Scholar
Philipp Borchert
Google Scholar ID: efKKfygAAAAJ
Researcher, Huawei
Citations & Impact
Citations
135
H-index
6
i10-index
4
Publications
12
Co-authors
11
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Language Fusion for Parameter-Efficient Cross-lingual Transfer: Introduces FLARE, a novel method that merges source and target language representations within low-rank adapters, enhancing cross-lingual transfer performance while maintaining parameter efficiency.
- Self-Distillation for Model Stacking Unlocks Cross-Lingual NLU in 200+ Languages: Presents MT-LLM, a method integrating machine translation (MT) encoders into LLM backbones using self-distillation, unlocking natural language understanding capabilities for over 127 languages.
- Efficient Information Extraction in Few-Shot Relation Classification through Contrastive Representation Learning: Proposes MultiRep, an approach to improve few-shot relation classification by combining multiple sentence representations using contrastive learning.
- CORE: A Few-Shot Company Relation Classification Dataset for Robust Domain Adaptation: Publishes CORE, a dataset for few-shot relation classification focused on company relations, designed to challenge models with the contextual complexity of business entities.
- Investigating Bias in Multilingual Language Models: Cross-Lingual Transfer of Debiasing Techniques: Investigates whether debiasing techniques can be effectively transferred across different languages within multilingual LLMs, finding that SentenceDebias technique reduces bias by an average of 13%.
- SEER: A Knapsack approach to Exemplar Selection for In-Context HybridQA: Introduces SEER, a method for selecting diverse and representative examples for in-context learning in complex question-answering tasks, outperforming previous methods.
Research Experience
- Working on AI for Math reasoning at Huawei in London; previous research involved multilingual NLP and information extraction.
Education
- Completed his PhD at KU Leuven, where his research focused on multilinguality and NLP for Business applications.
Background
- NLP researcher fascinated by how we can teach LLMs to reason and tackle complex, structured problems. His research spans from multilingual NLP over information extraction to his current work on reasoning in AI for Math at Huawei in London.
Miscellany
- Personal interests not mentioned
