no code implementations • COLING 2022 • Xiuyu Wu, Jingsong Yu, Xu sun, Yunfang Wu
We introduce a novel position offset label prediction subtask to the encoder-decoder architecture for grammatical error correction (GEC) task.
1 code implementation • 24 May 2023 • Chenming Tang, Xiuyu Wu, Yunfang Wu
To this end, we explore several ensemble strategies based on strong PLMs with four sophisticated single models.
1 code implementation • 16 Jan 2023 • Rui Sun, Xiuyu Wu, Yunfang Wu
By borrowing the powerful ability of BERT, we propose a novel zero-shot error detection method to do a preliminary detection, which guides our model to attend more on the probably wrong tokens in encoding and to avoid modifying the correct tokens in generating.
no code implementations • 3 Nov 2022 • Xiuyu Wu, Yunfang Wu
To handle grammatical error correction, we design part-of-speech (POS) features and semantic class features to enhance the neural network model, and propose an auxiliary task to predict the POS sequence of the target sentence.
no code implementations • WS 2020 • Xiuyu Wu, Nan Jiang, Yunfang Wu
The answer-agnostic question generation is a significant and challenging task, which aims to automatically generate questions for a given sentence but without an answer.
no code implementations • WS 2019 • Da Yin, Xiao Liu, Xiuyu Wu, Baobao Chang
In this paper, we propose a soft label approach to target-level sentiment classification task, in which a history-based soft labeling model is proposed to measure the possibility of a context word as an opinion word.
no code implementations • 16 May 2019 • Xiuyu Wu, Yunfang Wu
How to generate human like response is one of the most challenging tasks for artificial intelligence.