Zobrazeno 1 - 10
of 37
pro vyhledávání: '"Akbik, Alan"'
Intermediate task transfer learning can greatly improve model performance. If, for example, one has little training data for emotion detection, first fine-tuning a language model on a sentiment classification dataset may improve performance strongly.
Externí odkaz:
http://arxiv.org/abs/2410.15148
Classification tasks in NLP are typically addressed by selecting a pre-trained language model (PLM) from a model hub, and fine-tuning it for the task at hand. However, given the very large number of PLMs that are currently available, a practical chal
Externí odkaz:
http://arxiv.org/abs/2409.05997
Knowledge probing evaluates the extent to which a language model (LM) has acquired relational knowledge during its pre-training phase. It provides a cost-effective means of comparing LMs of different sizes and training setups and is useful for monito
Externí odkaz:
http://arxiv.org/abs/2408.15729
Available training data for named entity recognition (NER) often contains a significant percentage of incorrect labels for entity types and entity boundaries. Such label noise poses challenges for supervised learning and may significantly deteriorate
Externí odkaz:
http://arxiv.org/abs/2405.07609
Recent advancements in large language models (LLMs) have showcased their exceptional abilities across various tasks, such as code generation, problem-solving and reasoning. Existing benchmarks evaluate tasks in isolation, yet the extent to which LLMs
Externí odkaz:
http://arxiv.org/abs/2404.18766
Knowledge probing assesses to which degree a language model (LM) has successfully learned relational knowledge during pre-training. Probing is an inexpensive way to compare LMs of different sizes and training configurations. However, previous approac
Externí odkaz:
http://arxiv.org/abs/2404.04113
This paper introduces Fundus, a user-friendly news scraper that enables users to obtain millions of high-quality news articles with just a few lines of code. Unlike existing news scrapers, we use manually crafted, bespoke content extractors that are
Externí odkaz:
http://arxiv.org/abs/2403.15279
Few-shot named entity recognition (NER) detects named entities within text using only a few annotated examples. One promising line of research is to leverage natural language descriptions of each entity type: the common label PER might, for example,
Externí odkaz:
http://arxiv.org/abs/2403.14222
Autor:
Sänger, Mario, Garda, Samuele, Wang, Xing David, Weber-Genzel, Leon, Droop, Pia, Fuchs, Benedikt, Akbik, Alan, Leser, Ulf
Publikováno v:
Bioinformatics, Volume 40, Number 10, 2024, btae564, Oxford University Press
With the exponential growth of the life science literature, biomedical text mining (BTM) has become an essential technology for accelerating the extraction of insights from publications. Identifying named entities (e.g., diseases, drugs, or genes) in
Externí odkaz:
http://arxiv.org/abs/2402.12372
Autor:
Aynetdinov, Ansar, Akbik, Alan
Instruction-tuned Large Language Models (LLMs) have recently showcased remarkable advancements in their ability to generate fitting responses to natural language instructions. However, many current works rely on manual evaluation to judge the quality
Externí odkaz:
http://arxiv.org/abs/2401.17072