CLAILGJun 28, 2023

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

arXiv:2306.15926v1586 citationsh-index: 3Has Code
Originality Incremental advance
AI Analysis

This work provides a tool for users needing creative text generation under specific constraints, such as writers or educators, but it is incremental as it builds on existing language model capabilities.

The paper tackles the problem of constrained natural language generation by introducing a plug-and-play technique that applies filter functions to a language model's vocabulary, enabling compelling text generation under lexical, semantic, or phonetic constraints. It demonstrates superior performance compared to fine-tuning alone on a novel dataset of prose omitting the letter 'e'.

Despite rapid advancement in the field of Constrained Natural Language Generation, little time has been spent on exploring the potential of language models which have had their vocabularies lexically, semantically, and/or phonetically constrained. We find that most language models generate compelling text even under significant constraints. 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. This approach is plug-and-play and requires no modification to the model. To showcase the value of this technique, we present an easy to use AI writing assistant called Constrained Text Generation Studio (CTGS). CTGS allows users to generate or choose from text with any combination of a wide variety of constraints, such as banning a particular letter, forcing the generated words to have a certain number of syllables, and/or forcing the words to be partial anagrams of another word. We introduce a novel dataset of prose that omits the letter e. We show that our method results in strictly superior performance compared to fine-tuning alone on this dataset. We also present a Huggingface space web-app presenting this technique called Gadsby. The code is available to the public here: https://github.com/Hellisotherpeople/Constrained-Text-Generation-Studio

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes