Project Overview | Project Code: CIT 01 |
---|---|
Project name: | Parameter Efficient Knowledge Injection approaches for domain-specific Text Summarization |
TUM Department: | CIT - Electrical and Computer Engineering |
TUM Chair / Institute: | Chair of Software Engineering for Business Information Systems |
Research area: | Natural Language Processing |
Student background: | Computer ScienceComputer Science/ Informatics |
Further disciplines: | |
Participation also possible online only: | |
Planned project location: | Boltzmannstraße 385748 Garching bei München |
Project Description | |
---|---|
Project description: | Abstractive Text Summarization has been an active research area in the past years, and while state-of-the-art models can produce human competitive summaries, they are more suitable for general-purpose text. The performance of these models deteriorates when tested on a domain-specific text summarization task. One common explanation is the shift in the dataset distribution as most of the large language models (LLMs) are pre-trained on general-purpose corpora such as C4 (Raffel et al., 2020a), and hence do not fully comprehend the fine-grained linguistic details and concepts of a niche area such as the medical, scientific, or legal domain. |
Working hours per week planned: | 35 |
Prerequisites | |
---|---|
Required study level minimum (at time of TUM PREP project start): | 3 years of bachelor studies completed |
Subject related: | Machine Learning, Deep Learning, Natural Language Processing, Python Programming |
Other: |