Your Name

Hassan S. Shavarani

(Pronunciation: /hah-san ʃah-va-rah-ni/)

Email: sshavara@sfu.ca

LinkedIn: linkedin.com/in/shavarani

Academic CV: Download

Research Statement: Download

Research Interests: Neural Entity Linking, Clinical Information Extraction, Question Answering, Natural Language Processing, Deep Learning

Bio

I did my PhD at the Natural Language Processing Lab in the School of Computing Science at Simon Fraser University in Vancouver, Canada. My research uses pre-trained language models and structured prediction based fine-tuning methods. My published work includes using structured prediction to extract linguistically useful representation learning from pre-trained models for neural machine translation, work on policy generation for simultaneous neural machine translation, novel pre-training, fine-tuning and structured prediction inference for entity linking to ontologies like Wikipedia, analyzing the strengths and weaknesses of recent entity linking methods without relying on hand-crafted candidate sets, and information extraction, specifically entity linking, as an alternative to retrieval-augmented generation methods, for enhancing large language models for question answering.

Education

Doctor of Philosophy (PhD) in Computing Science

Simon Fraser University, 2024

Senior Supervisor: Dr. Anoop Sarkar

GPA: 4.25/4.00

Dissertation Title: Structured Prediction for Compute Efficient and High Accuracy NLP (Download)

Master of Science (MSc) in Computing Science

Simon Fraser University, 2016

Supervisor: Dr. Anoop Sarkar

GPA: 3.93/4.00

Thesis Title: Training Data Annotation for Segmentation Classification in Simultaneous Translation (Download)

Bachelor of Science (BSc) in Information Technology

Amirkabir University of Technology - Tehran Polytechnic, 2014

Capstone Project Advisor: Dr. Shahram Khadivi

GPA: 17.69/20

Capstone Project Title: The Design and Implementation of a New Webpage Classification Method Using WordNet (Download Abstract)

Research Experience

Ph.D. Research Assistant

Simon Fraser University, September 2017 - June 2024

Senior Supervisor: Dr. Anoop Sarkar

  • Investigated structured prediction for simplifying and improving various NLP tasks relying on pre-trained language models as part of a Ph.D. dissertation.
  • Conducted research on retrieval-augmented question answering, neural entity linking, neural machine translation and multi-lingual document classification.
  • Presented research findings at NAACL'24, EMNLP'23, EACL'21, and LREC'20.
  • Developed Entity Retrieval, an entity linking approach to retrieval-augmented question answering, SpEL, the state-of-the-art entity linking framework using structured prediction, and SFUTranslate, an academic neural machine translation toolkit with a focus on readability and changeability.
  • Created AIDA/testc, a new challenging test set to evaluate modern entity linking models, containing 131 annotated news articles.
  • Created Shinra-5LDS, a large multi-lingual and multi-labeled set of annotated Wikipedia articles in Japanese, English, French, German, and Farsi using Extended Named Entity (ENE) tag set.
  • Published 10 research papers in the course of the Ph.D. program.
  • Mentored 2 research projects in the course of the Ph.D. program.
  • Collaborated with Language Information Access Technology Team at Riken Center for Advanced Intelligence Project, Tokyo, Japan.

Research and Development Associate

Emtelligent Inc., August 2020 - December 2023

Supervisor: Dr. Anoop Sarkar

  • Designed and implemented deep learning models for entity linking in medical NLP.
  • Conducted research on the design of large-scale unsupervised neural models for multi-task learning in medical NLP.

Data Science Intern

Traction on Demand, January 2019 - April 2019

Supervisor: Vince Liu

  • Conducted research on negative opinion mining in slack messages from employees.
  • Performed data anonymization to remove traces of the employees.
  • Performed sentiment analysis using OpenAI’s sentiment neuron and conducted exploratory data analysis to identify trends and patterns in collected messages.
  • Presented insights and findings to team members and stakeholders through clear and concise reports.

Research Intern

Riken Center for Advanced Intelligence Project, May 2018 - August 2018

Supervisor: Dr. Satoshi Sekine

  • Developed a graph-based algorithm to expand the Shinra Japanese dataset to English, French, German, and Farsi using the Wikipedia language links.
  • Created a data visualization tool based on brat rapid annotation tool to demonstrate the extracted information.

Research Intern

TextIQ Labs Canada Inc., June 2016 - September 2016

Supervisor: Dr. Apoorv Agarwal

  • Designed and implemented an attention-based deep learning model for information extraction from unstructured email text.
  • Created a data visualization tool based on brat rapid annotation tool to demonstrate the extracted information.

M.Sc. Research Assistant

Simon Fraser University, September 2014 - May 2016

Supervisor: Dr. Anoop Sarkar

  • Conducted research on simultaneous text-to-text machine translation.
  • Conducted experiments and analyzed data, published and presented research findings at IWSLT'15.
  • Developed expertise in statistical NLP with a special focus on statistical machine translation.

B.Sc. Research Assistant

Amirkabir University of Technology - Tehran Polytechnic, May 2013 - April 2014

Advisor: Dr. Shahram Khadivi

  • Conducted research on a multi-hop Farsi news document classification technique.
  • Conducted experiments on using machine translation to translate Farsi articles into English and perform unsupervised document classification through keyword extraction and semantic similarity between document class labels and the document keywords.

