AI News, nicholaslocascio/deep-regex

nicholaslocascio/deep-regex

Our neural model translates natural language queries into regular expressions which embody their meaning.

We also present a methodology for collecting a large corpus of regular expression, natural language pairs using Mechanical Turk and grammar generation.

pip install -r requirements.txt Datasets are provided in 3 folders within /datasets/: KB13, NL-RX-Synth, NL-RX-Turk.

The data is a parallel corpus, so the folder is split into 2 files: src.txt and targ.txt.

Anna Rohrbach: Grounding and Generation of Natural Language Descriptions for Images and Videos

Anna Rohrbach Grounding and Generation of Natural Language Descriptions for Images and Videos Abstract: In recent years many challenging problems have emerged in the field of language and...

Lecture 16: Dynamic Neural Networks for Question Answering

Lecture 16 addresses the question ""Can all NLP tasks be seen as question answering problems?"". Key phrases: Coreference Resolution, Dynamic Memory Networks for Question Answering over Text...

A Joint Speaker-Listener-Reinforcer Model for Referring Expressions | Spotlight 2-2C

Licheng Yu; Hao Tan; Mohit Bansal; Tamara L. Berg Referring expressions are natural language constructions used to identify particular objects within a scene. In this paper, we propose a unified...

Elder in the Making | Episode 1: Cowboy X

Cowboy, a Blackfoot aboriginal and Chris, a Chinese-Canadian, agree to go on roadtrip across traditional Blackfoot territory rediscover the stories of their shared home. ---------------------------...

David Soares Batista - Semi-Supervised Bootstrapping of Relationship Extractors

Semi-Supervised Bootstrapping of Relationship Extractors with Distributional Semantics by David Soares Batista Description Semi-supervised bootstrapping techniques for relationship extraction...

The Zipf Mystery

The of and to. A in is I. That it, for you, was with on. As have ... but be they. RELATED LINKS AND SOURCES BELOW!

Lecture 8: Recurrent Neural Networks and Language Models

Lecture 8 covers traditional language models, RNNs, and RNN language models. Also reviewed are important training problems and tricks, RNNs for other sequence tasks, and bidirectional and deep...

Lecture 3 | GloVe: Global Vectors for Word Representation

Lecture 3 introduces the GloVe model for training word vectors. Then it extends our discussion of word vectors (interchangeably called word embeddings) by seeing how they can be evaluated intrinsic...

Tlingit Music--Past, Present and Future: Ed Littlefield at TEDxSitka

Ed Littlefield is a Tlingit Native of Southeast Alaska currently working on composing and arranging Native music from the Tlingit tradition. He studied percussion at the University of Idaho...

Adam Beach Introduction in movie/play "Kigeet"

Adam Beach Introduction in movie/play "Kigeet"