Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Mao, Xiaoxi"'
Autor:
Luo, Ziyang, Xi, Yadong, Ma, Jing, Yang, Zhiwei, Mao, Xiaoxi, Fan, Changjie, Zhang, Rongsheng
Since 2017, the Transformer-based models play critical roles in various downstream Natural Language Processing tasks. However, a common limitation of the attention mechanism utilized in Transformer Encoder is that it cannot automatically capture the
Externí odkaz:
http://arxiv.org/abs/2204.08688
Existing task-oriented chatbots heavily rely on spoken language understanding (SLU) systems to determine a user's utterance's intent and other key information for fulfilling specific tasks. In real-life applications, it is crucial to occasionally ind
Externí odkaz:
http://arxiv.org/abs/2201.06731
Autor:
Zhang, Rongsheng, Mao, Xiaoxi, Li, Le, Jiang, Lin, Chen, Lin, Hu, Zhiwei, Xi, Yadong, Fan, Changjie, Huang, Minlie
Recently, a variety of neural models have been proposed for lyrics generation. However, most previous work completes the generation process in a single pass with little human intervention. We believe that lyrics creation is a creative process with hu
Externí odkaz:
http://arxiv.org/abs/2201.06724
The wave of pre-training language models has been continuously improving the quality of the machine-generated conversations, however, some of the generated responses still suffer from excessive repetition, sometimes repeating words from utterance, so
Externí odkaz:
http://arxiv.org/abs/2112.08657
Unsupervised domain adaptation (UDA) with pre-trained language models (PrLM) has achieved promising results since these pre-trained models embed generic knowledge learned from various domains. However, fine-tuning all the parameters of the PrLM on a
Externí odkaz:
http://arxiv.org/abs/2111.00667
Grounded dialogue models generate responses that are grounded on certain concepts. Limited by the distribution of grounded dialogue data, models trained on such data face the transferability challenges in terms of the data distribution and the type o
Externí odkaz:
http://arxiv.org/abs/2109.07713
Standard multi-task benchmarks are essential for developing pretraining models that can generalize to various downstream tasks. Existing benchmarks for natural language processing (NLP) usually focus only on understanding or generating short texts. H
Externí odkaz:
http://arxiv.org/abs/2108.12960
Generating long and coherent text is an important but challenging task, particularly for open-ended language generation tasks such as story generation. Despite the success in modeling intra-sentence coherence, existing generation models (e.g., BART)
Externí odkaz:
http://arxiv.org/abs/2105.08963
Autor:
Guan, Jian, Zhang, Zhexin, Feng, Zhuoer, Liu, Zitao, Ding, Wenbiao, Mao, Xiaoxi, Fan, Changjie, Huang, Minlie
Automatic metrics are essential for developing natural language generation (NLG) models, particularly for open-ended language generation tasks such as story generation. However, existing automatic metrics are observed to correlate poorly with human e
Externí odkaz:
http://arxiv.org/abs/2105.08920
Autor:
Li, Gongzheng, Xi, Yadong, Ding, Jingzhen, Wang, Duan, Liu, Bai, Fan, Changjie, Mao, Xiaoxi, Zhao, Zeng
Recently, large-scale transformer-based models have been proven to be effective over various tasks across many domains. Nevertheless, applying them in industrial production requires tedious and heavy works to reduce inference costs. To fill such a ga
Externí odkaz:
http://arxiv.org/abs/2104.12470