View profile

NLP News - NMT, beam search, & food

Revue
 
Welcome to the second edition of NLP News. This time, we will take a more in-depth look at NMT and at
 
July 24 · Issue #2 · View online
NLP News
Welcome to the second edition of NLP News. This time, we will take a more in-depth look at NMT and at one of its key components, beam search. We will also look at food from different angles: from analyzing linguistic markers in menus, to predicting recipes, to learning multimodal representations. Enjoy!

NMT resources
TensorFlow NMT Tutorial
MxNet NMT Tutorial
NLP in-depth: Beam search
Beam search is an integral component of every state-of-the-art NMT model, but is generally taken for granted. Recent work takes a deeper look at beam search, which demonstrates that vanilla beam search has still a lot of potential for improvement.
Incorporating prior knowledge into beam search
Keeping track of other items on the beam
Finding the optimal beam size
Conference countdown
ACL 2017 kicks-off on July 30
Accepted papers for EMNLP 2017
Industry Insights
A chatbot for good
DyNet upgrades to v2.0
An analysis of censorship of the death of Liu Xiaobo on WeChat and Weibo
PAIR: the People + AI Research Initiative
ParlAI request for proposals
Paper picks
[1707.03389] SCAN: Learning Abstract Hierarchical Compositional Visual Concepts
[1707.05589] On the State of the Art of Evaluation in Neural Language Models
Linguistic Markers of Status in Food Culture: Bourdieu’s Distinction in a Menu Corpus
Learning Cross-modal Embeddings for Cooking Recipes and Food Images
[1707.06320] Learning Visually Grounded Sentence Representations
Dataset spotlight
A New Multi-Turn, Multi-Domain, Task-Oriented Dialogue Dataset
Did you enjoy this issue?
If you don't want these updates anymore, please unsubscribe here
If you were forwarded this newsletter and you like it, you can subscribe here
Powered by Revue