Zobrazeno 1 - 10
of 24
pro vyhledávání: '"Mao Qianren"'
Knowledge graph reasoning plays a vital role in various applications and has garnered considerable attention. Recently, path-based methods have achieved impressive performance. However, they may face limitations stemming from constraints in message-p
Externí odkaz:
http://arxiv.org/abs/2409.12865
Autor:
Li, Qian, Ji, Cheng, Guo, Shu, Zhao, Yong, Mao, Qianren, Wang, Shangguang, Wei, Yuntao, Li, Jianxin
Multi-modal relation extraction (MMRE) is a challenging task that aims to identify relations between entities in text leveraging image information. Existing methods are limited by their neglect of the multiple entity pairs in one sentence sharing ver
Externí odkaz:
http://arxiv.org/abs/2404.12006
Autor:
Hu, Qi, Jiang, Weifeng, Li, Haoran, Wang, Zihao, Bai, Jiaxin, Mao, Qianren, Song, Yangqiu, Fan, Lixin, Li, Jianxin
The increasing demand for large-scale language models (LLMs) has highlighted the importance of efficient data retrieval mechanisms. Neural graph databases (NGDBs) have emerged as a promising approach to storing and querying graph-structured data in n
Externí odkaz:
http://arxiv.org/abs/2402.14609
Pre-trained sentence representations are crucial for identifying significant sentences in unsupervised document extractive summarization. However, the traditional two-step paradigm of pre-training and sentence-ranking, creates a gap due to differing
Externí odkaz:
http://arxiv.org/abs/2310.18992
We propose a neuralized undirected graphical model called Neural-Hidden-CRF to solve the weakly-supervised sequence labeling problem. Under the umbrella of probabilistic undirected graph theory, the proposed Neural-Hidden-CRF embedded with a hidden C
Externí odkaz:
http://arxiv.org/abs/2309.05086
Autor:
Jiang, Weifeng, Mao, Qianren, Lin, Chenghua, Li, Jianxin, Deng, Ting, Yang, Weiyi, Wang, Zheng
Many text mining models are constructed by fine-tuning a large deep pre-trained language model (PLM) in downstream tasks. However, a significant challenge nowadays is maintaining performance when we use a lightweight model with limited labelled sampl
Externí odkaz:
http://arxiv.org/abs/2305.12074
Publikováno v:
Knowledge-Based Systems 254 (2022): 109581
Hashtag generation aims to generate short and informal topical tags from a microblog post, in which tokens or phrases form the hashtags. These tokens or phrases may originate from primary fragmental textual pieces (e.g., segments) in the original tex
Externí odkaz:
http://arxiv.org/abs/2106.03151
Timeline summarization (TLS) involves creating summaries of long-running events using dated summaries from numerous news articles. However, limited data availability has significantly slowed down the development of timeline summarization. In this pap
Externí odkaz:
http://arxiv.org/abs/2105.14201
Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to time, financial, and expertise constraints, which has limited the usef
Externí odkaz:
http://arxiv.org/abs/2105.13635
Publikováno v:
In Knowledge-Based Systems 27 October 2022 254