ABSTRACT
Motivated by the significant role of numeric values to convey concise and accurate information in news headlines, we focus the headline generation task on displaying correct numbers. We propose various ways to present the numeric values to the generative model. In the end, we come up with a simple but effective pre-train task to guide the generator to correctly process the values, which outperforms other base models even if the numbers in the headline are newly generated from the article.
- Chung-Chi Chen, Hen-Hsen Huang, Hiroya Takamura, and Hsin-Hsi Chen. 2019. Numeracy-600K: Learning Numeracy for Detecting Exaggerated Information in Market Comments. In ACL.Google Scholar
- Soichiro Murakami, Akihiko Watanabe, Akira Miyazawa, Keiichi Goshima, Toshihiko Yanase, Hiroya Takamura, and Yusuke Miyao. 2017. Learning to Generate Market Comments from Stock Prices. In ACL.Google Scholar
- Eric Wallace, Yizhong Wang, Sujian Li, Sameer Singh, and Matt Gardner. 2019. Do NLP Models Know Numbers? Probing Numeracy in Embeddings. In Proceedings of the 2019 Conference on EMNLP-IJCNLP.Google ScholarCross Ref
Index Terms
- Learning to Generate Correct Numeric Values in News Headlines
Recommendations
An extract-then-abstract based method to generate disaster-news headlines using a DNN extractor followed by a transformer abstractor
AbstractGenerating news headlines has been one of the predominant problems in Natural Language Processing research. Modern transformer models, if fine-tuned, can present a good headline with attention to all the parts of a disaster-news ...
Highlights- Proposed an extract-then-abstract based disaster-news headline generation approach.
SHEG: summarization and headline generation of news articles using deep learning
AbstractThe human attention span is continuously decreasing, and the amount of time a person wants to spend on reading is declining at an alarming rate. Therefore, it is imperative to provide a quick glance of important news by generating a concise ...
ElmNet: a benchmark dataset for generating headlines from Persian papers
AbstractHeadline generation is a challenging subtask of abstractive text summarization, which its output should be a summary, shorter than one sentence. It would be precious to develop a dataset for the evaluation of abstractive summarization methods on ...
Comments