Cause Information Extraction from Financial Articles Concerning Business Performance

Sakai, Hiroyuki; Masuyama, Shigeru

doi:10.1093/ietisy/e91-d.4.959

Cited by 17 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As training data, we manually extracted 2,920 articles concerning business performance from Nikkei newspapers published in 2000 and manually classified them into positive and negative ones. Causal expressions are extracted from Nikkei newspapers published from 1990 to 2005 (except 2000) by our previous method [1] and our method assigned polarity, "positive" or "negative", to them † † † . Note that parameter α used for determining the threshold value in Formula 2 was 0.3.…”

Section: Methodsmentioning

confidence: 99%

“…We proposed a method of extracting causal expressions from financial articles concerning business performance automatically [1]. In this section, we briefly introduce our previous method to help understand our method of assigning polarity.…”

Section: Extraction Of Causal Expressionsmentioning

confidence: 99%

“…Our previous method [1] acquires new clue expressions by using frequent expressions. First, our previous method extracts a bunsetu † modified by a phrase containing frequent expression e and acquires new clue expression s by adding a case particle contained in the phrase to the bunsetu.…”

Section: Acquisition Of New Clue Expressionsmentioning

confidence: 99%

“…Hence, we proposed a method of identifying articles concerning business performance of companies and extracting causal information (e.g. "zidousya no uriage ga koutyou: Sales of cars are good") from them automatically * * [1]. We defined a phrase implying causal information as a "causal expression".…”

Section: Introductionmentioning

confidence: 99%

“…In our previous method [1], we defined causal expressions to be extracted as expressions that contain some "frequent expressions" and a "clue expression". Then, we defined a frequent expression as a phrase frequently appearing in a set of causal expressions and a clue expression as a phrase frequently modified by causal expressions.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Assigning Polarity to Causal Information in Financial Articles on Business Performance of Companies

Sakai

Masuyama

2009

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYWe propose a method of assigning polarity to causal information extracted from Japanese financial articles concerning business performance of companies. Our method assigns polarity (positive or negative) to causal information in accordance with business performance, e.g. "zidousya no uriage ga koutyou: (Sales of cars are good)" (The polarity positive is assigned in this example). We may use causal expressions assigned polarity by our method, e.g., to analyze content of articles concerning business performance circumstantially. First, our method classifies articles concerning business performance into positive articles and negative articles. Using them, our method assigns polarity (positive or negative) to causal information extracted from the set of articles concerning business performance. Although our method needs training dataset for classifying articles concerning business performance into positive and negative ones, our method does not need a training dataset for assigning polarity to causal information. Hence, even if causal information not appearing in the training dataset for classifying articles concerning business performance into positive and negative ones exist, our method is able to assign it polarity by using statistical information of this classified sets of articles. We evaluated our method and confirmed that it attained 74.4% precision and 50.4% recall of assigning polarity positive, and 76.8% precision and 61.5% recall of assigning polarity negative, respectively.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Extraction Of Causal Expressionsmentioning

confidence: 99%

Section: Acquisition Of New Clue Expressionsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Assigning Polarity to Causal Information in Financial Articles on Business Performance of Companies

Sakai

Masuyama

2009

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

show abstract

Polarity Assignment to Causal Information Extracted from Financial Articles Concerning Business Performance of Companies

Sakai

Masuyama

2009

Research and Development in Intelligent Systems XXV

View full text Add to dashboard Cite

GFTE: Graph-Based Financial Table Extraction

Huang

Yan

et al. 2021

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Tabular data is a crucial form of information expression, which can organize data in a standard structure for easy information retrieval and comparison. However, in financial industry and many other fields tables are often disclosed in unstructured digital files, e.g. Portable Document Format (PDF) and images, which are difficult to be extracted directly. In this paper, to facilitate deep learning based table extraction from unstructured digital files, we publish a standard Chinese dataset named FinTab, which contains more than 1,600 financial tables of diverse kinds and their corresponding structure representation in JSON. In addition, we propose a novel graph-based convolutional neural network model named GFTE as a baseline for future comparison. GFTE integrates image feature, position feature and textual feature together for precise edge prediction and reaches overall good results 1 .

show abstract

Cause Information Extraction from Financial Articles Concerning Business Performance

Cited by 17 publications

References 9 publications

Assigning Polarity to Causal Information in Financial Articles on Business Performance of Companies

Assigning Polarity to Causal Information in Financial Articles on Business Performance of Companies

Polarity Assignment to Causal Information Extracted from Financial Articles Concerning Business Performance of Companies

GFTE: Graph-Based Financial Table Extraction

Contact Info

Product

Resources

About