我们提出了 CogBERT,一个能够有效地将认知信号纳入预训练模型的框架。实验结果表明,CogBERT 在多个 NLP 基准数据集上取得了超越基线的结果,同时模型表明证明对认知任务同样有用。分析表明,CogBERT 可以自适应地学习特定任务的认知特征权重,从而对认知数据在 NLP 任务中的工作方式做出精细的解释。这项工作为学习认知增强的预训练模型提供了一个新的方法,广泛阐述的实验可以指导未来的研究。 参考文献 [1] H.S. Scarborough, F. Fletcher-Campbell, Janet Soler, and G. Reid. 2009. Connecting early language and literacy to later reading (dis)abilities: Evidence, theory, and practice. Approaching difficulties in literacy development: assessment, pedagogy, and programmes.[2] Matthew Honnibal and Ines Montani. 2017. spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing. [3] Hochreiter, Sepp & Schmidhuber, Jürgen. (1997). Long Short-term Memory. Neural computation. 9. 1735-80. 10.1162/neco.1997.9.8.1735.[4] Nora Hollenstein, Jonathan Rotsztejn, Marius Troen-dle, Andreas Pedroni, Ce Zhang, and Nicolas Langer. 2018. Zuco, a simultaneous eeg and eye-tracking re- source for natural sentence reading. Scientific Data, 5:180291.[5] Nora Hollenstein, Marius Troendle, Ce Zhang, and Nicolas Langer. 2020. Zuco 2.0: A dataset of physiological recordings during natural reading and annotation.[6] Uschi Cop, Nicolas Dirix, Denis Drieghe, and Wouter Duyck. 2016. Presenting geco: An eyetracking corpus of monolingual and bilingual sentence reading. Behavior Research Methods, 49.[7] Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In the Proceedings of ICLR.[8] Erik Sang and Sabine Buchholz. 2000. Introduction to the conll-2000 shared task: Chunking. Proc of CoNLL-2000 and LLL-2000.[9] Nora Hollenstein, Federico Pirovano, Ce Zhang, Lena Jäger, and Lisa Beinborn. 2021. Multilingual language models predict human reading behavior.[10] Ian Tenney, Dipanjan Das, and Ellie Pavlick. 2019.BERT rediscovers the classical NLP pipeline. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4593–4601, Florence, Italy. Association for Computational Linguistics.