weka, Lucene
Looking for a different
Get an email address for anyone on LinkedIn with the ContactOut Chrome extension