Amirhossein Abaskohi

Amirhossein Abaskohi

Computer Science MSc Student at UBC

About me

Greetings! I’m Amir, short for Amirhossein Abaskohi (امیرحسین عباسکوهی). Feel free to call me Amir 😄.

I am currently embarking on my journey as a first-year PhD student at the University of British Columbia, under the supervision of Prof. Giuseppe Carenini and Prof. Peter West. I am part of the UBC Natural Language Processing Group.

I earned my Master of Science in Computer Science from UBC with distinction (A+), under the supervision of Prof. Giuseppe Carenini and Prof. Issam H. Laradji. My master’s thesis, titled Multimodal Understanding of Long Documents: From Topic Modeling to Question Answering, explores two novel methods — CEMTM, a topic modeling technique for long documents that integrates contextual embeddings and cross-modal alignment, and FM²DS, a synthetic-data-generation pipeline to support multimodal, multi-hop question answering in low-resource settings.

Prior to that, I earned my BSc in Computer Engineering from the University of Tehran. During my undergraduate studies, I had the privilege of collaborating with Prof. Azadeh Shakeri, Prof. Yadollah Yaghoobzadeh, and Prof. Behnam Bahrak, enriching my academic experience.

My research interests span across natural language processing, linguistics, and human-centered artificial intelligence. Specifically, I am fascinated by natural language inference and reasoning, long multimodal document reasoning, controlled generation, information retrieval, and deep research–related challenges. My research journey commenced during my second year of undergraduate studies, and since then, I have passionately delved into various problems at the intersection of multimodal understanding and deep research. This endeavor has resulted in several published papers across diverse areas, reflecting my commitment to exploring new frontiers of knowledge.

During my research journey, I have had the privilege of collaborating with researchers from some of the world’s leading research groups, including Google, Salesforce AI, and ServiceNow Research. Since May 2024, I have been working as a visiting research scientist at ServiceNow Research, further expanding my research collaborations. These experiences have enriched my research perspective and broadened my understanding of cutting-edge developments in natural language processing.

Beyond academia, I am enthusiastic about knowledge dissemination and community engagement. I actively share insights and discoveries through platforms like Medium and YouTube, fostering dialogue and knowledge exchange. In addition to my academic pursuits, I have honed my skills in software engineering through practical experiences. I have contributed to back-end development projects at reputable companies in Iran and Canada, including System Group in Summer 2022 and MateMachine for one year since November 2022.

When I’m not working or studying, I love getting lost in the world of novels and comics 📚. They spark my imagination and give me a fun break from my busy life 🌟. I don’t spend a lot of time outdoors, but I really enjoy it when I do. Living in Vancouver, with its amazing natural beauty, gives me plenty of chances to explore. Whether it’s a quiet hike in the forest, a walk along the beach, or watching a colorful sunset, being in nature always makes me feel calm and refreshed. Even though life can be hectic, these little moments in nature remind me to slow down and appreciate the world around me. 🌿✨

I am happy to answer any questions and chat about research/collboration! Reach me at aabaskoh@cs.ubc.ca.

News

  • 2025.08: Graduated with a Master’s degree in Computer Science from UBC 🥳🥳.
  • 2025.08: Three papers accepted to EMNLP 2025: CEMTM and ChartGaze (main proceedings), and FM²DS (Findings).
  • 2025.08: Our paper AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery received the Outstanding Paper Award at REALM@ACL 2025.
  • 2025.05: AgentAda: Skill-Adaptive Data Analytics for Tailored Insight Discovery accepted to REALM@ACL 2025 with an oral presentation.
  • 2025.01: 2/2 of my papers: “BigDocs” and “InsightBench” were accepted for ICLR 2025.
  • 2024.11: I will be attending NeurIPS 2024 and would be delighted to meet and connect with you there!
  • 2024.10: I’m excited to serve as a publicity chair for the Future of NLP Workshop, where I’ll also present my recent research. I look forward to sharing it with you!
  • 2024.10: Our paper entitled “BigDocs: An Open and Permissively-Licensed Dataset for Training Multimodal Models on Document and Code Tasks” has been accepted by RBFM@NeurIPS2024.
  • 2024.03: Our paper entitled “BCAmirs at SemEval-2024 Task 4: Beyond Words: A Multimodal and Multilingual Exploration of Persuasion in Memes” has been accepted by SemEval@NAACL2024.
  • 2024.03: Our paper entitled “uTeBC-NLP at SemEval-2024 Task 9: Can LLMs be Lateral Thinkers?” has been accepted by SemEval@NAACL2024.
  • 2024.02: Our paper titled “Benchmarking Large Language Models for Persian: A Preliminary Study Focusing on ChatGPT” has been accepted for presentation at LREC-CoLing 2024.
  • 2023.09: I started my Master’s Degree at UBC’s CS Department 🥳🥳.
  • 2023.05: Out paper with the title “LM-CPPF: Paraphrasing-Guided Data Augmentation for Contrastive Prompt-Based Few-Shot Fine-Tuning” has been accepted for ACL 2023.
  • 2023.03: Our paper with the title “PEACH: Pre-Training Sequence-to-Sequence Multilingual Models for Translation with Semi-Supervised Pseudo-Parallel Document Generation” has been accepted for LoResMT@EACL 2023.
  • 2023.02: I completed my B.Sc. from the University of Tehran’s ECE department.
  • 2022.09: My project with title “Presenting A Multilingual Sequence-to-Sequence Language Model For Machine Translation Using Supervised Parallel Document Generation” has been awarded as the best undergraduate project.
  • 2022.03: Our paper entitled “UTNLP at SemEval-2022 Task 6: A Comparative Analysis of Sarcasm Detection Using Generative-based and Mutation-based Data Augmentation” has been accepted by SemEval@NAACL2022.
  • 2021.09: I have been accepted for 1-year internship under supervision of Prof. Pedram Rooshenas.
  • 2021.07: I have been accepted for summer internship at World Data Science Institute.
  • 2020.11: I have been selected as a Iran’s Elites Foundation member.
  • 2019.09: I was awarded the Scholarship 2018-2019 by the University of Tehran.
  • 2018.09: Started my B.Sc. at the University of Tehran.

Misc

  • I have always been fascinated by languages, which led me to explore natural language processing. Combining linguistics, computer science, and AI, NLP allows me to study how computers understand and generate human language—a field that inspires my academic journey.

  • In my free time, I enjoy cooking, even though I’m not an expert. I love trying out different dishes, from Persian foods to classics like lasagna, and experimenting with flavors to create something delicious.

  • In addition to my academic and professional interests, I’m a big fan of gaming—especially story-driven games that immerse you in captivating narratives. I have a particular love for those in the survival-horror genre, where the thrill and puzzles keep me hooked. If you’re a gamer too, feel free to check out my Steam profile!