A survey on automatic generation of figurative language: From rule-based systems to large language models
Figurative language generation (FLG) is the task of reformulating a given text to include a
desired figure of speech, such as a hyperbole, a simile, and several others, while still being …
desired figure of speech, such as a hyperbole, a simile, and several others, while still being …
Ambipun: Generating humorous puns with ambiguous context
In this paper, we propose a simple yet effective way to generate pun sentences that does not
require any training on existing puns. Our approach is inspired by humor theories that …
require any training on existing puns. Our approach is inspired by humor theories that …
Can Language Models Make Fun? A Case Study in Chinese Comical Crosstalk
Artificial Intelligence (AI) has been widely used in Natural Language Processing (NLP),
computer vision, speech, robots, and further applied biology, etc. In NLP, Pre-trained …
computer vision, speech, robots, and further applied biology, etc. In NLP, Pre-trained …
The iron (ic) melting pot: Reviewing human evaluation in humour, irony and sarcasm generation
Human evaluation is often considered to be the gold standard method of evaluating a
Natural Language Generation system. However, whilst its importance is accepted by the …
Natural Language Generation system. However, whilst its importance is accepted by the …
Context-situated pun generation
Previous work on pun generation commonly begins with a given pun word (a pair of
homophones for heterographic pun generation and a polyseme for homographic pun …
homophones for heterographic pun generation and a polyseme for homographic pun …
MOVER: Mask, over-generate and rank for hyperbole generation
Despite being a common figure of speech, hyperbole is under-researched in Figurative
Language Processing. In this paper, we tackle the challenging task of hyperbole generation …
Language Processing. In this paper, we tackle the challenging task of hyperbole generation …
A unified framework for pun generation with humor principles
We propose a unified framework to generate both homophonic and homographic puns to
resolve the split-up in existing works. Specifically, we incorporate three linguistic attributes of …
resolve the split-up in existing works. Specifically, we incorporate three linguistic attributes of …
ExPUNations: Augmenting puns with keywords and explanations
The tasks of humor understanding and generation are challenging and subjective even for
humans, requiring commonsense and real-world knowledge to master. Puns, in particular …
humans, requiring commonsense and real-world knowledge to master. Puns, in particular …
Systematicity in GPT-3's Interpretation of Novel English Noun Compounds
Levin et al.(2019) show experimentally that the interpretations of novel English noun
compounds (eg, stew skillet), while not fully compositional, are highly predictable based on …
compounds (eg, stew skillet), while not fully compositional, are highly predictable based on …
Inducing character-level structure in subword-based language models with type-level interchange intervention training
Language tasks involving character-level manipulations (eg, spelling corrections, arithmetic
operations, word games) are challenging for models operating on subword units. To …
operations, word games) are challenging for models operating on subword units. To …