Profile picture
, 3 tweets, 3 min read
My Authors
Read all threads
Big congrats to the winners of the #conll2019 paper awards: 1) Best Paper: aclweb.org/anthology/K19-… by Gonen, Kementchedjhieva, Goldberg; 2) Best Paper for Research Inspired by Human Language Learning: aclweb.org/anthology/K19-… by Rabinovich, Watson, Beekhuizen, Stevenson.
We also had 2 honorable mentions for each best paper category:

Honorable mentions for best paper:

1) aclweb.org/anthology/K19-… by Koshorek, Stanovsky, Zhou, Srikumar, Berant

2) aclweb.org/anthology/K19-… by Jumelet, Zuidema, Hupkes
Honorable mentions for best paper inspired by research on human lang learning:

1) aclweb.org/anthology/K19-… by Ilharco, Zhang, Baldridge

2) aclweb.org/anthology/K19-… by Prasad, Schijndel, Linzen.

And a big thanks to our best paper committee members (names in the slide photo above)
Missing some Tweet in this thread? You can try to force a refresh.

Enjoying this thread?

Keep Current with CoNLL 2019

Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

Twitter may remove this content at anytime, convert it as a PDF, save and print for later use!

Try unrolling a thread yourself!

how to unroll video

1) Follow Thread Reader App on Twitter so you can easily mention us!

2) Go to a Twitter thread (series of Tweets by the same owner) and mention us with a keyword "unroll" @threadreaderapp unroll

You can practice here first or read more on our help page!

Related hashtags

#conll2019

Related threads

Profile picture
Hady Elsahar
@hadyelsahar
Talk3: @raquelfdzrovira talking about representations shaped by dialogue interaction data.

#ACL2019nlp #rep4nlp
"Task-oriented dialogue" is the setup we are discussing now because it gives us success notion to the dialogue analyse
The plan:

Instead of pre-defined symbolic representations for dialogue systems lets model visually grounded agents that learn to "see, ask and guess"
Read 13 tweets
Profile picture
Hady Elsahar
@hadyelsahar
Marco Baroni is starting the first invited talk at #rep4nlp
"Language is representations by itself. " #ACL2019nlp @sigrep_acl
@sigrep_acl Marco is talking about his previous work about the emergence of language communication between agents.

References:

"MULTI-AGENT COOPERATION
AND THE EMERGENCE OF (NATURAL) LANGUAGE"
arxiv.org/pdf/1612.07182…

"How agents see things"
aclweb.org/anthology/D18-…

#ACL2019nlp
@sigrep_acl Efficient encoding of input information:

"We explore providing some information to the sender and receiver agents and look at the emerging language if it develops to ignore the redundant parts of the input"

Kharitonov et al. 2019
arxiv.org/abs/1905.13687

#ACLnlp2019 #rep4nlp
Read 13 tweets
Profile picture
Hady Elsahar
@hadyelsahar
Tutorial 2: Story telling from structured data ans knowledge graphs #ACL2019nlp
Anirban laha @anirbanlaha Parag jain
#data2text #nlproc #NLG
@anirbanlaha Motivations for #Data2Text:
* Answer display in Question Answering systems
* kB summarization
* Question Generation
@anirbanlaha 4D perspective for #Data2Text
Paradigms, domain, tasks, Facets are 4 aspects of change.
Read 40 tweets
Profile picture
Sebastian Ruder
@seb_ruder
Coming up: A live Twitter thread of Session 8B: Machine Learning @NAACLHLT with some awesome papers on vocabulary size, subwords, Bayesian learning, multi-task learning, and inductive biases
@NAACLHLT First paper: How Large a Vocabulary Does Text Classification Need?
A Variational Approach to Vocabulary Selection aclweb.org/anthology/N19-…
@NAACLHLT Wenhu:
- Typically need to predefine vocabulary to get embeddings
- Most common approach: frequency-based cutoff; can lead to under-sized or over-sized vocabulary
Read 49 tweets
Profile picture
michael_nielsen
@michael_nielsen
Many people sharing this essay arguing that "computational scale beats clever new ideas". It takes for granted backprop, better activation functions, better learning methods, conv nets, better regularization techniques, etc etc. In other words, it seems to ignore the clever ideas
An example is this argument that Deep Blue was just massive search. It wasn't: it used more than 8,000 hand-engineered features that incorporated a huge amount of chess knowledge. Contrast Sutton's essay on the left with the paper about Deep Blue on the right:
Of course, I don't disagree at all with the essay that computational scale buys you an incredible amount, and it's easy to under-estimate. But GANs & levering pawns (etc) weren't discovered with computational scale.
Read 6 tweets
Profile picture
Yuval Pinter @🍺🍫 #emnlp2018
@yuvalpi
Invited talk from @yoavgo: Trying to Understand Recurrent Neural Networks for Language Processing
#BlackboxNLP #emnlp2018
Goldberg: "my career over the last few years, and maybe some of the others here: use LSTMs to build stuff"
#BlackboxNLP #emnlp2018
Goldberg: another use for LSTMs: build tools to use them. A less-pursued direction - trying to understand them ("reviewers don't care much")
#BlackboxNLP #emnlp2018
Read 18 tweets

Trending hashtags

#acl2019nlp #data2text #BikesMeanBusiness #evidence #documentary #SafetyOverSpeed #languageteachers #USBRS #RoadToZero #LTC #philanthropy #Yorkshire #RailTrails #signage #Leeds #Paper #grants #neuroscience #AV #BlackboxNLP #traffic #BikeTravel #AfD #KıbrısBarışHarekatı #k
Follow Us on Twitter!

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just three indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3.00/month or $30.00/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal Become our Patreon

Thank you for your support!