Systems and methods for unsupervised autoregressive text compression
US11487939B2 · kind B2 · utility
0Cited by
6References
18Claims
0Family size
Assignee
Inventors
Key dates
| Filing date | Aug 23, 2019 |
| Grant date | Nov 1, 2022 |
| Priority date | — |
| Expiry date | Feb 10, 2040 |
Classification
- Technology area (CPC H)Electricity
- CPC primaryH03M7/3059
- WIPO fieldBasic communication processes
- WIPO sectorElectrical engineering
Abstract
Embodiments described herein provide a provide a fully unsupervised model for text compression. Specifically, the unsupervised model is configured to identify an optimal deletion path for each input sequence of texts (e.g., a sentence) and words from the input sequence are gradually deleted along the deletion path. To identify the optimal deletion path, the unsupervised model may adopt a pretrained bidirectional language model (BERT) to score each candidate deletion based on the average perplexity of the resulting sentence and performs a simple greedy look-ahead tree search to select the best deletion for each step.
Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.