StanfordNLP: A Python NLP Library for Many Human Languages
StanfordNLP is the combination of the software package used by the Stanford team in the CoNLL 2018 Shared Task on Universal Dependency Parsing, and the group’s official Python interface to the Stanford CoreNLP software.
(StanfordNLP GitHub) / (PyPI)
Learning and Evaluating General Linguistic Intelligence
A team from DeepMind defines general linguistic intelligence as the ability to reuse previously acquired knowledge about a language’s lexicon, syntax, semantics, and pragmatic conventions to adapt to new tasks quickly. Using this definition, this team analyzes state-of-the-art natural language understanding models and conduct an extensive empirical investigation to evaluate them against these criteria through a series of experiments.
No Training Required: Exploring Random Encoders for Sentence Classification
The research team explores various methods for computing sentence representations from pre-trained word embeddings without any training. Their aim is to put sentence embeddings on more solid footing by 1) looking at how much modern sentence embeddings gain over random methods; and by 2) providing the field with more appropriate baselines going forward.
(Carnegie Mellon University & Facebook AI Research)
Glyce: Glyph-vectors for Chinese Character Representations
In this paper, researchers address this gap by presenting the Glyce, the glyph-vectors for Chinese character representations. They make three major innovations: using historical Chinese scripts to enrich the pictographic evidence in characters; designing CNN structures tailored to Chinese character image processing; and using image-classification as an auxiliary task in a multi-task learning setup to increase the model’s ability to generalize.
Go-Explore: a New Approach for Hard-Exploration Problems
Go-Explore opens up many new research directions into improving it and weaving its insights into current RL algorithms. It may also enable progress on previously unsolvable hard-exploration problems in a variety of domains, especially the many that often harness a simulator during training (e.g. robotics).
(Uber AI Lab)
Simpledet:A Simple and Versatile Framework for Object Detection and Instance Recognition
Simpledet is a simple and versatile framework for object detection and instance recognition. It’s major features include FP16 training for memory saving and up to 2.5X acceleration; highly scalable distributed training available out of box; full coverage of state-of-the-art models including FasterRCNN, MaskRCNN, CascadeRCNN, RetinaNet and TridentNet; and so on.
IBM Research Releases ‘Diversity in Faces’ Dataset to Advance Study of Fairness in Facial Recognition Systems
IBM Research is releasing a new large and diverse dataset called Diversity in Faces (DiF) to advance the study of fairness and accuracy in facial recognition technology. The first of its kind available to the global research community, DiF provides a dataset of annotations of 1 million human facial images. Using publicly available images from the YFCC-100M Creative Commons data set, we annotated the faces using 10 well-established and independent coding schemes from the scientific literature.
You May Also Like
Coursera and the University of Toronto Roll Out Autonomous Cars Specialization
Massive open online courses (MOOCs) students partial to machine learning, buckle up: The University of Toronto wants to inculcate you with driverless car engineering knowledge. Coursera, the online learning platform founded by Stanford professors Andrew Ng and Daphne Koller, today announced that it’s teaming up with the U of T to offer a Self-Driving Cars specialization, which it claims is the first of its kind.
AI Gaming Gets Physical: MIT Robot Plays Jenga!
There’s a lot more to a friendly game of Jenga than meets the eye. Strategies are informed by a complex set of tactile and visual stimuli — by touching a block and observing the tower, we not only see but also feel our actions and their consequences. The MIT Jenga robot thus marks an important step in AI’s transition to the physical world.
Tsinghua University Proves Quantum Supremacy on GANs
A recent publication has created quite a buzz in the quantum community: A Tsinghua University research paper has for the first time reported an experimental demonstration of quantum generative adversarial learning in a superconducting quantum circuit.
Global AI Events
Jan 27 – Feb 1, 2019 AAAI 2019: Association for the Advancement of Artificial Intelligence. Hawaii, United State
March 17 – 20, ACM IUI. Los Angeles, United States
Global AI Opportunities