Scholar
Amirhossein Abaskohi
Google Scholar ID: Xn--pmkAAAAJ
Computer Science PhD Student @ UBC
Citations & Impact
Citations
115
H-index
6
i10-index
5
Publications
18
Co-authors
26
list available
Publications
Resume (English only)
Academic Achievements
- - Three papers accepted to EMNLP 2025: CEMTM and ChartGaze (main proceedings), and FM²D
- - Master's thesis introduced 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
Research Experience
- - Visiting research scientist at ServiceNow Research since May 2024
- - Collaborated with researchers from leading research groups such as Google, Salesforce AI, and ServiceNow Research
- - Contributed to back-end development projects at System Group (Summer 2022) and MateMachine (November 2022 - November 2023)
Education
- - PhD student at the University of British Columbia (UBC), supervised by Prof. Giuseppe Carenini and Prof. Peter West
- - Master of Science in Computer Science from UBC, supervised by Prof. Giuseppe Carenini and Prof. Issam H. Laradji, thesis titled: 'Multimodal Understanding of Long Documents: From Topic Modeling to Question Answering'
- - Bachelor of Science in Computer Engineering from the University of Tehran, collaborated with Prof. Azadeh Shakeri, Prof. Yadollah Yaghoobzadeh, and Prof. Behnam Bahrak
Background
- Research interests span natural language processing, linguistics, and human-centered artificial intelligence. Specifically, fascinated by natural language inference and reasoning, long multimodal document reasoning, controlled generation, information retrieval, and deep research–related challenges.
Miscellany
- Enthusiastic about reading novels and comics; enjoys exploring the natural beauty of Vancouver, such as hiking in the forest, walking along the beach, or watching a colorful sunset
