相关论文: Pun Generation with Surprise

Unsupervised approaches to extractive summarization usually rely on a notion of sentence importance defined by the semantic similarity between a sentence and the document. We propose new metrics of relevance and redundancy using pointwise…

Generic generation and manipulation of text is challenging and has limited success compared to recent deep generative modeling in visual domain. This paper aims at generating plausible natural language sentences, whose attributes are…

Stories generated with neural language models have shown promise in grammatical and stylistic consistency. However, the generated stories are still lacking in common sense reasoning, e.g., they often contain sentences deprived of world…

The article describes a model of automatic analysis of puns, where a word is intentionally used in two meanings at the same time (the target word). We employ Roget's Thesaurus to discover two groups of words which, in a pun, form around two…

Generating paragraphs of diverse contents is important in many applications. Existing generation models produce similar contents from homogenized contexts due to the fixed left-to-right sentence order. Our idea is permuting the sentence…

Gender bias is a frequent occurrence in NLP-based applications, especially pronounced in gender-inflected languages. Bias can appear through associations of certain adjectives and animate nouns with the natural gender of referents, but also…

Generative AI models face the challenge of hallucinations that can undermine users' trust in such systems. We approach the problem of conversational information seeking as a two-step process, where relevant passages in a corpus are…

Natural language is compositional; the meaning of a sentence is a function of the meaning of its parts. This property allows humans to create and interpret novel sentences, generalizing robustly outside their prior experience. Neural…

In conversation, speakers produce language incrementally, word by word, while continuously monitoring the appropriateness of their own contribution in the dynamically unfolding context of the conversation; and this often leads them to…

Keyphrase generation is the task of automatically predicting keyphrases given a piece of long text. Despite its recent flourishing, keyphrase generation on non-English languages haven't been vastly investigated. In this paper, we call…

Generative Adversarial Networks (GAN) is a model for data synthesis, which creates plausible data through the competition of generator and discriminator. Although GAN application to image synthesis is extensively studied, it has inherent…

Natural Language Inference Generation task is to generate a text hypothesis given a text premise and a logical relation between the two. This task can be used in data augmentation and controllable text generation in practice. In this paper,…

Online hate speech poses a serious threat to individual well-being and societal cohesion. A promising solution to curb online hate speech is counterspeech. Counterspeech is aimed at encouraging users to reconsider hateful posts by direct…

Headline generation is a special type of text summarization task. While the amount of available training data for this task is almost unlimited, it still remains challenging, as learning to generate headlines for news articles implies that…

We introduce a novel data generation method for contradiction detection, which leverages the generative power of large language models as well as linguistic rules. Our vision is to provide a condensed corpus of prototypical contradictions,…

We propose a method for natural language generation, choosing the most representative output rather than the most likely output. By viewing the language generation process from the voting theory perspective, we define representativeness…

Automated story generation is the problem of automatically selecting a sequence of events, actions, or words that can be told as a story. We seek to develop a system that can generate stories by learning everything it needs to know from…

Current large language models (LLMs) can exhibit near-human levels of performance on many natural language-based tasks, including open-domain question answering. Unfortunately, at this time, they also convincingly hallucinate incorrect…

We propose GRS: an unsupervised approach to sentence simplification that combines text generation and text revision. We start with an iterative framework in which an input sentence is revised using explicit edit operations, and add…

A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through…