flashtext
KeyBERT
Our great sponsors
| flashtext | KeyBERT | |
|---|---|---|
| 8 | 5 | |
| 5,531 | 3,213 | |
| - | - | |
| 0.0 | 6.1 | |
| 6 months ago | about 1 month ago | |
| Python | Python | |
| MIT License | MIT License |
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.
flashtext
-
Show HN: LLMs can generate valid JSON 100% of the time
I have some other comment on this thread where I point out why I don’t think it’s superficial. Would love to get your feedback on that if you feel like spending more time on this thread.
But it’s not obscure? FlashText was a somewhat popular paper at the time (2017) with a popular repo (https://github.com/vi3k6i5/flashtext). Their paper was pretty derivative of Aho-Corasick, which they cited. If you think they genuinely fucked up, leave an issue on their repo (I’m, maybe to your surprise lol, not the author).
Anyway, I’m not a fan of the whatabboutery here. I don’t think OG’s paper is up to snuff on its lit review - do you?
-
[P] what is the most efficient way to pattern matching word-to-word?
The library flashtext basically creates these tries based on keywords you give it.
-
What is the most efficient way to find substrings in strings?
Seems like https://github.com/vi3k6i5/flashtext would be better suited here.
-
[P] Library for end-to-end neural search pipelines
I started developing this tool after using haystack. Pipelines are easier to build with cherche because of the operators. Also, cherche offers FlashText, Lunr.py retrievers that are not available in Haystack and that I needed for the project I wanted to solve. Haystack is clearly more complete but I think also more complex to use.
-
How can I speed up thousands of re.subs()?
For the text part not requiring regex, https://github.com/vi3k6i5/flashtext might help
-
My first NLP pipeline using SpaCy: detect news headlines with company acquisitions
Spacy for parsing the Headlines, remove stop words etc. might be ok but I think the problem is quite narrow so a set of fixed regex searches might work quite well. If regex is too slow, try: https://github.com/vi3k6i5/flashtext
-
What tech do I need to learn to programmatically parse ingredients from a recipe?
I would probably use something like [flashtext](https://github.com/vi3k6i5/flashtext) which should not be too hard to port to kotlin.
- Quickest way to check that 14000 strings arent in An original string.
KeyBERT
-
I want to extract important keywords from large documents...
Use something else like KeyBERT or BERTopic: https://github.com/MaartenGr/KeyBERT It's much faster.
-
[D]: Predict the most probable document including the answer to a given question
Using keyword similarity using KeyBERT:https://github.com/MaartenGr/KeyBERT (i.e. loading keywords for each of the given documents and compare to the keywords of the question)
-
BERT execution time
Would anyone know an equation or a general rule of thumb for how long it would take this BERT algorithm (KeyBERT: https://github.com/MaartenGr/KeyBERT) to select n keywords from a string of character length m on a GPU of certain relevant specs?
-
[P] Building model to extract keywords from legal documents
Look into rake, pke, phrasemachine, pyate, keybert.
- Alternate approaches to TF-IDF?
What are some alternatives?
rake-nltk - Python implementation of the Rapid Automatic Keyword Extraction algorithm using NLTK.
yake - Single-document unsupervised keyword extraction
magnitude - A fast, efficient universal vector embedding utility package.
RAKE-tutorial - A python implementation of the Rapid Automatic Keyword Extraction
Optimus - :truck: Agile Data Preparation Workflows made easy with Pandas, Dask, cuDF, Dask-cuDF, Vaex and PySpark
pke - Python Keyphrase Extraction module
faiss - A library for efficient similarity search and clustering of dense vectors.
gensim - Topic Modelling for Humans
spaCy - 💫 Industrial-strength Natural Language Processing (NLP) in Python
dutch-word-embeddings - Dutch word embeddings, trained on a large collection of Dutch social media messages and news/blog/forum posts.
scattertext - Beautiful visualizations of how language differs among document types.