Сжатие
Related Papers
Subtree Extractive Summarization via Submodular Maximization
This study proposes a text summarization model that simultaneously performs sen- tence extraction and compression. We translate the text summarization task into a problem of extracting a set of depen- …...
Learning Succinct Models: Pipelined Compression with L1-Regularization, Hashing, Elias-Fano Indices, and Quantization
AbstractThe recent proliferation of smart devices necessitates methods to learn small-sized models. This paper demonstrates that if there are m features in total but only n = o(√m) features are …...
Scoring Sentence Singletons and Pairs for Abstractive Summarization
AbstractWhen writing a summary, humans tend to choose content from one or two sentences and merge them into a single summary sentence. However, the mechanisms behind the selection of one …...
Compression, Transduction, and Creation: A Unified Framework for Evaluating Natural Language Generation
AbstractNatural language generation (NLG) spans a broad range of tasks, each of which serves for specific objectives and desires different properties of generated text. The complexity makes automatic evaluation of …...
MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers
We generalize deep self-attention distillation in MINILM (Wang et al., 2020) by only us- ing self-attention relation distillation for task- agnostic compression of pretrained Transform- ers. In particular, we define …...