Zobrazeno 1 - 10
of 751
pro vyhledávání: '"Xu, Jialiang"'
Autor:
Liu, Shicheng, Semnani, Sina J., Triedman, Harold, Xu, Jialiang, Zhao, Isaac Dan, Lam, Monica S.
Recent work integrating Large Language Models (LLMs) has led to significant improvements in the Knowledge Base Question Answering (KBQA) task. However, we posit that existing KBQA datasets that either have simple questions, use synthetically generate
Externí odkaz:
http://arxiv.org/abs/2407.11417
Autor:
Zhang, Heidi C., Semnani, Sina J., Ghassemi, Farhad, Xu, Jialiang, Liu, Shicheng, Lam, Monica S.
We introduce SPAGHETTI: Semantic Parsing Augmented Generation for Hybrid English information from Text Tables and Infoboxes, a hybrid question-answering (QA) pipeline that utilizes information from heterogeneous knowledge sources, including knowledge
Externí odkaz:
http://arxiv.org/abs/2406.00562
Despite impressive advances in recent multimodal large language models (MLLMs), state-of-the-art models such as from the GPT-4 suite still struggle with knowledge-intensive tasks. To address this, we consider Reverse Image Retrieval (RIR) augmented g
Externí odkaz:
http://arxiv.org/abs/2405.18740
Autor:
Liu, Shicheng, Xu, Jialiang, Tjangnaka, Wesley, Semnani, Sina J., Yu, Chen Jie, Lam, Monica S.
While most conversational agents are grounded on either free-text or structured knowledge, many knowledge corpora consist of hybrid sources. This paper presents the first conversational agent that supports the full generality of hybrid data access fo
Externí odkaz:
http://arxiv.org/abs/2311.09818
Autor:
Han, Chi, Xu, Jialiang, Li, Manling, Fung, Yi, Sun, Chenkai, Jiang, Nan, Abdelzaher, Tarek, Ji, Heng
Language models (LMs) automatically learn word embeddings during pre-training on language corpora. Although word embeddings are usually interpreted as feature vectors for individual words, their roles in language model generation remain underexplored
Externí odkaz:
http://arxiv.org/abs/2305.12798
Transformers are widely used in NLP tasks. However, current approaches to leveraging transformers to understand language expose one weak spot: Number understanding. In some scenarios, numbers frequently occur, especially in semi-structured data like
Externí odkaz:
http://arxiv.org/abs/2212.02691
Numerical Question Answering is the task of answering questions that require numerical capabilities. Previous works introduce general adversarial attacks to Numerical Question Answering, while not systematically exploring numerical capabilities speci
Externí odkaz:
http://arxiv.org/abs/2211.07455
Autor:
Song, Ying1 (AUTHOR), Xu, Jialiang2 (AUTHOR), Geng, Wanru1 (AUTHOR), Yin, Long1 (AUTHOR), Wang, Jialu3 (AUTHOR) wangjl_cmu1h@126.com, Zhao, JiuHan3 (AUTHOR) cmu_zhaojh@126.com
Publikováno v:
Orphanet Journal of Rare Diseases. 8/23/2024, Vol. 19 Issue 1, p1-12. 12p.
Autor:
He, Xinyi, Zhou, Mengyu, Zhou, Mingjie, Xu, Jialiang, Lv, Xiao, Li, Tianle, Shao, Yijia, Han, Shi, Yuan, Zejian, Zhang, Dongmei
Tabular data analysis is performed every day across various domains. It requires an accurate understanding of field semantics to correctly operate on table fields and find common patterns in daily analysis. In this paper, we introduce the AnaMeta dat
Externí odkaz:
http://arxiv.org/abs/2209.00946
Autor:
Ye, Zijian1,2 (AUTHOR) 2022110004@stu.cqmu.edu.cn, Xu, Jialiang1,3 (AUTHOR) 2020221770@stu.cqmu.edu.cn, Zhang, Xin1 (AUTHOR) 2020220523@stu.cqmu.cn, Zhang, Yifan1,2 (AUTHOR) 2019221495@stu.cqmu.edu.cn, Ivanova, Deyana4 (AUTHOR) deyana.ivanova@yahoo.com, Lu, Weiyu1 (AUTHOR) 2020220512@stu.cqmu.edu.cn, Zhang, Jianning1,2 (AUTHOR), Li, Fangfang3 (AUTHOR) chenxuemei@cqmu.edu.cn, Chen, Xuemei3 (AUTHOR) yxwang@cqmu.edu.cn, Wang, Yingxiong3 (AUTHOR), Wang, Meijiao1,3 (AUTHOR) meijiaowang@cqmu.edu.cn, Xie, Biao2 (AUTHOR) meijiaowang@cqmu.edu.cn
Publikováno v:
International Journal of Molecular Sciences. Jun2024, Vol. 25 Issue 12, p6792. 28p.