Financial Event Extraction Using Wikipedia-Based Weak Supervision

Proceedings of the Second Workshop on Economics and Natural Language Processing, pages 10–15 Hong Kong, November 4. c⃝2019 Association for Computational Linguistics 10 Financial Event Extraction Using Wikipedia-Based Weak Supervision Liat Ein-Dor, Ariel Gera, Orith Toledo-Ronen, Alon Halfon, Benjamin Sznajder, Lena Dankin, Yonatan Bilu, Yoav Katz and Noam Slonim IBM Research, Haifa, Israel Abstract Extraction of financial and economic events from text has previously been done mostly using rule-based methods, with more re- cent works employing machine learning tech- niques. This work is in line with this latter ap- proach, leveraging relevant Wikipedia sections to extract weak labels for sentences describing economic events. Whereas previous weakly supervised approaches required a knowledge- base of such events, or corresponding finan- cial figures, our approach requires no such ad- ditional data, and can be employed to extract economic events related to companies which are not even mentioned in the training data. 1 Introduction Event Extraction from text (Hogenboom et al., 2011; Ritter et al., 2012; Hogenboom et al., 2016) has been the subject of active research for over two decades (Allan et al., 2003). Detection and extrac- tion of finance-related events have mostly focused on events described in news articles, which are likely to impact stock prices. In particular, pre- vious work has sought to extract descriptions of events pertaining to a specific company, and ana- lyzed how such events correlate with measures of that company’s stock (price, volatility etc.). While much of the literature has focused on the predic- tion of stock prices (e.g., Ding et al., 2015; Xie et al., 2013), it is recognized that predicting future stock movements is a formidable challenge (see e.g. Merello et al., 2018); still, there are use-cases that might benefit from business-related event ex- traction from news. One promising direction is enhancing the finance-related research performed by finance an- alysts. Such research typically requires reviewing a large body of news data under severe time con- straints. We propose an automatic system for high- lighting meaningful company-related news events that are likely to deserve the analyst’s attention. Work on economic event extraction often de- fines an ad-hoc taxonomy of events, and what con- stitutes an ’important event’ for one might not be considered as such for another. For instance, the CoProE event ontology (Kakkonen and Mufti, 2011) includes events such as patent issuance and delayed filing of company reports, which are not considered by Du et al. (2016); similarly, while CoProE consider earnings estimates by analysts as events, Jacobs et al. (2018) examine instead ana- lyst buy ratings and recommendations. Outlining a comprehensive list of event types seems futile. For example, if a company’s databases are hacked, this is certainly an influen- tial event; but compiling an explicit and exhaustive event taxonomy that is sufficiently fine-grained to include all events such as this one is doomed to fail. At the same time, a formal event hierarchy is not necessarily required from an analyst’s perspec- tive. The strength of an automated system comes from the ability to …

Content truncated to 500 words