paper-with-me

홈 › Papers

Zero-shot topic generation

2020-04-29 · Oleg Vasilyev, Kathryn Evans, Anna Venancio-Marques, John Bohannon

We present an approach to generating topics using a model trained only for document title generation, with zero examples of topics given during training. We leverage features that capture the relevance of a candidate span in a document for the generation of a title for that document. The output is a weighted collection of the phrases that are most relevant for describing the document and distinguishing it within a corpus, without requiring access to the rest of the corpus. We conducted a double-blind trial in which human annotators scored the quality of our machine-generated topics along with original human-written topics associated with news articles from The Guardian and The Huffington Post. The results show that our zero-shot model generates topic labels for news documents that are on average equal to or higher quality than those written by humans, as judged by humans.

📄 PDF Abstract BibTeX arXiv:2004.13956

Code (0)

등록된 구현이 없습니다.

Tasks

Articles

Similar Papers 제목 키워드 기반

Assaying on the Robustness of Zero-Shot Machine-Generated Text Detectors

2023-12-20 · Yi-Fan Zhang, Zhang Zhang, Liang Wang, Tieniu Tan 외

To combat the potential misuse of Natural Language Generation (NLG) technology, a variety of algorithms have been developed for the detection of AI-generated texts. Traditionally, this task is treated as a binary classif…

Binary ClassificationText DetectionText Generation

Adversarial Learning for Zero-Shot Stance Detection on Social Media

2021-05-14 · NAACL 2021 4 · Emily Allaway, Malavika Srikanth, Kathleen McKeown

Stance detection on social media can help to identify and understand slanted news or commentary in everyday life. In this work, we propose a new model for zero-shot stance detection on Twitter that uses adversarial learn…

Stance DetectionZero-Shot Stance Detection

Zero-Shot Stance Detection using Contextual Data Generation with LLMs

2024-05-19 · Ghazaleh Mahmoudi, Babak Behkamkia, Sauleh Eetemadi

Stance detection, the classification of attitudes expressed in a text towards a specific topic, is vital for applications like fake news detection and opinion mining. However, the scarcity of labeled data remains a chall…

Fake News DetectionFew-Shot LearningOpinion MiningStance Detection+1

Zero-Shot Stance Detection: A Dataset and Model using Generalized Topic Representations

2020-10-07 · EMNLP 2020 11 · Emily Allaway, Kathleen McKeown

Stance detection is an important component of understanding hidden influences in everyday life. Since there are thousands of potential topics to take a stance on, most with little to no training data, we focus on zero-sh…

Stance DetectionZero-Shot Stance Detection

ZYN: Zero-Shot Reward Models with Yes-No Questions for RLAIF

2023-08-11 · Victor Gallego

In this work, we address the problem of directing the text generation of a language model (LM) towards a desired behavior, aligning the generated text with the preferences of the human operator. We propose using another,…

AttributeDiversityLanguage ModelingLanguage Modelling+1