Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
- Medijski sadržaj
Blokirali ste korisnika/cu @andreasvc
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @andreasvc
-
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
We intend to analyze the performance of Bertje in more detail and on more tasks. To be continued!
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Bertje is the latest installment in a series of language-specific BERT models, after French, German, Italian, Finish, and Japanese. Collecting better data and pretraining a monolingual model is clearly worth the effort compared to using multilingual BERT.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The architecture of Bertje is the same as English BERT_base, but we use improved training objectives presented in recent work: we apply Sentence Order Prediction instead of Next Sentence Prediction, and the Masked Language Model predicts whole words.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Our gains in performance over multilingual BERT are due to (1) focusing on a single language, (2) improvements in training, but also (3) the quantity and especially quality of our training data which contains not just Wikipedia text, but also a large number of books.pic.twitter.com/wYgOuytb8r
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We evaluate on several downstream tasks and outperform multilingual BERT. In addition, we test the effect of the number of iterations using a checkpoint at 850k iterations.pic.twitter.com/5iYYf4RQGI
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hot off the press: Bertje. We collected a large and diverse corpus of Dutch and trained a monolingual BERT model. The model is available for download. Paper: http://arxiv.org/abs/1912.09582 joint work by
@WietseDEV me@AriannaBisazza@tommaso_caselli Gertjan van Noord & Malvina Nissimpic.twitter.com/c1aRvR8QOv
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Another surprising finding is that my old-fashioned rule-based system appears to be competitive with a neural, BERT-based system, as suggested by the comparison with
@dbamman et al 2019, who report results on 19th century English novels https://arxiv.org/abs/1912.01140Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
There does appear to be interesting variation in performance across novels, which warrants further study, especially with respect to literariness.
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Computers still struggle to understand "who did what to whom?" in texts. My latest paper on coreference resolution presents results on an annotated corpus of contemporary Dutch novels. Surprisingly, literature is not harder than news text! Paper: https://clinjournal.org/clinj/article/view/91/ …
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Andreas proslijedio/la je Tweet
.
@Ted_Underwood made a plea today@UniLeiden for the critical use of digital tools and methods in the Humanities. "There's really nothing about machine learning methods that is contradictory with a perspectival humanistic approach. These tools only enlarge the humanities."pic.twitter.com/e36yQnjR2s
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Andreas proslijedio/la je Tweet
I'm not at any conference, but Andreas van Cranenburgh is presenting about coreference resolution in our local seminar. I like this summary of the state of the field over the past years...pic.twitter.com/U0LZ4NLyGk
Prikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
-
This Friday
@corinakoolen and I will present interesting new survey results on literariness. Come to our presentation 10:12-10:30, Cloud Nine,#DH2019https://twitter.com/andreasvc/status/1123607801291509766 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Andreas proslijedio/la je Tweet
1/7 Do word embeddings really say that man is to doctor as woman is to nurse? Apparently not. Check out this thread for a description of a short paper I co-wrote with Malvina Nissim and Rob van der Goot, available here: https://arxiv.org/abs/1905.09866
#NLProc#biasPrikaži ovu nitHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Literary Pepsi Challenge: intrinsic and extrinsic factors in judging literary quality. Abstract to be presented at
#DH2019 with@corinakoolen: http://andreasvc.github.io/dh2019.pdfHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This Thursday I'll reflect on what predictive modeling results tell us about literature in a lecture
@univgroningen https://www.rug.nl/research/research-let/expertisecentra/centre-for-digital-humanities/news-and-events/events/2019-02-14-dt-koolen-cranenburgh-literary-quality … Unfortunately@corinakoolen can't make it, so the talk won't cover her results on gender.Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
How recognizable is literary language? Very! See my new paper https://doi.org/10.1007/s10579-018-09442-4 … Joint work with Karina van Dalen and @brandaen
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
This Thursday I'll present "A Dutch coreference resolution system with quote attribution"
@29_clin including an evaluation on literature. Poster #2 in the second poster session at 14:45-16:15. Code:https://github.com/andreasvc/dutchcoref …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Andreas proslijedio/la je Tweet
To get outside North Am: Andreas van Cranenburgh presented a fascinating paper at COLING showing that a corpus of clichés can be used to predict human judgment about novels. http://aclweb.org/anthology/W18-4504 … Just 1 ex. of great work coming out of the Riddle of Literary Quality in NL 6/9.pic.twitter.com/OeznhuV4R9
Prikaži ovu nitHvala. 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.