Proceedings of the Second Workshop on Economics and Natural Language Processing
Extracting Complex Relations from Banking Documents (D19-51)
Copied to clipboard
| Challenge: | Existing methods to extract complex relations from banking orders are limited . formal letters, petitions, demands or complaints are still a major communication medium in corporate banking. |
| Approach: | They propose a relation extraction method that extracts intersentential, nested and complex relations from banking orders. |
| Outcome: | The proposed method shows 11% error reduction over previous methods. |
Financial Event Extraction Using Wikipedia-Based Weak Supervision (D19-51)
Copied to clipboard
Liat Ein-Dor, Ariel Gera, Orith Toledo-Ronen, Alon Halfon, Benjamin Sznajder, Lena Dankin, Yonatan Bilu, Yoav Katz, Noam Slonim
| Challenge: | Existing methods for detecting financial and economic events from text have relied on a knowledge-base of financial events, or corresponding financial figures. |
| Approach: | They propose to use Wikipedia sections to extract weak labels for sentences describing economic events from text. |
| Outcome: | The proposed method can extract weak labels for sentences describing economic events from Wikipedia sentences. |
A Time Series Analysis of Emotional Loading in Central Bank Statements (D19-51)
Copied to clipboard
| Challenge: | a recent study has found that central bankers are communicating proactively to economic agents, resulting in a rapid growth of economic literature. |
| Approach: | They examine the affective content of central bank press statements using emotion analysis . they focus on the European Central Bank and the US Federal Reserve Bank . |
| Outcome: | The results show that the ECB and the Fed have strong emotional dimensions . the authors suggest that the use of emotion analysis could reveal latent emotions . |
Forecasting Firm Material Events from 8-K Reports (D19-51)
Copied to clipboard
| Challenge: | In this paper, we show deep learning models can be used to forecast firm material event sequences based on the contents of the company’s 8-K Current Reports. |
| Approach: | They exploit state-of-the-art neural architectures, including sequence-to-sequence architecture and attention mechanisms, to build a deep learning model that can forecast firm material event sequences based on company 8-K Current Reports. |
| Outcome: | The proposed model can forecast firm material event sequences based on the contents of the firm's 8-K Current Reports. |
Incorporating Fine-grained Events in Stock Movement Prediction (D19-51)
Copied to clipboard
| Challenge: | Existing studies mainly adopt coarse-grained events, which loses the specific semantic information of diverse event types. |
| Approach: | They propose to use a finance event dictionary to extract fine-grained events from finance news to train a neural model that uses the extracted events as the distant supervised label to train stock prediction. |
| Outcome: | The proposed method outperforms baselines and has good generalizability. |
Group, Extract and Aggregate: Summarizing a Large Amount of Finance News for Forex Movement Prediction (D19-51)
Copied to clipboard
| Challenge: | Existing studies on forex prediction ignore related text completely and focus on forex trade data only, which loses important semantic information. |
| Approach: | They propose a BERT-based Hierarchical Aggregation Model to summarize forex news . they group news from different aspects and extract the most crucial news in each group . |
| Outcome: | The proposed model outperforms baseline methods and grouping methods and summarizes the influence patterns for forex trading. |
Complaint Analysis and Classification for Economic and Food Safety (D19-51)
Copied to clipboard
João Filgueiras, Luís Barbosa, Gil Rocha, Henrique Lopes Cardoso, Luís Paulo Reis, João Pedro Machado, Ana Maria Oliveira
| Challenge: | Governmental institutions are using artificial intelligence to deal with specific problems and exploit their huge amounts of structured and unstructured information. |
| Approach: | They propose to use natural language processing and machine learning to classify complaints . they use feature-based approaches and traditional classifiers to analyze complaints based on citizen feedback . |
| Outcome: | The proposed methods have accuracy scores above 70% and can be used to improve public services. |
Annotation Process for the Dialog Act Classification of a Taglish E-commerce Q&A Corpus (D19-51)
Copied to clipboard
| Challenge: | Existing studies on DA classification in general contexts have not addressed this problem. |
| Approach: | They constructed a text-based corpus of 7,265 posts from the question and answer section of products on Lazada Philippines. |
| Outcome: | The text-based corpus of 7,265 posts from the question and answer section of products on Lazada Philippines was constructed using a tagset for DA classification . the corpus was composed dominantly of single-label posts, with 34% of the corpuse having multiple intent tags. |