Search Results for author: Mingzhe Li

Found 16 papers, 6 papers with code

Unsupervised Mitigating Gender Bias by Character Components: A Case Study of Chinese Word Embedding

no code implementations NAACL (GeBNLP) 2022 Xiuying Chen, Mingzhe Li, Rui Yan, Xin Gao, Xiangliang Zhang

Word embeddings learned from massive text collections have demonstrated significant levels of discriminative biases. However, debias on the Chinese language, one of the most spoken languages, has been less explored. Meanwhile, existing literature relies on manually created supplementary data, which is time- and energy-consuming. In this work, we propose the first Chinese Gender-neutral word Embedding model (CGE) based on Word2vec, which learns gender-neutral word embeddings without any labeled data. Concretely, CGE utilizes and emphasizes the rich feminine and masculine information contained in radicals, i. e., a kind of component in Chinese characters, during the training procedure. This consequently alleviates discriminative gender biases. Experimental results on public benchmark datasets show that our unsupervised method outperforms the state-of-the-art supervised debiased word embedding models without sacrificing the functionality of the embedding model.

Word Embeddings

Multi-Intent Attribute-Aware Text Matching in Searching

no code implementations12 Feb 2024 Mingzhe Li, Xiuying Chen, Jing Xiang, Qishen Zhang, Changsheng Ma, Chenchen Dai, Jinxiong Chang, Zhongyi Liu, Guannan Zhang

Since attributes from two ends are often not aligned in terms of number and type, we propose to exploit the benefit of attributes by multiple-intent modeling.

Attribute Text Matching

Improving the Robustness of Summarization Systems with Dual Augmentation

1 code implementation1 Jun 2023 Xiuying Chen, Guodong Long, Chongyang Tao, Mingzhe Li, Xin Gao, Chengqi Zhang, Xiangliang Zhang

The other factor is in the latent space, where the attacked inputs bring more variations to the hidden states.

Data Augmentation

A Topic-aware Summarization Framework with Different Modal Side Information

no code implementations19 May 2023 Xiuying Chen, Mingzhe Li, Shen Gao, Xin Cheng, Qiang Yang, Qishen Zhang, Xin Gao, Xiangliang Zhang

To address these two challenges, we first propose a unified topic encoder, which jointly discovers latent topics from the document and various kinds of side information.

Contrastive Learning

Learning towards Selective Data Augmentation for Dialogue Generation

no code implementations17 Mar 2023 Xiuying Chen, Mingzhe Li, Jiayi Zhang, Xiaoqiang Xia, Chen Wei, Jianwei Cui, Xin Gao, Xiangliang Zhang, Rui Yan

As it is cumbersome and expensive to acquire a huge amount of data for training neural dialog models, data augmentation is proposed to effectively utilize existing training samples.

Data Augmentation Dialogue Generation +1

EZInterviewer: To Improve Job Interview Performance with Mock Interview Generator

no code implementations3 Jan 2023 Mingzhe Li, Xiuying Chen, Weiheng Liao, Yang song, Tao Zhang, Dongyan Zhao, Rui Yan

The key idea is to reduce the number of parameters that rely on interview dialogs by disentangling the knowledge selector and dialog generator so that most parameters can be trained with ungrounded dialogs as well as the resume data that are not low-resource.

Follow the Timeline! Generating Abstractive and Extractive Timeline Summary in Chronological Order

1 code implementation2 Jan 2023 Xiuying Chen, Mingzhe Li, Shen Gao, Zhangming Chan, Dongyan Zhao, Xin Gao, Xiangliang Zhang, Rui Yan

Nowadays, time-stamped web documents related to a general news query floods spread throughout the Internet, and timeline summarization targets concisely summarizing the evolution trajectory of events along the timeline.

Document Summarization Timeline Summarization +1

Scientific Paper Extractive Summarization Enhanced by Citation Graphs

no code implementations8 Dec 2022 Xiuying Chen, Mingzhe Li, Shen Gao, Rui Yan, Xin Gao, Xiangliang Zhang

We first propose a Multi-granularity Unsupervised Summarization model (MUS) as a simple and low-cost solution to the task.

Extractive Summarization Link Prediction +1

Towards Improving Faithfulness in Abstractive Summarization

1 code implementation4 Oct 2022 Xiuying Chen, Mingzhe Li, Xin Gao, Xiangliang Zhang

The evaluation of factual consistency also shows that our model generates more faithful summaries than baselines.

Abstractive Text Summarization Language Modelling +1

Target-aware Abstractive Related Work Generation with Contrastive Learning

1 code implementation26 May 2022 Xiuying Chen, Hind Alamro, Mingzhe Li, Shen Gao, Rui Yan, Xin Gao, Xiangliang Zhang

The related work section is an important component of a scientific paper, which highlights the contribution of the target paper in the context of the reference papers.

Contrastive Learning TAG

Capturing Relations between Scientific Papers: An Abstractive Model for Related Work Section Generation

1 code implementation ACL 2021 Xiuying Chen, Hind Alamro, Mingzhe Li, Shen Gao, Xiangliang Zhang, Dongyan Zhao, Rui Yan

Hence, in this paper, we propose a Relation-aware Related work Generator (RRG), which generates an abstractive related work from the given multiple scientific papers in the same research area.

Relation

Sketching Merge Trees for Scientific Data Visualization

no code implementations8 Jan 2021 Mingzhe Li, Sourabh Palande, Lin Yan, Bei Wang

That is, given a large set T of merge trees, we would like to find a much smaller basis set S such that each tree in T can be approximately reconstructed from a linear combination of merge trees in S. A set of high-dimensional vectors can be sketched via matrix sketching techniques such as principal component analysis and column subset selection.

Data Visualization

The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement

no code implementations14 Dec 2020 Mingzhe Li, Xiuying Chen, Min Yang, Shen Gao, Dongyan Zhao, Rui Yan

In this paper, we propose a Disentanglement-based Attractive Headline Generator (DAHG) that generates headline which captures the attractive content following the attractive style.

Disentanglement

VMSMO: Learning to Generate Multimodal Summary for Video-based News Articles

1 code implementation EMNLP 2020 Mingzhe Li, Xiuying Chen, Shen Gao, Zhangming Chan, Dongyan Zhao, Rui Yan

Hence, in this paper, we propose the task of Video-based Multimodal Summarization with Multimodal Output (VMSMO) to tackle such a problem.

Cannot find the paper you are looking for? You can Submit a new open access paper.