ML Anthology

TA-DA: Topic-Aware Domain Adaptation for Scientific Keyphrase Identification and Classification (Student Abstract)

Razvan-Alexandru Smadu, George-Eduard Zaharia, Andrei-Marius Avram, Dumitru-Clementin Cercel, Mihai Dascalu, Florin Pop
AAAI 2023 pp. 16334-16335
doi:10.1609/AAAI.V37I13.27027 /aaai/2023/smadu2023aaai-ta/

Abstract

Keyphrase identification and classification is a Natural Language Processing and Information Retrieval task that involves extracting relevant groups of words from a given text related to the main topic. In this work, we focus on extracting keyphrases from scientific documents. We introduce TA-DA, a Topic-Aware Domain Adaptation framework for keyphrase extraction that integrates Multi-Task Learning with Adversarial Training and Domain Adaptation. Our approach improves performance over baseline models by up to 5% in the exact match of the F1-score.

PDF AAAI Semantic Scholar

Cite

Text

Smadu et al. "TA-DA: Topic-Aware Domain Adaptation for Scientific Keyphrase Identification and Classification (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.27027

Markdown

[Smadu et al. "TA-DA: Topic-Aware Domain Adaptation for Scientific Keyphrase Identification and Classification (Student Abstract)." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/smadu2023aaai-ta/) doi:10.1609/AAAI.V37I13.27027

BibTeX

@inproceedings{smadu2023aaai-ta,
  title     = {{TA-DA: Topic-Aware Domain Adaptation for Scientific Keyphrase Identification and Classification (Student Abstract)}},
  author    = {Smadu, Razvan-Alexandru and Zaharia, George-Eduard and Avram, Andrei-Marius and Cercel, Dumitru-Clementin and Dascalu, Mihai and Pop, Florin},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {16334-16335},
  doi       = {10.1609/AAAI.V37I13.27027},
  url       = {https://mlanthology.org/aaai/2023/smadu2023aaai-ta/}
}