Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP)最新文献_第2页

Toward Privacy-preserving Text Embedding Similarity with Homomorphic Encryption 基于同态加密的保护隐私文本嵌入相似度研究

Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.finnlp-1.4

Donggyu Kim, Garam Lee, Sungwoo Oh

{"title":"Toward Privacy-preserving Text Embedding Similarity with Homomorphic Encryption","authors":"Donggyu Kim, Garam Lee, Sungwoo Oh","doi":"10.18653/v1/2022.finnlp-1.4","DOIUrl":"https://doi.org/10.18653/v1/2022.finnlp-1.4","url":null,"abstract":"Text embedding is an essential component to build efficient natural language applications based on text similarities such as search engines and chatbots. Certain industries like finance and healthcare demand strict privacy-preserving conditions that user’s data should not be exposed to any potential malicious users even including service providers. From a privacy standpoint, text embeddings seem impossible to be interpreted but there is still a privacy risk that they can be recovered to original texts through inversion attacks. To satisfy such privacy requirements, in this paper, we study a Homomorphic Encryption (HE) based text similarity inference. To validate our method, we perform extensive experiments on two vital text similarity tasks. Through text embedding inversion tests, we prove that the benchmark datasets are vulnerable to inversion attacks and another privacy preserving approach, dχ-privacy, a relaxed version of Local Differential Privacy method fails to prevent them. We show that our approach preserves the performance of models compared to that the baseline has degradation up to 10% of scores for the minimum security.","PeriodicalId":331851,"journal":{"name":"Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130460450","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

UOA at the FinNLP-2022 ERAI Task: Leveraging the Class Label Description for Financial Opinion Mining FinNLP-2022 ERAI任务中的UOA:利用类标签描述进行财务意见挖掘

Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.finnlp-1.15

Jinan Zou, Hai Cao, Yanxi Liu, Lingqiao Liu, Ehsan Abbasnejad, Javen Qinfeng Shi

引用次数: 0

Stock Price Volatility Prediction: A Case Study with AutoML 股票价格波动预测:基于AutoML的案例研究

Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.finnlp-1.6

Hilal Pataci, Yunyao Li, Yannis Katsis, Yada Zhu, Lucian Popa

{"title":"Stock Price Volatility Prediction: A Case Study with AutoML","authors":"Hilal Pataci, Yunyao Li, Yannis Katsis, Yada Zhu, Lucian Popa","doi":"10.18653/v1/2022.finnlp-1.6","DOIUrl":"https://doi.org/10.18653/v1/2022.finnlp-1.6","url":null,"abstract":"Accurate prediction of the stock price volatility, the rate at which the price of a stock increases or decreases over a particular period, is an important problem in finance. Inaccurate prediction of stock price volatility might lead to investment risk and financial loss, while accurate prediction might generate significant returns for investors. Several studies investigated stock price volatility prediction in a regression task by using the transcripts of earning calls (quarterly conference calls held by public companies) with Natural Language Processing (NLP) techniques. Existing studies use the entire transcript and this degrades the performance due to noise caused by irrelevant information that might not have a significant impact on stock price volatility. In order to overcome these limitations, by considering stock price volatility prediction as a classification task, we explore several denoising approaches, ranging from general-purpose approaches to techniques specific to finance to remove the noise, and leverage AutoML systems that enable auto-exploration of a wide variety of models. Our preliminary findings indicate that domain-specific denoising approaches provide better results than general-purpose approaches, moreover AutoML systems provide promising results.","PeriodicalId":331851,"journal":{"name":"Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133686012","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Jetsons at the FinNLP-2022 ERAI Task: BERT-Chinese for mining high MPP posts 《杰森一家》在芬兰nlp -2022 ERAI任务:BERT-Chinese挖掘高MPP岗位

Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.finnlp-1.19

Alolika Gon, Sihan Zha, Sai Krishna Rallabandi, Parag Dakle, Preethi Raghavan

引用次数: 1

LDPP at the FinNLP-2022 ERAI Task: Determinantal Point Processes and Variational Auto-encoders for Identifying High-Quality Opinions from a pool of Social Media Posts 在FinNLP-2022 ERAI任务中的LDPP:从社交媒体帖子池中识别高质量意见的决定性点过程和变分自编码器

Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.finnlp-1.18

Paul Trust, R. Minghim

引用次数: 0

LIPI at the FinNLP-2022 ERAI Task: Ensembling Sentence Transformers for Assessing Maximum Possible Profit and Loss from Online Financial Posts LIPI在FinNLP-2022 ERAI任务:集成句子变形以评估在线金融帖子的最大可能利润和损失

Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.finnlp-1.13

Sohom Ghosh, S. Naskar

引用次数: 1

Overview of the FinNLP-2022 ERAI Task: Evaluating the Rationales of Amateur Investors FinNLP-2022 ERAI任务概述:评估业余投资者的基本原理

Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.finnlp-1.11

Chung-Chi Chen, Hen-Hsen Huang, Hiroya Takamura, Hsin-Hsi Chen

引用次数: 6

TweetFinSent: A Dataset of Stock Sentiments on Twitter TweetFinSent: Twitter上的股票情绪数据集

Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.finnlp-1.5

Yulong Pei, A. Mbakwe, Akshat Gupta, Salwa Alamir, Hanxuan Lin, Xiaomo Liu, Sameena Shah

引用次数: 3

No Stock is an Island: Learning Internal and Relational Attributes of Stocks with Contrastive Learning 没有股票是孤岛:用对比学习学习股票的内在属性和关系属性

Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.finnlp-1.20

Shicheng Li, Wei Li, Zhiyuan Zhang, Ruihan Bao, Keiko Harimoto

{"title":"No Stock is an Island: Learning Internal and Relational Attributes of Stocks with Contrastive Learning","authors":"Shicheng Li, Wei Li, Zhiyuan Zhang, Ruihan Bao, Keiko Harimoto","doi":"10.18653/v1/2022.finnlp-1.20","DOIUrl":"https://doi.org/10.18653/v1/2022.finnlp-1.20","url":null,"abstract":"Previous work has demonstrated the viability of applying deep learning techniques in the financial area. Recently, the task of stock embedding learning has been drawing attention from the research community, which aims to represent the characteristics of stocks with distributed vectors that can be used in various financial analysis scenarios. Existing approaches for learning stock embeddings either require expert knowledge, or mainly focus on the textual part of information corresponding to individual temporal movements. In this paper, we propose to model stock properties as the combination of internal attributes and relational attributes, which takes into consideration both the time-invariant properties of individual stocks and their movement patterns in relation to the market. To learn the two types of attributes from financial news and transaction data, we design several training objectives based on contrastive learning to extract and separate the long-term and temporary information in the data that are able to counter the inherent randomness of the stock market. Experiments and further analyses on portfolio optimization reveal the effectiveness of our method in extracting comprehensive stock information from various data sources.","PeriodicalId":331851,"journal":{"name":"Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128906665","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

How Can a Teacher Make Learning From Sparse Data Softer? Application to Business Relation Extraction 教师如何让从稀疏数据中学习变得更容易?在业务关系抽取中的应用

Proceedings of the Fourth Workshop on Financial Technology and Natural Language Processing (FinNLP) Pub Date : 1900-01-01 DOI: 10.18653/v1/2022.finnlp-1.23

Hadjer Khaldi, F. Benamara, Camille Pradel, Nathalie Aussenac-Gilles

引用次数: 0