8 papers
Embedding-based Scientific Literature Discovery in a Text Editor Application
Onur Gökçe, Jonathan Prada, Nikola I. Nikolov +2
Each claim in a research paper requires all relevant prior knowledge to be discovered, assimilated, and appropriately cited. However, despite the availability of powerful search en…
Character-Level Translation with Self-attention
Yingqiang Gao, Nikola I. Nikolov, Yuhuang Hu +1
We explore the suitability of self-attention models for character-level neural machine translation. We test the standard transformer model, as well as a novel variant in which the…
Rapformer: Conditional Rap Lyrics Generation with Denoising Autoencoders
Nikola I. Nikolov, Eric Malmi, Curtis G. Northcutt +1
The ability to combine symbols to generate language is a defining characteristic of human intelligence, particularly in the context of artistic story-telling through lyrics. We dev…
Summary Refinement through Denoising
Nikola I. Nikolov, Alessandro Calmanovici, Richard H. R. Hahnloser
We propose a simple method for post-processing the outputs of a text summarization system in order to refine its overall quality. Our approach is to train text-to-text rewriting mo…
Abstractive Document Summarization without Parallel Data
Nikola I. Nikolov, Richard H. R. Hahnloser
Abstractive summarization typically relies on large collections of paired articles and summaries. However, in many cases, parallel data is scarce and costly to obtain. We develop a…
Large-scale Hierarchical Alignment for Data-driven Text Rewriting
Nikola I. Nikolov, Richard H. R. Hahnloser
We propose a simple unsupervised method for extracting pseudo-parallel monolingual sentence pairs from comparable corpora representative of two different text styles, such as news…