Hello!
I'm Salim Salmi


an Amsterdam-based computer scientist, specializing in natural language processing and deep learning. I have a passion for creativity, whether it’s in my work, art, or cooking. With a strong background in innovative problem-solving, I love blending my technical skills with my creative hobbies to develop unique solutions.

Experience

Data Specialist 113 Suicide Prevention

At 113 I worked on researching and developing machine learning methods to facilitate suicide prevention research. For this purpose, I used machine learning models for audio transcription (Whisper) and language generation (Llama), to create an automated pipeline for interview transcription, labeling, summarization, and analysis.

2023 - Present

PhD Candidate at CWI

At CWI I worked on several natural language processing applications on suicide helpline chat data in cooperation with 113 Zelfmoordpreventie. I used shallow as well as deep learning methods to tackle this complex dataset for unsupervised and supervised tasks. I developed methods that provided information to the helpline at the macro level through explainable AI, as well as real-time tools to assist the helpline in their day-to-day tasks.

2019 - 2023

Software developer at Vialis

At Vialis I worked with the Vialis development team on a traffic management application. I assisted the team with implementing new features as well as resolving current issues. Furthermore, I developed an extendable end-to-end testing suite, including tests for several important use-cases within the environment.

2015 - 2016

Education

MSc Computer Science

Technical University Delft - The Netherlands

2016 - 2019

BSc Computer Science

Technical University Delft - The Netherlands

2010 - 2016

Publications

Salmi, S., Mérelle, S., Gilissen, R. & Brinkman, W.P. (2021) "Content-Based Recommender Support System for Counselors in a Suicide Prevention Chat Helpline: Design and Evaluation Study" Journal of medical internet research
Salmi, S., Mérelle, S., Gilissen, R., van der Mei, R., & Bhulai, S. (2022) "Detecting changes in help seeker conversations on a suicide prevention helpline during the COVID− 19 pandemic: in-depth analysis using encoder representations from transformers" BMC public health
Salmi, S., van der Mei, R., Mérelle, S., & Bhulai, S. (2024) "Topic modeling for conversations for mental health helplines with utterance embedding." Telematics and Informatics Reports
Pellemans, M., Salmi, S., Mérelle, S., Janssen, W., & van der Mei, R. (2024) "Automated Behavioral Coding to Enhance the Effectiveness of Motivational Interviewing in a Chat-Based Suicide Prevention Helpline: Secondary Analysis of a Clinical Trial" Journal of medical internet research
Salmi, S., Mérelle, S., Gilissen, R., van der Mei, R., & Bhulai, S. (2024) "The Most Effective Interventions for Classification Model Development to Predict Chat Outcomes Based on the Conversation Content in Online Suicide Prevention Chats: Machine Learning Approach JMIR Mental Health
Curriculum Vitea Dissertation