2020/11/14 by Fan-Keng Sun, Sun, Fan-Keng, Cheng-I Lai +1 · 9 citations
Computer Science · #Computation and Language (cs.CL) #Computer science #FOS: Computer and information sciences #Geology #Machine Learning (cs.LG) #Natural (archaeology) #Natural Language Processing Techniques #Natural language #Natural language processing #Speech Recognition and Synthesis #Topic Modeling #cs.CL #cs.LG
paper · pdf · doi:10.48550/arxiv.2011.07347
published in arXiv (Cornell University) (Cornell University)
arxiv created 2020/11/14 · openalex publication_date 2020/11/14 · arxiv updated 2020/11/17 · openalex created_date 2020/11/23 · openalex updated_date 2026/07/28
Transformer-based language models have shown to be very powerful for natural language generation (NLG). However, text generation conditioned on some user inputs, such as topics or attributes, is non-trivial. Past approach relies on either modifying the original LM architecture, re-training the LM on corpora with attribute labels, or having separately trained `guidance models' to guide text generation in decoding. We argued that the above approaches are not necessary, and the original unconditioned LM is sufficient for conditioned NLG. We evaluated our approaches by the samples' fluency and diversity with automated and human evaluation.