@inproceedings{xiong2019open,
author = {Xiong, Lee and Hu, Chuan and Xiong, Chenyan and Campos, Daniel and Overwijk, Arnold},
title = {Open Domain Web Keyphrase Extraction Beyond Language Modeling},
organization = {ACL},
booktitle = {Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)},
year = {2019},
month = {November},
abstract = {This paper studies keyphrase extraction in real-world scenarios where documents are from diverse domains and have variant content quality. We curate and release OpenKP, a large scale open domain keyphrase extraction dataset with near one hundred thousand web documents and expert keyphrase annotations. To handle the variations of domain and content quality, we develop BLING-KPE, a neural keyphrase extraction model that goes beyond language understanding using visual presentations of documents and weak supervision from search queries. Experimental results on OpenKP confirm the effectiveness of BLING-KPE and the contributions of its neural architecture, visual features, and search log weak supervision. Zero-shot evaluations on DUC-2001 demonstrate the improved generalization ability of learning from the open domain data compared to a specific domain.},
publisher = {ACL},
url = {http://approjects.co.za/?big=en-us/research/publication/open-domain-web-keyphrase-extraction-beyond-language-modeling/},
pages = {5174-5183},
}