Data augmentation has been an important ingredient for boosting performances of learned models. Prior data augmentation methods for few-shot text classification have led to great performance boosts. However, they have not been designed to capture the intricate compositional structure of natural language. As a result, they fail to generate samples with plausible and diverse sentence structures. Motivated by this, we present the data Augmentation using Lexicalized Probabilistic context-free grammars (ALP) that generates augmented samples with diverse syntactic structures with plausible grammar. The lexicalized PCFG parse trees consider both the constituents and dependencies to produce a syntactic frame that maximizes a variety of word choices in a syntactically preservable manner without specific domain experts. Experiments on few-shot text classification tasks demonstrate that ALP enhances many state-of-the-art classification methods. As a second contribution, we delve into the train-val splitting methodologies when a data augmentation method comes into play. We argue empirically that the traditional splitting of training and validation sets is sub-optimal compared to our novel augmentation-based splitting strategies that further expand the training split with the same number of labeled data. Taken together, our contributions on the data augmentation strategies yield a strong training recipe for few-shot text classification tasks.

Entity resolution is a widely studied problem with several proposals to match records across relations. Matching textual content is a widespread task in many applications, such as question answering and search. While recent methods achieve promising results for these two tasks, there is no clear solution for the more general problem of matching textual content and structured data. We introduce a framework that supports this new task in an unsupervised setting for any pair of corpora, being relational tables or text documents. Our method builds a fine-grained graph over the content of the corpora and derives word embeddings to represent the objects to match in a low dimensional space. The learned representation enables effective and efficient matching at different granularity, from relational tuples to text sentences and paragraphs. Our flexible framework can exploit pre-trained resources, but it does not depends on their existence and achieves better quality performance in matching content when the vocabulary is domain specific. We also introduce optimizations in the graph creation process with an "expand and compress" approach that first identifies new valid relationships across elements, to improve matching, and then prunes nodes and edges, to reduce the graph size. Experiments on real use cases and public datasets show that our framework produces embeddings that outperform word embeddings and fine-tuned language models both in results' quality and in execution times.

The technological standards of photography have dramatically increased over the last few years. While cell phones used to not even have photo capture capabilities, nowadays, it is becoming more and more expected that modern smartphones can take pictures of a quality close to that of a dedicated camera. The computer vision community has recently focused on assessing image aesthetics for image cropping and learning systems for capturing cinematographic videos. In other words, researchers are asking themselves if robots can understand and capture aesthetically pleasing imagery. However, these systems often focus on composing specific objects of interest into the photo by using composition heuristics, like the rule of thirds, and do not translate directly to a system that can capture well-composed photographs in general.

Why do we mistake computer generated poems as the work of humans? From Wordsworth's "spontaneous overflow of powerful feelings" to Eavan Boland's "figure in which secret things confide," poetry is often defined by -- and extolled for -- its ability to convey human emotion. What, then, does it mean that we can not distinguish poems penned by humans from those generated by machine? Indeed, researchers Nils Köbis and Luca D.Mossink at the University of Amsterdam have found that humans cannot tell AI-generated poems from those written by amateur poets, or by well known professionals, provided a human selects the best poem from a set of machine-generated verses to compare. Have machines become as talented as our poets?

For this project we are using The Million Playlist Dataset (MPD) released by Spotify. As it name implies, the dataset consists of one million playlists and each playlists contains n number of songs and additional metadata is included as well such as title of the playlist, duration, number of songs, number of artists, etc. This dataset was created by sampling playlists from the billions of playlists that Spotify users have created over the years.

WHAT with everything that has happened this year, I have found myself at home watching the box more often than usual. That was especially true recently when I was laid up in bed for three weeks with covid-19. I spent my time largely watching my favourite genre of film: science fiction. This has made me realise how surprisingly often my main passion – plants – plays a vital role in the plot of such films. And so, as 2021 draws to an end, I offer you my essential analysis of the botanical accuracy of a selection of sci-fi films.

The SCALE AI Research Chair in Artificial Intelligence for Urban Mobility and Logistics, at HEC Montréal, held by Professor Carolina Osorio;; The …

Musiio, an artificial intelligence brand for the music industry, has a revolutionary Hit Potential Algorithm that analyzes music at scale and awards scores between 0 to 100. The algorithm score depends on the likelihood of commercial success. Utilizing this technology to songs in pre-production made it possible to create a second-by-second track analysis. To know more, read further and know AI curator for the music industry and how Hit potential algorithm helps to discover the next smash. The readouts done using the Hit potential algorithm allow a data-driven creative process to take place.

This video is a recap of our June 2019 EMEA TWiML Online Meetup: MeshCNN: A Network with an Edge. In this month's community segment, we discuss the Imagenet-trained CNNs are biased towards texture article and the Open-sourcing Ax and Bo Torch article. In our presentation segment, Rana Hanocka presents on a method for employing neural networks on irregular triangular meshes with the MeshCNN: A Network with an Edge paper by Rana Hanocka et al. For links to the papers, podcasts, and more mentioned above or during this meetup, for more information on previous meetups, or to get registered for upcoming meetups, visit twimlai.com/meetup!

When tasking AI with writing a story, more coherent plots can be created by prompting it to write a story backwards, starting from an ending. In previous work, AI has been capable of taking an opening paragraph and use it to generate a whole story, sentence by sentence, by applying patterns gleaned from vast amounts of training data. But this approach can quickly wander into incoherence as the length of the story increases.