Train and Constrain: Phonologically Informed Tongue Twister Generation from Topics and Paraphrases

T Loakman, C Tang, C Lin - Computational Linguistics, 2024 - direct.mit.edu
Previous work in phonologically and phonetically grounded language generation has
mainly focused on domains such as puns and poetry. In this article, we present new work on …

TwistList: Resources and baselines for tongue twister generation

T Loakman, C Tang, C Lin - arxiv preprint arxiv:2306.03457, 2023 - arxiv.org
Previous work in phonetically-grounded language generation has mainly focused on
domains such as lyrics and poetry. In this paper, we present work on the generation of …

CHARD: clinical health-aware reasoning across dimensions for text generation models

SY Feng, V Khetan, B Sacaleanu, A Gershman… - arxiv preprint arxiv …, 2022 - arxiv.org
We motivate and introduce CHARD: Clinical Health-Aware Reasoning across Dimensions,
to investigate the capability of text generation models to act as implicit clinical knowledge …

PINEAPPLE: Personifying INanimate entities by acquiring parallel personification data for learning enhanced generation

SS Keh, K Lu, V Gangal, SY Feng, H Jhamtani… - arxiv preprint arxiv …, 2022 - arxiv.org
A personification is a figure of speech that endows inanimate entities with properties and
actions typically seen as requiring animacy. In this paper, we explore the task of …