Research on the Relevant Matching Method of Internet MediaInformation-Stock Assets Based on the Combination of Literal and Semantic
DOI:
https://doi.org/10.54097/ehss.v4i.2771Keywords:
NLP; Few-Shot Learning; Media Information; Siamese Network.Abstract
Classify and match kinds of media information has been a problem to be solved. To solve the problem, the study finished the experiment of text matching, include the process of data collection and building the media information with stock asset matcher, based on the perspective of literal matching and semantic matching. The experimental data comes from financial news websites such as eastmoney.com and jrj.com. This study uses a small sample learning model to solve the problem of lacking labeled data and too much types of financial media information. Based on the Siamese network and Word2Vec model, the matcher performs well in matching tasks. This study will provide the basic way to support the research of impact of Internet media information on financial market asset prices from the perspective of salient effects.
Downloads
References
Sepp Hochreiter, Jürgen Schmidhuber. Long short-term memory. Neural Computation, 1997, 9(8): 1735-1780.
Hochreiter, Sepp, Schmidhuber. LSTM can solve hard long time lag problems. Advances in Neural Information Processing Systems, 1996.
Felix A. Gers, Jürgen Schmidhuber, Fred Cummins. Learning to Forget: Continual Prediction with LSTM. Neural Computation, 2000, 12(10): 2451-2471.
Hochreiter, Sepp. Untersuchungen zu dynamischen neuronalen Netzen. Technical University Munich, Institute of Computer Science, 1991.
Chicco, Davide. Siamese neural networks: an overview. Artificial Neural Networks, Methods in Molecular Biology, 2020, vol. 2190 (3rd ed.)
Bromley, Jane, Guyon, et al. Signature verification using a Siamese time delay neural network. Advances in Neural Information Processing Systems, 1994, 6: 737–744.
Chopra, Hadsell, LeCun. Learning a similarity metric discriminatively, with application to face verification. IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2005, 1: 539–546.
Taigman, Yang, Ranzato, et al. DeepFace: Closing the Gap to Human-Level Performance in Face Verification. IEEE Conference on Computer Vision and Pattern Recognition, 2014, 1701–1708.
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
