Author name cluster

Yawei Sun

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

EAAI Journal 2024 Journal Article

Autoregressive data generation method based on wavelet packet transform and cascaded stochastic quantization for bearing fault diagnosis under unbalanced samples

Yawei Sun
Hongfeng Tao
Vladimir Stojanovic

The capacity to diagnose faults in rolling bearings is of significant practical importance to ensure the normal operation of the equipment. However, because it is challenging to obtain a sufficient number of labeled fault samples in practical engineering applications, the collected datasets will be unbalanced, which will greatly affect the performance of diagnosis. To tackle the above mentioned challenges, an autoregressive data generation method based on wavelet packet transform and cascaded stochastic quantization for fault diagnosis under unbalanced samples is proposed in this paper. Firstly, we propose a cascaded autoregressive data generation model. The hierarchical structure can better learn the multi-scale deep features of the input signal. Secondly, to increase the diversity of pseudo samples, we use wavelet packet decomposition to obtain high and low frequency information, which is used as the training data for the generative model, then reconstruct the generated high and low frequency information to obtain pseudo samples. Finally, a parallel attention-guided quantization mechanism and a multi-scale quantization feature fusion module are proposed to better integrate latent variable features of different scales. The experimental results validate the effectiveness of the proposed method, and demonstrate its significant application potential in fault diagnosis under unbalanced samples.

Details DOI

AAAI Conference 2021 Conference Paper

TSQA: Tabular Scenario Based Question Answering

Xiao Li
Yawei Sun
Gong Cheng

Scenario-based question answering (SQA) has attracted an increasing research interest. Compared with the well-studied machine reading comprehension (MRC), SQA is a more challenging task: a scenario may contain not only a textual passage to read but also structured data like tables, i. e. , tabular scenario based question answering (TSQA). AI applications of TSQA such as answering multiple-choice questions in high-school exams require synthesizing data in multiple cells and combining tables with texts and domain knowledge to infer answers. To support the study of this task, we construct GeoTSQA. This dataset contains 1k real questions contextualized by tabular scenarios in the geography domain. To solve the task, we extend state-of-the-art MRC methods with TTGen, a novel table-to-text generator. It generates sentences from variously synthesized tabular data and feeds the downstream MRC method with the most useful sentences. Its sentence ranking model fuses the information in the scenario, question, and domain knowledge. Our approach outperforms a variety of strong baseline methods on GeoTSQA.

PDF Details

AAAI Conference 2020 Conference Paper

Learning to Select Bi-Aspect Information for Document-Scale Text Content Manipulation

Xiaocheng Feng
Yawei Sun
Bing Qin
Heng Gong
Yibo Sun
Wei Bi
Xiaojiang Liu
Ting Liu

In this paper, we focus on a new practical task, documentscale text content manipulation, which is the opposite of text style transfer and aims to preserve text styles while altering the content. In detail, the input is a set of structured records and a reference text for describing another recordset. The output is a summary that accurately describes the partial content in the source recordset with the same writing style of the reference. The task is unsupervised due to lack of parallel data, and is challenging to select suitable records and style words from bi-aspect inputs respectively and generate a high-ﬁdelity long document. To tackle those problems, we ﬁrst build a dataset based on a basketball game report corpus as our testbed, and present an unsupervised neural model with interactive attention mechanism, which is used for learning the semantic relationship between records and reference texts to achieve better content transfer and better style preservation. In addition, we also explore the effectiveness of the back-translation in our task for constructing some pseudotraining pairs. Empirical results show superiority of our approaches over competitive methods, and the models also yield a new state-of-the-art result on a sentence-level dataset. 1

PDF Details

AAAI Conference 2020 Conference Paper

SPARQA: Skeleton-Based Semantic Parsing for Complex Questions over Knowledge Bases

Yawei Sun
Lingling Zhang
Gong Cheng
Yuzhong Qu

Semantic parsing transforms a natural language question into a formal query over a knowledge base. Many existing methods rely on syntactic parsing like dependencies. However, the accuracy of producing such expressive formalisms is not satisfying on long complex questions. In this paper, we propose a novel skeleton grammar to represent the high-level structure of a complex question. This dedicated coarse-grained formalism with a BERT-based parsing algorithm helps to improve the accuracy of the downstream ﬁne-grained semantic parsing. Besides, to align the structure of a question with the structure of a knowledge base, our multi-strategy method combines sentence-level and word-level semantics. Our approach shows promising performance on several datasets.

PDF Details