Open source Microsoft Translator alternatives

Transformers Explained Visually

“It isn't so much that "other setups didn't work". More like "the first thing we found that did work turned out to be the minimal thing that could work". Transformers are conventional feed-forward neural networks alternated with attention blocks. You can think of them as big huge…”

Transformers Explained Visually

“If I had to summarize this in with sentences then here is my attempt. Transformer training can be parallelized easily, making it possible to use brute force to train the neural network quickly (bitter lesson rewards compute friendly scalable architectures). Transformers have…”

Show HN: Thinc, a new deep learning library by the makers of spaCy and FastAPI

“I've been working on various versions of Thinc for a long time --- it's always been the name for the machine learning code powering spaCy. But previous versions really weren't worth using for other developers, and so I never wanted to advertise the library as something people…”

Show HN: Thinc, a new deep learning library by the makers of spaCy and FastAPI

“I'm going to try this simply because spaCy is so great. It's my goto for NLP in different languages (notably German) and a joy to work with.”

Facebook AI Research Open Sources fastText

“Jupyter notebook with some numbers on performance and accuracy of fastText: This compares fastText against the word2vec implementation in gensim, on the syntactic/semantic word analogy task. (raw pull request with comments: )”

RasaGPT: First headless LLM chatbot built on top of Rasa, Langchain and FastAPI

“FWIW, individual classes are generally tiny, so we found using langchain is fine and then for places we need to beef up (chunking, not calling 'eval', ...), we do our own class/subclass. That way we can align with community for broader pieces and patterns, and decrease technical…”

RasaGPT: First headless LLM chatbot built on top of Rasa, Langchain and FastAPI

“OP here. i agree. perhaps you're confused on the intent. the only flag being planted is for folks using rasa looking for a reference implementation just like i was a week ago. not sure if you're being intentionally cynical but trying is good thing. why? bc most ppl don't try.…”

Dead Code Should Be Buried – Why I Didn't Contribute to NLTK

“So rather than jump in and start adding documentation you blast the developers, who are offering this stuff free and without warranty or implied fitness for any purpose? You can contribute by adding documentation where you see it lacking, especially if you have domain specific…”

Dead Code Should Be Buried – Why I Didn't Contribute to NLTK

“I disagree strongly. This is the same difference as Linux vs Minix. Minix didn't want anything added as it was said to be for educational purposes even though that didn't reflect the use cases. The author points out that whilst the stated aim of NLTK is for education, it's used…”

Stanza: A Python natural language processing toolkit for many human languages

“You can also try out Stanza in spaCy --- Ines updated the spacy-stanfordnlp wrapper to use the new version pretty much immediately: I was asked by a friend about Stanza in a private DM, I'll paste the answer here as I think others might find it helpful: Q: are stanza models more…”

Stanza: A Python natural language processing toolkit for many human languages

“I was rather curious to see how this handled Garden Path Sentences[0]. For "The old man the boat.", Stanza interprets "man" as a noun rather than a verb. Similarly, for "The complex houses married and single soldiers and their families." "houses" is also interpreted as a noun…”

Abstractive Summarization Results

“Hey guys, looking at recent pull requests and issues, it looks like a common interest of contributors (On top of NMT obv) is Abstractive Summarization. Any suggestions of how to train a model that will get close results to recent papers on the CNN-Daily Mail Database? Any…”

How to reproduce your results on WMT'14 ENDE datasets of "Attention is All You Need"?

“Hi, I want to reproduce the results on WMT'14 ENDE datasets of "Attention is All You Need" paper. I have read [OpenNMT-FAQ]( and I want to know the exact details about your experiments: 1. Did you do the BPE or word spiece? 2. What's the exact BLEU score of your experiments on…”

Show HN: Argos Translate open source neural machine translation in Python

“This is my project it's a Python library and GUI that lets you install "packages" which contain all of the files for doing neural machine translation locally. I have pretrained models packaged for translating between English and Arabic, Chinese, French, Russian, and Spanish.…”

Port to more platforms

“The easiest are probably MacOS and Windows using py2app and py2exe but other platforms to consider could be mobile, BSD, Debian, Red Hat, FlatPak, or BSD. I'd like to be able to run builds on Linux as much as possible but this may not be possible for some platforms. There's also…”

Show HN: ColBERT Build from Sentence Transformers

“Hi, there is a single loss right now, but I plan to add some Sentence Transformers losses. ColBERT is slow as a retriever, but is quite efficient as a Ranker on GPU (way faster than cross-encoder). I plan to release pre-trained checkpoints on HuggingFace with benchmarks using…”