Clifton Poth

Bio

I am currently a Machine Learning Engineer in the Search & Embeddings Team at Cohere. My work focuses on developing models for efficient retrieval and reranking of multilingual and multimodal data.
Previously, I studied at the Computer Science Department of TU Darmstadt with a focus on Machine Learning and NLP. I worked as a student research assistant in NLP at the UKP Lab of Prof. Iryna Gurevych, where I built and maintained the AdapterHub project and contributed to various research projects.

Projects

• Selected
• All

Cohere Embed v4
State-of-the-art multimodal embedding model for multilingual text and image retrieval

Cohere Rerank v3.5
Efficient multilingual reranking model with improved reasoning capabilities

Adapters Library
A unified library for parameter-efficient and modular transfer learning with Transformers

Cohere Embed v4
State-of-the-art multimodal embedding model for multilingual text and image retrieval

Cohere Rerank v3.5
Efficient multilingual reranking model with improved reasoning capabilities

Adapters Library
A unified library for parameter-efficient and modular transfer learning with Transformers

Publications

Complete and up-to-date list on Semantic Scholar.
^‡ indicates equal contribution.

• Selected
• All

M2QA: Multi-domain Multilingual Question Answering

Leon Engländer, Hannah Sterz, Clifton Poth, Jonas Pfeiffer, Ilia Kuznetsov, Iryna Gurevych

Findings of the Association for Computational Linguistics: EMNLP 2024

Paper Code

Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning

Clifton Poth^‡, Hannah Sterz^‡, Indraneil Paul, Sukannya Purkayastha, Leon Engländer, Timo Imhof, Ivan Vulić, Sebastian Ruder, Iryna Gurevych, Jonas Pfeiffer

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP 2023)

Paper Code

UKP-SQUARE: An Online Platform for Question Answering Research

Tim Baumgärtner, Kexin Wang, Rachneet Sachdeva, Max Eichler, Gregor Geigle, Clifton Poth, Hannah Sterz, Haritz Puerto, Leonardo F. R. Ribeiro, Jonas Pfeiffer, Nils Reimers, Gözde Gül Sahin, Iryna Gurevych

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations (ACL 2022)

Paper Code

What to Pre-Train on? Efficient Intermediate Task Selection

Clifton Poth, Jonas Pfeiffer, Andreas Rücklé, Iryna Gurevych

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)

Paper Video Code

AdapterHub: A Framework for Adapting Transformers

Jonas Pfeiffer^‡, Andreas Rücklé^‡, Clifton Poth^‡, Aishwarya Kamath, Ivan Vulić, Sebastian Ruder, Kyunghyun Cho, Iryna Gurevych

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP 2020)

Paper Code

M2QA: Multi-domain Multilingual Question Answering

Leon Engländer, Hannah Sterz, Clifton Poth, Jonas Pfeiffer, Ilia Kuznetsov, Iryna Gurevych

Findings of the Association for Computational Linguistics: EMNLP 2024

Paper Code

Adapters: A Unified Library for Parameter-Efficient and Modular Transfer Learning

Clifton Poth^‡, Hannah Sterz^‡, Indraneil Paul, Sukannya Purkayastha, Leon Engländer, Timo Imhof, Ivan Vulić, Sebastian Ruder, Iryna Gurevych, Jonas Pfeiffer

Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP 2023)

Paper Code

UKP-SQUARE: An Online Platform for Question Answering Research

Tim Baumgärtner, Kexin Wang, Rachneet Sachdeva, Max Eichler, Gregor Geigle, Clifton Poth, Hannah Sterz, Haritz Puerto, Leonardo F. R. Ribeiro, Jonas Pfeiffer, Nils Reimers, Gözde Gül Sahin, Iryna Gurevych

Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations (ACL 2022)

Paper Code

What to Pre-Train on? Efficient Intermediate Task Selection

Clifton Poth, Jonas Pfeiffer, Andreas Rücklé, Iryna Gurevych

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP 2021)

Paper Video Code

AdapterHub: A Framework for Adapting Transformers

Jonas Pfeiffer^‡, Andreas Rücklé^‡, Clifton Poth^‡, Aishwarya Kamath, Ivan Vulić, Sebastian Ruder, Kyunghyun Cho, Iryna Gurevych

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations (EMNLP 2020)

Paper Code

Vitæ

• Cohere Feb 2023 - now

  Machine Learning Engineer
  Modeling in the Search Team
• UKP Lab Apr 2020 - Jan 2023

  Student Research Assistant
  Adapters for Deep NLP, QA
• TU Darmstadt Apr 2021 - Apr 2023

  M.Sc. Student
  Computer Science; focus on Deep Learning & NLP
• TU Darmstadt Sep 2019 - Sep 2020

  Teaching Assistant
  Mathematics for CS; Algorithms
• Acando GmbH Jan 2019 - May 2019

  Trainee in IT consulting
  Machine Learning
• TU Darmstadt Oct 2017 - Apr 2021

  B.Sc. Student
  Computer Science

Acknowledgement