Towards Building a Knowledge Base of Monetary Transactions from a News Collection
This work addresses the challenge of building a financial knowledge base from noisy news data, which is incremental as it improves upon existing extraction techniques.
The paper tackled the problem of extracting structured economic events from news articles by developing a supervised learning method that jointly extracts and stores event attributes as quintuples, achieving a 25% improvement in F1-score over baseline methods.
We address the problem of extracting structured representations of economic events from a large corpus of news articles, using a combination of natural language processing and machine learning techniques. The developed techniques allow for semi-automatic population of a financial knowledge base, which, in turn, may be used to support a range of data mining and exploration tasks. The key challenge we face in this domain is that the same event is often reported multiple times, with varying correctness of details. We address this challenge by first collecting all information pertinent to a given event from the entire corpus, then considering all possible representations of the event, and finally, using a supervised learning method, to rank these representations by the associated confidence scores. A main innovative element of our approach is that it jointly extracts and stores all attributes of the event as a single representation (quintuple). Using a purpose-built test set we demonstrate that our supervised learning approach can achieve 25% improvement in F1-score over baseline methods that consider the earliest, the latest or the most frequent reporting of the event.