Papers by Nikola I. Nikolov
Embedding-based Scientific Literature Discovery in a Text Editor Application (2020.acl-demos)
Copied to clipboard
| Challenge: | Despite the availability of powerful search engines and text editing software, discovering relevant papers and integrating the knowledge into a manuscript remain complex tasks associated with high cognitive load. |
| Approach: | They propose to combine text editing and literature discovery in an interactive user interface with a search engine that couples Boolean keyword filtering with nearest neighbor search over text embeddings. |
| Outcome: | The proposed application combines text editing and literature discovery in an interactive user interface. |
Abstractive Document Summarization without Parallel Data (2020.lrec-1)
Copied to clipboard
| Challenge: | Abstractive summarization typically relies on large collections of paired articles and summaries. |
| Approach: | They propose a system that relies only on example summaries and non-matching articles . they use an unsupervised sentence extractor that selects salient sentences . |
| Outcome: | The proposed system performs well on CNN/DailyMail benchmark and automatic generating a press release from a scientific journal article. |
Character-Level Translation with Self-attention (2020.acl-main)
Copied to clipboard
| Challenge: | Existing models for character-level neural machine translation operate on word-level, which makes them memory inefficient because of large vocabulary sizes. |
| Approach: | They propose a transformer-based model and a novel variant that uses convolutions to combine information from nearby characters to facilitate character interactions. |
| Outcome: | The proposed model outperforms the standard transformer model and learns more robust character alignments on bilingual and multilingual translation datasets. |