Related papers: An implemented model of punning riddles
We explore the ability of large language models to solve and generate puzzles from the NPR Sunday Puzzle game show using PUZZLEQA, a dataset comprising 15 years of on-air puzzles. We evaluate four large language models using PUZZLEQA, in…
Large pre-trained language models (LMs) have been shown to perform surprisingly well when fine-tuned on tasks that require commonsense and world knowledge. However, in end-to-end architectures, it is difficult to explain what is the…
We propose a method for generating explainable rule sets from tree-ensemble learners using Answer Set Programming (ASP). To this end, we adopt a decompositional approach where the split structures of the base decision trees are exploited in…
When the inverse of an algorithm is well-defined -- that is, when its output can be deterministically transformed into the input producing it -- we say that the algorithm is invertible. While one can describe an invertible algorithm using a…
The subjective nature of humor makes computerized humor generation a challenging task. We propose an automatic humor generation framework for filling the blanks in Mad Libs stories, while accounting for the demographic backgrounds of the…
Recently, large language models such as GPT-2 have shown themselves to be extremely adept at text generation and have also been able to achieve high-quality results in many downstream NLP tasks such as text classification, sentiment…
Humor is prevalent in online communications and it often relies on more than one modality (e.g., cartoons and memes). Interpreting humor in multimodal settings requires drawing on diverse types of knowledge, including metaphorical,…
Natural Language Generation systems typically have two parts - strategic ('what to say') and tactical ('how to say'). We present our experiments in building an unsupervised corpus-driven template based tactical NLG system. We consider…
While subword tokenizers such as BPE and WordPiece are typically used to build vocabularies for NLP models, the method of decoding text into a sequence of tokens from these vocabularies is often left unspecified, or ill-suited to the method…
Thanks to the advanced improvement of large pre-trained language models, prompt-based fine-tuning is shown to be effective on a variety of downstream tasks. Though many prompting methods have been investigated, it remains unknown which type…
Recent advances in large language models (LLMs) have significantly enhanced question-answering (QA) capabilities, particularly in open-domain contexts. However, in closed-domain scenarios such as education, healthcare, and law, users demand…
Pre-trained language models (PLMs) fail to generate long-form narrative text because they do not consider global structure. As a result, the generated texts are often incohesive, repetitive, or lack content. Recent work in story generation…
Writers generally rely on plans or sketches to write long stories, but most current language models generate word by word from left to right. We explore coarse-to-fine models for creating narrative texts of several hundred words, and…
Large Language Models (LLMs) have demonstrated impressive performances in complex text generation tasks. However, the contribution of the input prompt to the generated content still remains obscure to humans, underscoring the necessity of…
Puns play a vital role in academic research due to their distinct structure and clear definition, which aid in the comprehensive analysis of linguistic humor. However, the understanding of puns in large language models (LLMs) has not been…
We study idiom-based visual puns--images that align an idiom's literal and figurative meanings--and present an iterative framework that coordinates a large language model (LLM), a text-to-image model (T2IM), and a multimodal LLM (MLLM) for…
This paper presents the Crowd Score, a novel method to assess the funniness of jokes using large language models (LLMs) as AI judges. Our method relies on inducing different personalities into the LLM and aggregating the votes of the AI…
Many recent prompting strategies for large language models (LLMs) query the model multiple times sequentially -- first to produce intermediate results and then the final answer. However, using these methods, both decoder and model are…
This paper presents a joint model for performing unsupervised morphological analysis on words, and learning a character-level composition function from morphemes to word embeddings. Our model splits individual words into segments, and…
Code-mixing is a phenomenon of mixing words and phrases from two or more languages in a single utterance of speech and text. Due to the high linguistic diversity, code-mixing presents several challenges in evaluating standard natural…