ПЕГАСУС
Related Papers
PEGASUS: A Spoken Language Interface for On-Line Air Travel Planning
This paper describes PEGASUS, a spoken language inter- face for on-line air travel planning that we have recently devel- oped. PEGASUS leverages off our spoken language technology development in the …...
Flight of the PEGASUS? Comparing Transformers on Few-shot and Zero-shot Multi-document Abstractive Summarization
AbstractRecent work has shown that pre-trained Transformers obtain remarkable performance on many natural language processing tasks including automatic summarization. However, most work has focused on (relatively) data-rich single-document summarization settings. …...
Effective Sequence-to-Sequence Dialogue State Tracking
AbstractSequence-to-sequence models have been applied to a wide variety of NLP tasks, but how to properly use them for dialogue state tracking has not been systematically investigated. In this paper, …...
Noobs at Semeval-2021 Task 4: Masked Language Modeling for abstract answer prediction
AbstractThis paper presents the system developed by our team for Semeval 2021 Task 4: Reading Comprehension of Abstract Meaning. The aim of the task was to benchmark the NLP techniques …...
Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents
AbstractWe argue that disentangling content selection from the budget used to cover salient content improves the performance and applicability of abstractive summarizers. Our method, FactorSum, does this disentanglement by factorizing …...
FactPEGASUS: Factuality-Aware Pre-training and Fine-tuning for Abstractive Summarization
AbstractWe present FactPEGASUS, an abstractive summarization model that addresses the problem of factuality during pre-training and fine-tuning: (1) We augment the sentence selection strategy of PEGASUS’s (Zhang et al., 2019) …...
When and how to paraphrase for named entity recognition?
AbstractWhile paraphrasing is a promising approach for data augmentation in classification tasks, its effect on named entity recognition (NER) is not investigated systematically due to the difficulty of span-level label …...