Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @anttiajanki
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @anttiajanki
-
Prikvačeni tweet
I published a Finnish language model for
@spacy_io : https://github.com/aajanki/spacy-fi … POS tagging and dependency parsing for Finnish on#Python !pic.twitter.com/FydWJxaa7z
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Updated my Finnish POS and lemmatization comparison https://github.com/aajanki/finnish-pos-accuracy …: * includes new spaCy Finnish model * batched evaluation makes most models run much faster * auxiliary verbs as a distinct tag * tokenization fixespic.twitter.com/vprOB5hE8q
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
"You look like a thing and I love you" by
@JanelleCShane is a delightful introduction to AI. It studies cases where algorithms fail, often with silly and/or terrifying consequences.pic.twitter.com/n2f072gVVp
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I run a small experiment on
#classification with noisy labels. https://github.com/aajanki/label-noise-classification/blob/master/Label%20noise%20robust%20classification.ipynb …#MachineLearningHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Antti Ajanki proslijedio/la je Tweet
The 2010s were an eventful decade for NLP! Here are ten shocking developments since 2010, and 13 papers* illustrating them, that have changed the field almost beyond recognition. (* in the spirit of
@iamtrask and@FelixHill84, exclusively from other groups :)).Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
What does it mean for a machine to “understand”?https://medium.com/@tdietterich/what-does-it-mean-for-a-machine-to-understand-555485f3ad40 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
A great explanation on what transformers are and how they are applied on sequence modeling: http://www.peterbloem.nl/blog/transformers …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
In exploratory search, relevant results are those that reveal available options and possible query refinements. Relevance can't really be assigned to individual results but to the whole result set.https://opensourceconnections.com/blog/2019/12/11/what-is-a-relevant-search-result/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Suomen kielen sanojen taivutus:
oppilaiksi → oppilaki
perusteluissa → perusteluu
aikajanoja → aikajano
ääri-ilmiöissä → ääri-ilmiyö
asiantuntijoiksi → asiantuntijoki
perustuvan → perustupa
aurinkoamme → aurinkoammeHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Antti Ajanki proslijedio/la je Tweet
Overhyped claims about AI have contributed to past AI winters.
@GaryMarcus fears that we could be headed down that same path again. Here's what we can do to stop it.#ai#hypehttps://thegradient.pub/an-epidemic-of-ai-misinformation/ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Antti Ajanki proslijedio/la je Tweet
A history of procedural text generation:https://tedium.co/2019/11/14/procedural-text-history/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Antti Ajanki proslijedio/la je Tweet
On the linguistic patterns of "her/hers" and "him/his" which results in data with gender imbalance: “linguistic difference that is not inherently biased could still result in a biased machine learning model.” — Robert Munrohttps://link.medium.com/tpaxWGmGx1
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Granted, I'm on CPU and processing one sentence at a time. GPU and longer documents would hopefully reduce the required time.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Lemmatization is expensive. Halving the error rate requires increasing the computational effort more than 1000-fold!pic.twitter.com/XGzxzUbCPM
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Comparing Finnish part-of-speech tagging and lemmatization algorithms. Turku neural parser, FinnPos and StanfordNLP are the most accurate in my tests.
#NLProc https://github.com/aajanki/finnish-pos-accuracy …pic.twitter.com/KMYFPZTiBd
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
A comprehensive review of document embedding methods:https://towardsdatascience.com/document-embedding-techniques-fed3e7a6a25d …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Antti Ajanki proslijedio/la je Tweet
Evaluation metrics are crucial to progress in machine learning. In light of recent interest in transfer learning in NLP,
@chipro gives a comprehensive overview of some of the most important evaluation metrics in language modeling.#NLProchttps://thegradient.pub/understanding-evaluation-metrics-for-language-models/ …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
My colleague
@alucardna has been training hate speech detectors on multiple languages. She gave a presentation of what she has learned so far at#PyConDE Check out the slides!https://twitter.com/alucardna/status/1183007087665827842 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
A Very Short History of Artificial Neural Networkshttps://medium.com/@jimstone_68634/a-very-short-history-of-artificial-neural-networks-9820dfd6d903 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Reasons why English is not representative of all natural languages:https://thegradient.pub/the-benderrule-on-naming-the-languages-we-study-and-why-it-matters/ …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.