Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @lmthang
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @lmthang
-
Prikvačeni tweet
Introducing
#MeenaBot, a 2.6B-param open-domain chatbot with near-human quality. Remarkably, we show strong correlation between perplexity & humanlikeness! Paper: https://arxiv.org/abs/2001.09977 Sample conversations: https://github.com/google-research/google-research/tree/master/meena … https://twitter.com/GoogleAI/status/1222230622355087360 …pic.twitter.com/3xNSV4r4uB
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
About
#MeenaBot data (asked by@GaryMarcus & others): 1. Only one occurrence of "Hayvard" in the training data. 2. The sentence that contains "Hayvard" has meaning similar to "Guess what, I obtained my bachelor from Hayvard." 3. No occurrence of "cow*" in the same conversation.https://twitter.com/quocleix/status/1222571742746443776 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
If this is about
#MeenaBot, totally understand the sentiment & we are working hard on making sure the community can verify & reproduce. Our research (cc@quocleix) has always been very open whenever we can. Btw, conversations here are not cherry picked :)https://github.com/google-research/google-research/blob/master/meena/meena.txt …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
It was a pleasure to have Mitsuku included in your research and to have it ranked so highly, especially against Xiaoice, as I've never seen the two compared before. I guess the big question is when can we talk to Meena?
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
Happy
#PalindromeDay 02 02 2020 This is the first time in over 900 years (since 11/11/1111) the date is palindromic no matter the date format. It’s also the 33rd day of the year with 333 days left!pic.twitter.com/0hYP0p6mEaHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
#MeenaBot@Imthang@GoogleAI These are incredibly interesting to read.pic.twitter.com/paG4E6iQzz
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
I chatted with
#MeenaBot about the#coronavirus and her advice is to see a doctor sooner rather than later. I guess it's not a bad one & hope everyone is well! On the other hand, Meena is also excited about technology, especially VR!pic.twitter.com/pKRxfFxp38
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Highly recommend watching this 8-minute video https://youtu.be/STrrlLG15OY on
#MeenaBot & the paper, with details not included the blog such as SSA vs humanlikeness correlation, sample-and-rank, removing cross-turn repetition. (Blog: https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html …)https://twitter.com/CShorten30/status/1222655686980644864 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Meena was simply a name that
@xpearhead dreamt of, but if you'd like an acronym, here's mine: "May End-to-End Neural-network be AGI"! thanks to all great collaborators, David,@jamie_hall,@nfiedel,@ThoppilanRomal, Zi,@ImAKulshreshtha,@gnemade15,@yifenglou, and@quocleix!https://twitter.com/JeffDean/status/1222253733016268800 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
New paper: Towards a Human-like Open-Domain Chatbot. Key takeaways: 1. "Perplexity is all a chatbot needs" ;) 2. We're getting closer to a high-quality chatbot that can chat about anything Paper: https://arxiv.org/abs/2001.09977 Blog: https://ai.googleblog.com/2020/01/towards-conversational-agent-that-can.html …pic.twitter.com/5SOBa58qx3
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Implications from the
#MeenaBot project: 1. Perplexity might be "the" automatic metric that the field's been looking for. 2. Bots trained on large-scale social conversations & pushed hard for low perplexity will be good. 3. Safety layer is needed for respectful conversations!pic.twitter.com/WHrcstcgltPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We design a new human evaluation metric, Sensibleness & Specificity Average (SSA), which captures key elements of natural conversations. SSA is also shown to correlate with humanlikeness while being easier to measure. Human scores 86% SSA,
#MeenaBot 79%, other best chatbots 56%.pic.twitter.com/I7NKl2b9Tl
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
#MeenaBot is based on the Evolved Transformer (ET, an improved Transformer) & trained to minimize perplexity, the uncertainty of predicting the next word in a conversation. We built a novel "shallow-deep" seq2seq architecture: 1 ET block for encoder & 13 ET blocks for decoder.pic.twitter.com/Mv2d4Los3k
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
Google Dataset Search is now officially out of beta. "Dataset Search has indexed almost 25 million of these datasets, giving you a single place to search for datasets & find links to where the data is." Nice work, Natasha Noy and everyone else involved!https://blog.google/products/search/discovering-millions-datasets-web/ …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
My grandpa passed away a few years ago. We didn’t get to say goodbye to him. Yesterday we found out google maps finally drove through his farm and as we were curious going through it, where the road ends, there is my grandpa, just sitting there.
pic.twitter.com/CbwRTkCKrZPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
tf.keras in
@TensorFlow 2.1 adds TextVectorization layer to flexibly map raw strings to tokens/word pieces/ngrams/vocab. An image is just a matrix of numbers but text always needs extra work and it‘s cleaner having preprocessing inside the model
https://github.com/tensorflow/tensorflow/releases/tag/v2.1.0 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
Okay yeah I'm convinced: it's not actually weird to have MT as an example problem, even if it's not most people's end-goal. Someone else pointed out that the datasets are actually available too, which is a big consideration I didn't think of. Thanks all!https://twitter.com/lmthang/status/1215047953989038082 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
.
@stanfordnlp people’s#ICLR2020 papers #2—ELECTRA:@clark_kev and colleagues (incl. at@GoogleAI) show how to build a much more compute/energy efficient discriminative pre-trainer for text encoding than BERT etc. using instead replaced token detection https://openreview.net/forum?id=r1xMH1BtvB …pic.twitter.com/lFAr6XYSWx
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
Vim finally usable on a smartphone.https://twitter.com/ValaAfshar/status/1214280917528694784 …
0:31Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Thang Luong proslijedio/la je Tweet
Throw back at
#vietaisummit last month, over 500 attendees, renowned speakers@lmthang (Google Brain), CEO@KambriaNetwork Thuc Vu, CMU prof & CEO@TRIAD_Global James Kuffer, Principal scientist@QatarComputing Preslav Nakov,@chipro & many more! Recap: https://facebook.com/notes/vietai/event-recap-vietai-summit-2019-ai-for-the-future/2090687904366925/ …pic.twitter.com/VO0wN21RTN
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.