[Read more] In September 2018, Deep Learning Indaba 2018 conference was held in South Africa, which gathered many world-class top research scholars. During his own sharing at the conference, Sebastian Ruder consulted the 25 cutting-edge researchers present, including Yoshua Bengio, on four questions within the NLP field, and made the full 25 Q&A transcripts public on twitter yesterday, as detailed below.

Presentation.

The Deep Learning Indaba 2018 conference was started last year with the vision of accelerating the research climate for machine learning in Africa through state-of-the-art teaching, networking, and policy debates, and helping African people grow rapidly into stalwarts in the field of machine learning.

This article brings together 25 leading scholars in NLP, including Yoshua Bengio, the father of neural networks and author of "The Flower Book," and Kevin Gimpel, an associate professor at the University of Chicago, who each shared their thoughts on the following four questions.

1. What do you think are the three major problems facing the NLP field today?

What do you think are the three biggest open problems in NLP at the moment?

2、What do you think is the most influential work in the last ten years?

What would you say is the most influential work in NLP in the last decade, if you had to pick just one?

3. if they exist, what factors do you think are taking this field in the wrong direction?

What, if anything, has led the field in the wrong direction?

4. what advice would you give to graduate students who are just starting to approach NLP issues?

What advice would you give a postgraduate student in NLP starting their project now?

The list of big names is as follows.

Hal Daumé III，Barbara Plank，Miguel Ballesteros，Anders Søgaard，Manaal Faruqui，Mikel Artetxe，Sebastian Riedel，Isabelle Augenstein，Bernardt Duvenhage，Lea Frermann，Brink van der Merwe，Karen Livescu，Jan Buys，Kevin Gimpel，Christine de Kock，Alta de Waal，Michael Roth，Maletěabisa Molapo，Annie Louise，Chris Dyer，Yoshua Bengio，Felix Hill，Kevin Knight，Richard Socher，George Dahl，Dirk Hovy，Kyunghyun Cho

Also, after summarizing the expert answers, Sebastian Ruder reviews the natural language development lineage and gives the top questions that appear most frequently in the expert responses.

Q&A transcript and sharing download at

Please follow Pro-Knowledge (scan the Pro-Knowledge QR code at the bottom, or click the blue Pro-Knowledge above).

• Reply to "FNLPEP" to get the link to download the full PPT of the expert advice.

The lineage of developments in the field of natural language processing

Problem 1: The biggest problem in the field of NLP research

Question 2: The problem of applying NLP in resource-constrained scenarios

Issue 3: Large-scale or multi-document reasoning

Issue 4: Data sets, questions and evaluation methods

With the full text of the expert's response.

-END-

Recommended>>
1、Virtual currencies becoming the only thing that exists on the blockchain
2、MYSQL String Interception Summary LEFT RIGHT SUBSTRING SUBSTRING
3、Intels 4th5th generation Core patched for vulnerabilities reboots frequently official response
4、A strange shortage of talent will constrain the development of AI in China
5、How should cancer prevention and treatment evolve in the era of big data

已发送

发送中