Search Results for author: Allen Roush

Found 6 papers, 4 papers with code

LLM as an Art Director (LaDi): Using LLMs to improve Text-to-Media Generators

no code implementations7 Nov 2023 Allen Roush, Emil Zakirov, Artemiy Shirokov, Polina Lunina, Jack Gane, Alexander Duffy, Charlie Basil, Aber Whitcomb, Jim Benedetto, Chris DeWolfe

Recent advancements in text-to-image generation have revolutionized numerous fields, including art and cinema, by automating the generation of high-quality, context-aware images and video.

Retrieval Text-to-Image Generation +1

DebateKG: Automatic Policy Debate Case Creation with Semantic Knowledge Graphs

1 code implementation9 Jul 2023 Allen Roush, David Mezzetti

We leverage the txtai semantic search and knowledge graph toolchain to produce and contribute 9 semantic knowledge graphs built on this dataset.

Argument Mining Knowledge Graphs

Most Language Models can be Poets too: An AI Writing Assistant and Constrained Text Generation Studio

1 code implementation CAI (COLING) 2022 Allen Roush, Sanjay Basu, Akshay Moorthy, Dmitry Dubovoy

We present a simple and universally applicable technique for modifying the output of a language model by compositionally applying filter functions to the language models vocabulary before a unit of text is generated.

Language Modelling Text Generation

CX DB8: A queryable extractive summarizer and semantic search engine

2 code implementations7 Dec 2020 Allen Roush

Competitive Debate's increasingly technical nature has left competitors looking for tools to accelerate evidence production.

Extractive Summarization Extractive Text Summarization +1

DebateSum: A large-scale argument mining and summarization dataset

3 code implementations COLING (ArgMining) 2020 Allen Roush, Arvind Balaji

Finally, we present a search engine for this dataset which is utilized extensively by members of the National Speech and Debate Association today.

Abstractive Text Summarization Argument Mining +4

Cannot find the paper you are looking for? You can Submit a new open access paper.