DeepAI AI Chat
Log In Sign Up

Zero-shot topic generation

by   Oleg Vasilyev, et al.

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.


Headline Generation: Learning from Decomposable Document Titles

We propose a novel method for generating titles for unstructured text do...

Headline Generation: Learning from Decomposed Document Titles

We propose a novel method for generating titles for unstructured text do...

KPDrop: An Approach to Improving Absent Keyphrase Generation

Keyphrase generation is the task of generating phrases (keyphrases) that...

Automatic Generation of Topic Labels

Topic modelling is a popular unsupervised method for identifying the und...

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

Stance detection is an important component of understanding hidden influ...

Cross-lingual Contextualized Topic Models with Zero-shot Learning

Many data sets in a domain (reviews, forums, news, etc.) exist in parall...

OpenStance: Real-world Zero-shot Stance Detection

Prior studies of zero-shot stance detection identify the attitude of tex...