cLegal-QA: a Chinese legal question answering with natural language generation methods by Yizhen Wang, Xueying Shen, Zixian Huang, Lihui Niu, Shiyan Ou

Subjects: Get full text

A Discourse Coherence Analysis Method Combining Sentence Embedding and Dimension Grid by Lanlan Jiang, Shengjun Yuan, Jun Li

“…Discourse coherence is strongly associated with text quality, making it important to natural language generation and understanding. However, existing coherence models focus on measuring individual aspects of coherence, such as lexical overlap, entity centralization, rhetorical structure, etc., lacking measurement of the semantics of text. …”
Get full text

Barriers and enabling factors for error analysis in NLG research by Emiel van Miltenburg, Miruna Clinciu, Ondřej Dušek, Dimitra Gkatzia, Stephanie Inglis, Leo Leppänen, Saad Mahamood, Stephanie Schoch, Craig Thomson, Luou Wen

“… Earlier research has shown that few studies in Natural Language Generation (NLG) evaluate their system outputs using an error analysis, despite known limitations of automatic evaluation metrics and human ratings. …”
Get full text

Unsupervised Text Embedding Space Generation Using Generative Adversarial Networks for Text Synthesis by Jun-Min Lee, Tae-Bin Ha

“…Although GAN application to image synthesis is extensively studied, it has inherent limitations to natural language generation. Because natural language is composed of discrete tokens, a generator has difficulty updating its gradient through backpropagation; therefore, most text-GAN studies generate sentences starting with a random token based on a reward system. …”
Get full text

Frozen Weights as Prior for Parameter-Efficient Fine-Tuning by Xiaolong Ma, Peishun Liu, Haojie Gao, Zikang Yan, Ningning Ma, Wenqiang Liu, Xuefang Wang, Ruichun Tang

“…We have conducted extensive experiments on various tasks, including natural language processing, question answering, natural language generation, and visual classification, demonstrating the effectiveness of FoWA.…”
Get full text