Pre-trained large language models (LLMs) have recently achieved better generalization and sample efficiency in autonomous web automation. However, the performance on real-world websites has still suffered from (1) open domainness, (2) limited context length, and (3) lack of inductive bias on HTML. We introduce WebAgent, an LLM-driven agent that learns from self-experience to complete tasks on real websites following natural language instructions. WebAgent plans ahead by decomposing instructions into canonical sub-instructions, summarizes long HTML documents into task-relevant snippets, and acts on websites via Python programs generated from those. We design WebAgent with Flan-U-PaLM, for grounded code generation, and HTML-T5, new pre-trained LLMs for long HTML documents using local and global attention mechanisms and a mixture of long-span denoising objectives, for planning and summarization. We empirically demonstrate that our modular recipe improves the success on real websites by over 50%, and that HTML-T5 is the best model to solve various HTML understanding tasks; achieving 18.7% higher success rate than the prior method on MiniWoB web automation benchmark, and SoTA performance on Mind2Web, an offline task planning evaluation.

In jazz, a contrafact is a new melody composed over an existing, but often reharmonized chord progression. Because reharmonization can introduce a wide range of variations, detecting contrafacts is a challenging task. This paper develops a novel vector-space model to represent chord progressions, and uses it for contrafact detection. The process applies principles from music theory to reduce the dimensionality of chord space, determine a common key signature representation, and compute a chordal co-occurrence matrix. The rows of the matrix form a basis for the vector space in which chord progressions are represented as piecewise linear functions, and harmonic similarity is evaluated by computing the membrane area, a novel distance metric. To illustrate our method's effectiveness, we apply it to the Impro-Visor corpus of 2,612 chord progressions, and present examples demonstrating its ability to account for reharmonizations and find contrafacts.

This content can also be viewed on the site it originates from. The salvage yard at M. Maselli & Sons, in Petaluma, California, is made up of six acres of angle irons, block pulleys, doorplates, digging tools, motors, fencing, tubing, reels, spools, and rusted machinery. To the untrained eye, the place is a testament to the enduring power of American detritus, but to Foley artists--craftspeople who create custom sound effects for film, television, and video games--it's a trove of potential props. On a recent morning, Shelley Roden and John Roesch, Foley artists who work at Skywalker Sound, the postproduction audio division of Lucasfilm, stood in the parking lot, considering the sonic properties of an enormous industrial hopper. "I'm looking for a resonator, and I need more ka-chunkers," Roden, who is blond and in her late forties, said.