|
|
|
ProphetNet |
|
|
|
Overview |
|
The ProphetNet model was proposed in ProphetNet: Predicting Future N-gram for Sequence-to-Sequence Pre-training, by Yu Yan, Weizhen Qi, Yeyun Gong, Dayiheng Liu, Nan Duan, Jiusheng Chen, Ruofei |
|
Zhang, Ming Zhou on 13 Jan, 2020. |
|
ProphetNet is an encoder-decoder model and can predict n-future tokens for "ngram" language modeling instead of just |
|
the next token. |
|
The abstract from the paper is the following: |
|
In this paper, we present a new sequence-to-sequence pretraining model called ProphetNet, which introduces a novel |
|
self-supervised objective named future n-gram prediction and the proposed n-stream self-attention mechanism. Instead of |
|
the optimization of one-step ahead prediction in traditional sequence-to-sequence model, the ProphetNet is optimized by |
|
n-step ahead prediction which predicts the next n tokens simultaneously based on previous context tokens at each time |
|
step. The future n-gram prediction explicitly encourages the model to plan for the future tokens and prevent |
|
overfitting on strong local correlations. We pre-train ProphetNet using a base scale dataset (16GB) and a large scale |
|
dataset (160GB) respectively. Then we conduct experiments on CNN/DailyMail, Gigaword, and SQuAD 1.1 benchmarks for |
|
abstractive summarization and question generation tasks. Experimental results show that ProphetNet achieves new |
|
state-of-the-art results on all these datasets compared to the models using the same scale pretraining corpus. |
|
The Authors' code can be found here. |
|
Usage tips |
|
|
|
ProphetNet is a model with absolute position embeddings so it's usually advised to pad the inputs on the right rather than |
|
the left. |
|
The model architecture is based on the original Transformer, but replaces the “standard” self-attention mechanism in the decoder by a a main self-attention mechanism and a self and n-stream (predict) self-attention mechanism. |
|
|
|
Resources |
|
|
|
Causal language modeling task guide |
|
Translation task guide |
|
Summarization task guide |
|
|
|
ProphetNetConfig |
|
[[autodoc]] ProphetNetConfig |
|
ProphetNetTokenizer |
|
[[autodoc]] ProphetNetTokenizer |
|
ProphetNet specific outputs |
|
[[autodoc]] models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqLMOutput |
|
[[autodoc]] models.prophetnet.modeling_prophetnet.ProphetNetSeq2SeqModelOutput |
|
[[autodoc]] models.prophetnet.modeling_prophetnet.ProphetNetDecoderModelOutput |
|
[[autodoc]] models.prophetnet.modeling_prophetnet.ProphetNetDecoderLMOutput |
|
ProphetNetModel |
|
[[autodoc]] ProphetNetModel |
|
- forward |
|
ProphetNetEncoder |
|
[[autodoc]] ProphetNetEncoder |
|
- forward |
|
ProphetNetDecoder |
|
[[autodoc]] ProphetNetDecoder |
|
- forward |
|
ProphetNetForConditionalGeneration |
|
[[autodoc]] ProphetNetForConditionalGeneration |
|
- forward |
|
ProphetNetForCausalLM |
|
[[autodoc]] ProphetNetForCausalLM |
|
- forward |