jina financial qa search
1.0.0
Dalam contoh ini, kami menggunakan trafo Jina, PyTorch, dan Hugging Face untuk membangun Sistem Penjawab Pertanyaan Keuangan berbasis BERT yang siap produksi. Kami mengadaptasi pendekatan pemeringkatan ulang bagian dengan terlebih dahulu mengambil 50 jawaban kandidat teratas, kemudian mengurutkan ulang jawaban kandidat menggunakan FinBERT-QA, model berbasis BERT yang disesuaikan dengan kumpulan data FiQA yang mencapai hasil canggih.
? Silakan merujuk ke tutorial ini untuk panduan langkah demi langkah dan penjelasan rinci.
Termotivasi oleh meningkatnya permintaan di industri keuangan untuk analisis otomatis data tidak terstruktur dan terstruktur dalam skala besar, sistem QA dapat memberikan keunggulan yang menguntungkan dan kompetitif bagi perusahaan dengan memfasilitasi pengambilan keputusan oleh penasihat keuangan. Tujuan sistem kami adalah mencari daftar bagian jawaban relevan yang diberikan sebuah pertanyaan. Berikut adalah contoh pertanyaan dan jawaban kebenaran dasar dari kumpulan data FiQA:
https://github.com/yuanbit/jina-financial-qa-search.git
Kami akan menggunakan jina-financial-qa-search/ sebagai direktori kerja kami.
pip install -r requirements.txt
bash get_data.sh
Kami ingin mengindeks subkumpulan bagian jawaban dari kumpulan data 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.
Anda dapat mengubah jalur answer_collection.tsv untuk mengindeks dengan kumpulan data lengkap.
python app.py index
Pada akhirnya Anda akan melihat yang berikut:
✅ 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
Kita perlu membuat Pelaksana khusus untuk mengurutkan ulang 50 jawaban kandidat teratas. Kita bisa melakukan ini dengan Jina Hub API. Mari kita pastikan bahwa ekstensi Jina Hub sudah terpasang:
pip install "jina[hub]"
Kita dapat membangun Ranker khusus, FinBertQARanker dengan menjalankan:
jina hub build FinBertQARanker/ --pull --test-uses --timeout-ready 60000
Kami sekarang dapat menggunakan mesin pencari QA Keuangan kami dengan menjalankan:
python app.py search
Ranker mungkin memerlukan waktu untuk menghitung skor relevansi karena menggunakan model berbasis BERT. Anda dapat mencoba daftar pertanyaan berikut dari kumpulan data 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?
#JinaSearchHak Cipta (c) 2021 Sahabat Jina. Semua hak dilindungi undang-undang.
