1 code implementation • 12 May 2023 • Xiaolei Lu, Jianghong Ma, Haode Zhang
In this work, we propose an asymmetric feature interaction attribution explanation model that aims to explore asymmetric higher-order feature interactions in the inference of deep neural NLP models.
no code implementations • 4 Jan 2023 • Xiaolei Lu
Most crowdsourcing learning methods treat disagreement between annotators as noisy labelings while inter-disagreement among experts is often a good indicator for the ambiguity and uncertainty that is inherent in natural language.
no code implementations • 20 Sep 2022 • Xiaolei Lu, Tommy W. S. Chow
To accelerate the marginalization of the proposed model, a valid label sequence inference (VLSE) method is proposed to derive the valid ground-truth label sequences from crowd sequential annotations.
no code implementations • 20 Sep 2022 • Xiaolei Lu, Tommy W. S. Chow
Existing disambiguation strategies for partial structured output learning just cannot generalize well to solve the problem that there are some candidates which can be false positive or similar to the ground-truth label.
no code implementations • 20 Sep 2022 • Xiaolei Lu, Tommy W. S. Chow
Then confidence measure is introduced in the model to address different contributions of candidate labels, which enables the ground-truth label information to be utilized in parameter learning.
no code implementations • 19 Sep 2022 • Xiaolei Lu, Tommy W. S. Chow
Existing methods for keyphrase extraction need preprocessing to generate candidate phrase or post-processing to transform keyword into keyphrase.
1 code implementation • NAACL 2022 • Haode Zhang, Haowen Liang, Yuwei Zhang, LiMing Zhan, Xiao-Ming Wu, Xiaolei Lu, Albert Y. S. Lam
It is challenging to train a good intent classifier for a task-oriented dialogue system with only a few annotations.
no code implementations • 3 Nov 2019 • Xiaolei Lu, Bin Ni
The automatic classification is a process of automatically assigning text documents to predefined categories.
no code implementations • 3 Nov 2019 • Xiaolei Lu, Bin Ni
This article focuses on the study of Word Embedding, a feature-learning technique in Natural Language Processing that maps words or phrases to low-dimensional vectors.