no code implementations • 23 Feb 2024 • Junlong Liu, Xichen Shang, Huawen Feng, Junhao Zheng, Qianli Ma
However, due to the token bias in pretrained language models, the models can not capture the fine-grained semantics in sentences, which leads to poor predictions.
no code implementations • 15 Feb 2024 • Junhao Zheng, Ruiyan Wang, Chongzhi Zhang, Huawen Feng, Qianli Ma
In this way, the model is encouraged to adapt to all classes with causal effects from both new and old data and thus alleviates the causal imbalance problem.
Class Incremental Learning Continual Named Entity Recognition +6
no code implementations • 17 Jan 2024 • Junhao Zheng, Qianli Ma, Zhen Liu, Binquan Wu, Huawen Feng
The discrepancy results in the model learning irrelevant information for old and pre-trained tasks, which leads to catastrophic forgetting and negative forward transfer.
no code implementations • 30 Oct 2023 • Huawen Feng, Yan Fan, Xiong Liu, Ting-En Lin, Zekun Yao, Yuchuan Wu, Fei Huang, Yongbin Li, Qianli Ma
Despite the recent progress in text summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known as "hallucinations" in text generation.
1 code implementation • 19 Jun 2023 • Junhao Zheng, Qianli Ma, Shengjie Qiu, Yue Wu, Peitian Ma, Junlong Liu, Huawen Feng, Xichen Shang, Haibin Chen
Intriguingly, the unified objective can be seen as the sum of the vanilla fine-tuning objective, which learns new knowledge from target data, and the causal objective, which preserves old knowledge from PLMs.
no code implementations • 25 May 2023 • Huawen Feng, Zhenxi Lin, Qianli Ma
In text classification, the traditional attention mechanisms usually focus too much on frequent words, and need extensive labeled data in order to learn.