Teaching Experience

Teaching Faculty

British Columbia Institute of Technology, September 2019 - December 2024

  • Offered Artificial Intelligence (COMP 8085) for 6 semesters to multiple classes of 20 students (on average).
  • Offered Advanced Algorithms and Data Structures Design and Analysis (COMP 8042) for 10 semesters to multiple classes of 20 students (on average).
  • Offered Artificial Intelligence for Games Development (COMP 8901) for one semester before proposing to morph the course into COMP 8085.
  • Responsible for design of the teaching material including the slides, assignments and exams as well as the grading.
  • Supervised several software development projects in the ISSP (Industry Sponsored Student Projects) program.

Sessional Instructor

Capilano University, September 2024 - December 2024

  • Offered Computers and their applications (COMP 101) for one semester.
  • Responsible for delivering the lectures as well as grading the assignments and exams.

Sessional Instructor

Simon Fraser University, January 2018 - April 2024

  • Offered Introduction to Web Design and World Wide Web (CMPT 165) for one semester [Outline and Material].
  • Responsible for design of the teaching material including the slides, assignments and exams as well as the grading.

Mathematics Tutor

Teachers' Tutoring Service, April 2019 - June 2019

  • Tutoring for Math 8, Pre-Calc 11, and Math 12.

Workshop Instructor

Amirkabir University of Technology - Tehran Polytechnic, June 2017

  • Offered a workshop on Programming in React.js with an introduction to different React.js modules and libraries including Redux and Reflux [Outline and Material].

Teaching English as a Foreign Language (TOEFL)

Shokuh’s English Institute in Tehran, March 2012 - May 2012

  • Teaching skills required to excel in Reading, Listening, and Writing parts of paper-based TOEFL examination.

JavaSE Programming Instructor

Information Technology Association - Islamic Azad University, January 2012 - February 2012

  • Teaching object-oriented programming in Java Standard Edition.

Publications

Conference Papers

Hassan S. Shavarani, and Anoop Sarkar. "Entity Retrieval for Answering Entity-Centric Questions." Under review for the 2024 Conference on Empirical Methods in Natural Language Processing, 2024.

Nicolas Ong, Hassan S. Shavarani, and Anoop Sarkar. "Unified Examination of Entity Linking in Absence of Candidate Sets." In Proceedings of the 2024 Annual Conference of the North American Chapter of the Association for Computational Linguistics, 2024.

Hassan S. Shavarani, and Anoop Sarkar. "SpEL: Structured Prediction for Entity Linking." In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp. 11123-11137. 2023.

Ashkan Alinejad, Hassan S. Shavarani, and Anoop Sarkar. "Translation-based supervision for policy generation in simultaneous neural machine translation." In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 1734-1744. 2021.

Hassan S. Shavarani, and Anoop Sarkar. "Better Neural Machine Translation by Extracting Linguistic Information from BERT." In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pp. 2772-2783. 2021.

Hassan S. Shavarani, and Satoshi Sekine. "Multi-class Multilingual Classification of Wikipedia Articles Using Extended Named Entity Tag Set ." In Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 1197-1201. 2020.

Jetic Gū, Hassan S. Shavarani, and Anoop Sarkar. "Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing." In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 401-413. 2018.

Maryam Siahbani, Hassan S. Shavarani, Ashkan Alinejad, and Anoop Sarkar. "Simultaneous translation using optimized segmentation ." In Proceedings of the 13th Conference of the Association for Machine Translation in the Americas (Volume 1: Research Track), pp. 154-167. 2018.

Hassan S. Shavarani, Maryam Siahbani, Ramtin Mehdizadeh Seraj, and Anoop Sarkar. "Learning segmentations that balance latency versus quality in spoken language translation." In Proceedings of the 12th International Workshop on Spoken Language Translation: Papers, pp. 217-224. 2015.

Preprint and ArXiv Papers

Nasrin Seifi, and Hassan S. Shavarani. "Predicting Idiosyncratic Volatility from Stock Market Trade Records: A Machine Learning Approach ." 2023.

Jetic Gū, Hassan S. Shavarani, and Anoop Sarkar. "Pointer-based fusion of bilingual lexicons into neural machine translation." arXiv preprint arXiv:1909.07907. 2019.

Awards and Scholarships

Helmut and Hugo Eppich Family Graduate Scholarship - Ebco Eppich Competition Simon Fraser University, 2020, 2021 and 2024.

Upper Bound Talent Bursary Alberta Machine Intelligence Institute (Amii), Summer 2023.

Clark, Wilson Graduate Scholarship - Ebco Eppich Competition Simon Fraser University, Spring 2022.

Faculty of Applied Sciences Graduate Fellowship Award Simon Fraser University, Fall 2020.

MITACS Research Training Award Mitacs, Summer 2020.

Computing Science Travel Award Simon Fraser University, Summer 2020.

Graduate Fellowship Award Simon Fraser University, 2015-2020.

Century 21 Charlwood Family Award - Ebco Eppich Competition Simon Fraser University, Spring 2019.

Service

Peer reviewer in CanAI 2019, ACL 2020, EMNLP 2021, T-ASL 2024, COLM 2024, ARR 2022-2024.

Area chair in EMNLP 2024 (ARR June 2024 Cycle).