KitanaQA
FinBERT-QA
Our great sponsors
KitanaQA | FinBERT-QA | |
---|---|---|
1 | 1 | |
57 | 113 | |
- | - | |
0.0 | 0.0 | |
9 months ago | 11 months ago | |
Python | Python | |
Apache License 2.0 | - |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
KitanaQA
-
Ask HN: Who is hiring? (February 2021)
Searchable.ai | Full Stack Engineer | Full Time | Remote U.S.
We help our users find their stuff wherever it's stored as we build the future of enterprise search.
We are hiring a full-stack engineer with Rails experience to join our growing engineering team. Our stack includes: Rails, Electron, Webpack, PostgreSQL, Elasticsearch & Kubernetes.
This position will also have the opportunity to help integrate our research teams' SOTA work into our product to help users ask questions across their files (see: https://github.com/searchableai/kitanaqa).
Full description here: https://www.searchable.ai/full-stack-engineer/ and drop us a line at careers at searchable dot ai if you're interested!
FinBERT-QA
-
Best way to approach financial statement analysis with NLP and Image Recognition?
Open Domain Question Answering (ODQA) using a deep transformer NLP model that has been fine tune trained on a financial domain dataset such as FiQA.
What are some alternatives?
TextAttack - TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP https://textattack.readthedocs.io/en/master/
haystack - :mag: LLM orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
akvo-flow - A data collection and monitoring tool that works anywhere.
BERT-QE - Code and resources for the paper "BERT-QE: Contextualized Query Expansion for Document Re-ranking".
ozone - Scalable, redundant, and distributed object store for Apache Hadoop
happy-transformer - Happy Transformer makes it easy to fine-tune and perform inference with NLP Transformer models.
auto-attack - Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
kiri - Backprop makes it simple to use, finetune, and deploy state-of-the-art ML models.
eClaire - Trello card printer
kiri - Kiri is a visual tool designed for reviewing schematics and layouts of KiCad projects that are version-controlled with Git.
OpenAttack - An Open-Source Package for Textual Adversarial Attack.
TextFooler - A Model for Natural Language Attack on Text Classification and Inference