Zobrazeno 1 - 10
of 139
pro vyhledávání: '"Cao, YunBo"'
A customer service platform system with a core text semantic similarity (STS) task faces two urgent challenges: Firstly, one platform system needs to adapt to different domains of customers, i.e., different domains adaptation (DDA). Secondly, it is d
Externí odkaz:
http://arxiv.org/abs/2311.12310
Autor:
Wang, Peiyi, Li, Lei, Chen, Liang, Song, Feifan, Lin, Binghuai, Cao, Yunbo, Liu, Tianyu, Sui, Zhifang
Reasoning is a cognitive process of using evidence to reach a sound conclusion. The reasoning capability is essential for large language models (LLMs) to serve as the brain of the artificial general intelligence agent. Recent studies reveal that fine
Externí odkaz:
http://arxiv.org/abs/2309.02144
Few-shot sequence labeling aims to identify novel classes based on only a few labeled samples. Existing methods solve the data scarcity problem mainly by designing token-level or span-level labeling models based on metric learning. However, these met
Externí odkaz:
http://arxiv.org/abs/2307.07946
Autor:
Feng, Zhangyin, Dai, Yong, Zhang, Fan, Tang, Duyu, Feng, Xiaocheng, Wu, Shuangzhi, Qin, Bing, Cao, Yunbo, Shi, Shuming
Traditional multitask learning methods basically can only exploit common knowledge in task- or language-wise, which lose either cross-language or cross-task knowledge. This paper proposes a general multilingual multitask model, named SkillNet-X, whic
Externí odkaz:
http://arxiv.org/abs/2306.16176
Autor:
Zeng, Jiali, Jiang, Yufan, Yin, Yongjing, Jing, Yi, Meng, Fandong, Lin, Binghuai, Cao, Yunbo, Zhou, Jie
Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from source languages or when pre-training data i
Externí odkaz:
http://arxiv.org/abs/2306.07610
Autor:
Wang, Peiyi, Li, Lei, Chen, Liang, Cai, Zefan, Zhu, Dawei, Lin, Binghuai, Cao, Yunbo, Liu, Qi, Liu, Tianyu, Sui, Zhifang
In this paper, we uncover a systematic bias in the evaluation paradigm of adopting large language models~(LLMs), e.g., GPT-4, as a referee to score and compare the quality of responses generated by candidate models. We find that the quality ranking o
Externí odkaz:
http://arxiv.org/abs/2305.17926
Autor:
Tong, Shoujie, Xia, Heming, Dai, Damai, Xu, Runxin, Liu, Tianyu, Lin, Binghuai, Cao, Yunbo, Sui, Zhifang
Pretrained language models have achieved remarkable success in natural language understanding. However, fine-tuning pretrained models on limited training data tends to overfit and thus diminish performance. This paper presents Bi-Drop, a fine-tuning
Externí odkaz:
http://arxiv.org/abs/2305.14760
Autor:
Cai, Zefan, Zheng, Xin, Liu, Tianyu, Wang, Xu, Meng, Haoran, Han, Jiaqi, Yuan, Gang, Lin, Binghuai, Chang, Baobao, Cao, Yunbo
In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates. Within the newly added
Externí odkaz:
http://arxiv.org/abs/2305.14751
Video multimodal fusion aims to integrate multimodal signals in videos, such as visual, audio and text, to make a complementary prediction with multiple modalities contents. However, unlike other image-text multimodal tasks, video has longer multimod
Externí odkaz:
http://arxiv.org/abs/2305.14652
Autor:
Chai, Linzheng, Xiao, Dongling, Yang, Jian, Yang, Liqun, Zhang, Qian-Wen, Cao, Yunbo, Li, Zhoujun, Yan, Zhao
Context-dependent Text-to-SQL aims to translate multi-turn natural language questions into SQL queries. Despite various methods have exploited context-dependence information implicitly for contextual SQL parsing, there are few attempts to explicitly
Externí odkaz:
http://arxiv.org/abs/2305.06655