jina financial qa search
1.0.0
En este ejemplo, utilizamos los transformadores Jina, PyTorch y Hugging Face para construir un sistema de respuesta a preguntas financieras basado en BERT listo para producción. Adaptamos un enfoque de reclasificación de pasajes recuperando primero las 50 respuestas de los candidatos principales y luego reclasificando las respuestas de los candidatos utilizando FinBERT-QA, un modelo basado en BERT ajustado en el conjunto de datos de FiQA que logró resultados de última generación.
? Consulte este tutorial para obtener una guía paso a paso y explicaciones detalladas.
Motivados por la demanda emergente en la industria financiera por el análisis automático de datos estructurados y no estructurados a escala, los sistemas de control de calidad pueden proporcionar ventajas lucrativas y competitivas a las empresas al facilitar la toma de decisiones de los asesores financieros. El objetivo de nuestro sistema es buscar una lista de pasajes de respuestas relevantes a una pregunta. A continuación se muestra un ejemplo de una pregunta y una respuesta real del conjunto de datos de FiQA:
https://github.com/yuanbit/jina-financial-qa-search.git
Usaremos jina-financial-qa-search/ como nuestro directorio de trabajo.
pip install -r requirements.txt
bash get_data.sh
Queremos indexar un subconjunto de pasajes de respuestas del conjunto de datos de FiQA, dataset/test_answers.csv :
398960 From http://financial-dictionary.thefreedictionary.com/Business+Fundamentals The facts that affect a company's underlying value. Examples of business fundamentals include debt, cash flow, supply of and demand for the company's products, and so forth. For instance, if a company does not have a sufficient supply of products, it will fail. Likewise, demand for the product must remain at a certain level in order for it to be successful. Strong business fundamentals are considered essential for long-term success and stability. See also: Value Investing, Fundamental Analysis. For a stock the basic fundamentals are the second column of numbers you see on the google finance summary page, P/E ratio, div/yeild, EPS, shares, beta. For the company itself it's generally the stuff on the 'financials' link (e.g. things in the quarterly and annual report, debt, liabilities, assets, earnings, profit etc.
19183 If your sole proprietorship losses exceed all other sources of taxable income, then you have what's called a Net Operating Loss (NOL). You will have the option to "carry back" and amend a return you filed in the last 2 years where you owed tax, or you can "carry forward" the losses and decrease your taxes in a future year, up to 20 years in the future. For more information see the IRS links for NOL. Note: it's important to make sure you file the NOL correctly so I'd advise speaking with an accountant. (Especially if the loss is greater than the cost of the accountant...)
327002 To be deductible, a business expense must be both ordinary and necessary. An ordinary expense is one that is common and accepted in your trade or business. A necessary expense is one that is helpful and appropriate for your trade or business. An expense does not have to be indispensable to be considered necessary. (IRS, Deducting Business Expenses) It seems to me you'd have a hard time convincing an auditor that this is the case. Since business don't commonly own cars for the sole purpose of housing $25 computers, you'd have trouble with the "ordinary" test. And since there are lots of other ways to house a computer other than a car, "necessary" seems problematic also.
Puede cambiar la ruta a answer_collection.tsv para indexar con el conjunto de datos completo.
python app.py index
Al final verás lo siguiente:
✅ done in ⏱ 1 minute and 54 seconds ? 7.7/s
gateway@18904[S]:terminated
doc_indexer@18903[I]:recv ControlRequest from ctl▸doc_indexer▸⚐
doc_indexer@18903[I]:Terminating loop requested by terminate signal RequestLoopEnd()
doc_indexer@18903[I]:#sent: 56 #recv: 56 sent_size: 1.7 MB recv_size: 1.7 MB
doc_indexer@18903[I]:request loop ended, tearing down ...
doc_indexer@18903[I]:indexer size: 865 physical size: 3.1 MB
doc_indexer@18903[S]:artifacts of this executor (vecidx) is persisted to ./workspace/doc_compound_indexer-0/vecidx.bin
doc_indexer@18903[I]:indexer size: 865 physical size: 3.2 MB
doc_indexer@18903[S]:artifacts of this executor (docidx) is persisted to ./workspace/doc_compound_indexer-0/docidx.bin
Necesitamos crear un Ejecutor personalizado para reclasificar las 50 respuestas de los candidatos principales. Podemos hacer esto con la API de Jina Hub. Asegurémonos de que la extensión Jina Hub esté instalada:
pip install "jina[hub]"
Podemos construir el Ranker personalizado, FinBertQARanker ejecutando:
jina hub build FinBertQARanker/ --pull --test-uses --timeout-ready 60000
Ahora podemos utilizar nuestro motor de búsqueda de control de calidad financiero ejecutando:
python app.py search
El clasificador puede tardar algún tiempo en calcular las puntuaciones de relevancia, ya que utiliza un modelo basado en BERT. Puede probar esta lista de preguntas del conjunto de datos de FiQA:
• What does it mean that stocks are “memoryless”?
• What would a stock be worth if dividends did not exist?
• What are the risks of Dividend-yielding stocks?
• Why do financial institutions charge so much to convert currency?
• Is there a candlestick pattern that guarantees any kind of future profit?
• 15 year mortgage vs 30 year paid off in 15
• Why is it rational to pay out a dividend?
• Why do companies have a fiscal year different from the calendar year?
• What should I look at before investing in a start-up?
• Where do large corporations store their massive amounts of cash?
#JinaSearchCopyright (c) 2021 Amiga de Jina. Reservados todos los derechos.
