HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge

• URL: http://arxiv.org/abs/2109.05097v1
• Date: Fri, 10 Sep 2021 20:19:52 GMT
• Title: HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge
• Authors: Yufei Tian, Arvind krishna Sridhar, and Nanyun Peng
• Abstract summary: A hyperbole is an intentional and creative exaggeration not to be taken literally. We tackle the under-explored and challenging task of sentence-level hyperbole generation. Our generation method is able to generate hyperboles creatively with high success rate and intensity scores.
• Score: 11.93269712166532
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: A hyperbole is an intentional and creative exaggeration not to be taken literally. Despite its ubiquity in daily life, the computational explorations of hyperboles are scarce. In this paper, we tackle the under-explored and challenging task: sentence-level hyperbole generation. We start with a representative syntactic pattern for intensification and systematically study the semantic (commonsense and counterfactual) relationships between each component in such hyperboles. Next, we leverage the COMeT and reverse COMeT models to do commonsense and counterfactual inference. We then generate multiple hyperbole candidates based on our findings from the pattern, and train neural classifiers to rank and select high-quality hyperboles. Automatic and human evaluations show that our generation method is able to generate hyperboles creatively with high success rate and intensity scores.

Related papers

• Hyperbolic Delaunay Geometric Alignment [52.835250875177756]
  We propose a similarity score for comparing datasets in a hyperbolic space. The core idea is counting the edges of the hyperbolic Delaunay graph connecting datapoints across the given sets. We provide an empirical investigation on synthetic and real-life biological data and demonstrate that HyperDGA outperforms the hyperbolic version of classical distances between sets.
  arXiv  Detail & Related papers  (2024-04-12T17:14:58Z)
• Hyperbolic vs Euclidean Embeddings in Few-Shot Learning: Two Sides of the Same Coin [49.12496652756007]
  We show that the best few-shot results are attained for hyperbolic embeddings at a common hyperbolic radius. In contrast to prior benchmark results, we demonstrate that better performance can be achieved by a fixed-radius encoder equipped with the Euclidean metric.
  arXiv  Detail & Related papers  (2023-09-18T14:51:46Z)
• Image Matters: A New Dataset and Empirical Study for Multimodal Hyperbole Detection [52.04083398850383]
  We create a multimodal detection dataset from Weibo (a Chinese social media) We treat the text and image from a piece of weibo as two modalities and explore the role of text and image for hyperbole detection. Different pre-trained multimodal encoders are also evaluated on this downstream task to show their performance.
  arXiv  Detail & Related papers  (2023-07-01T03:23:56Z)
• A Match Made in Heaven: A Multi-task Framework for Hyperbole and Metaphor Detection [27.85834441076481]
  Hyperbole and metaphor are common in day-to-day communication. Existing approaches to automatically detect metaphor and hyperbole have studied these language phenomena independently. We propose a multi-task deep learning framework to detect hyperbole and metaphor simultaneously.
  arXiv  Detail & Related papers  (2023-05-27T14:17:59Z)
• HRCF: Enhancing Collaborative Filtering via Hyperbolic Geometric Regularization [52.369435664689995]
  We introduce a textitHyperbolic Regularization powered Collaborative Filtering (HRCF) and design a geometric-aware hyperbolic regularizer. Specifically, the proposal boosts optimization procedure via the root alignment and origin-aware penalty. Our proposal is able to tackle the over-smoothing problem caused by hyperbolic aggregation and also brings the models a better discriminative ability.
  arXiv  Detail & Related papers  (2022-04-18T06:11:44Z)
• Enhancing Hyperbolic Graph Embeddings via Contrastive Learning [7.901082408569372]
  We propose a novel Hyperbolic Graph Contrastive Learning (HGCL) framework which learns node representations through multiple hyperbolic spaces. Experimental results on multiple real-world datasets demonstrate the superiority of the proposed HGCL.
  arXiv  Detail & Related papers  (2022-01-21T06:10:05Z)
• MOVER: Mask, Over-generate and Rank for Hyperbole Generation [82.63394952538292]
  We introduce a new task of hyperbole generation to transfer a literal sentence into its hyperbolic paraphrase. We construct HYPO-XL, the first large-scale hyperbole corpus containing 17,862 hyperbolic sentences in a non-trivial way. Based on our corpus, we propose an unsupervised method for hyperbole generation with no need for parallel literal-hyperbole pairs.
  arXiv  Detail & Related papers  (2021-09-16T05:25:13Z)
• Fully Hyperbolic Neural Networks [63.22521652077353]
  We propose a fully hyperbolic framework to build hyperbolic networks based on the Lorentz model. We show that our method has better performance for building both shallow and deep networks.
  arXiv  Detail & Related papers  (2021-05-31T03:36:49Z)
• Unsupervised Hyperbolic Representation Learning via Message Passing Auto-Encoders [29.088604461911892]
  In this paper, we analyze how unsupervised tasks can benefit from learned representations in hyperbolic space. To explore how well the hierarchical structure of unlabeled data can be represented in hyperbolic spaces, we design a novel hyperbolic message passing auto-encoder. The proposed model conducts auto-encoding the networks via fully utilizing hyperbolic geometry in message passing.
  arXiv  Detail & Related papers  (2021-03-30T03:09:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.