基于ULMFiT迁移学习的孟加拉语文学作品作者归属（AABL）研究
Authorship Attribution in Bangla Literature (AABL) via Transfer Learning using ULMFiT
AI总结：
针对孟加拉语作者归属研究匮乏、现有系统可扩展性差且小样本性能下降的问题，本文提出基于AWD-LSTM和ULMFiT迁移学习的方法，构建了BAAD16数据集，取得99.8%的准确率，提升了系统可扩展性和小样本稳定性。
摘要：
作者归属是指构建恰当的文本特征表征，捕捉作者的写作风格，以识别给定文本的原作者的任务。随着互联网上匿名性的提升，该任务在各类安全和剽窃检测领域的重要性日益凸显。尽管英语、西班牙语和汉语等语言在该领域已取得显著进展，但孟加拉语由于其复杂的语言特征和句子结构，相关研究仍较为匮乏。此外，现有系统在作者数量增加时不具备可扩展性，且当每位作者的样本数量较少时，性能会出现下降。\n本文提出采用平均随机梯度下降权重丢弃长短期记忆（AWD-LSTM）架构及一种有效的迁移学习方法，解决孟加拉语文学作品作者归属（AABL）任务中的复杂语言特征提取与可扩展性问题。我们分析了词级、子词级和字符级等不同分词方式的效果，并验证了这些分词方式在所提模型中的有效性。此外，我们推出了公开可用的包含16位作者的孟加拉语作者归属数据集BAAD16，该数据集包含17966个文本样本、1340多万个单词，以解决标准数据集稀缺的问题，同时发布了6种变体的预训练语言模型，可用于任何孟加拉语自然语言处理下游任务。在评估环节，我们使用了自行构建的BAAD16数据集以及其他公开可用的数据集。实验结果表明，本文提出的模型性能优于现有最优模型，在BAAD16数据集上达到了99.8%的准确率。此外我们还证实，即使作者数量不断增加，所提系统的可扩展性仍表现更优，且即便训练样本较少，系统性能也能保持稳定。
英文摘要：
Authorship Attribution is the task of creating an appropriate characterization of text that captures the authors' writing style to identify the original author of a given piece of text. With increased anonymity on the internet, this task has become increasingly crucial in various security and plagiarism detection fields. Despite significant advancements in other languages such as English, Spanish, and Chinese, Bangla lacks comprehensive research in this field due to its complex linguistic feature and sentence structure. Moreover, existing systems are not scalable when the number of author increases, and the performance drops for small number of samples per author. In this paper, we propose the use of Average-Stochastic Gradient Descent Weight-Dropped Long Short-Term Memory (AWD-LSTM) architecture and an effective transfer learning approach that addresses the problem of complex linguistic features extraction and scalability for authorship attribution in Bangla Literature (AABL). We analyze the effect of different tokenization, such as word, sub-word, and character level tokenization, and demonstrate the effectiveness of these tokenizations in the proposed model. Moreover, we introduce the publicly available Bangla Authorship Attribution Dataset of 16 authors (BAAD16) containing 17,966 sample texts and 13.4+ million words to solve the standard dataset scarcity problem and release six variations of pre-trained language models for use in any Bangla NLP downstream task. For evaluation, we used our developed BAAD16 dataset as well as other publicly available datasets. Empirically, our proposed model outperformed state-of-the-art models and achieved 99.8% accuracy in the BAAD16 dataset. Furthermore, we showed that the proposed system scales much better even with an increasing number of authors, and performance remains steady despite few training samples.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
