search

Yale-LILY / SummerTime

An open-source text summarization toolkit for non-experts. EMNLP'2021 Demo
https://arxiv.org/abs/2108.12738
Apache License 2.0
269 stars 30 forks source link

Speed up hmnet inference #52

Closed yszh8 closed 3 years ago

yszh8 commented 3 years ago

Add parameters in hmnet model, i.e. model = HMNetModel(max_gen_length=100, beam_width=2) will greatly decrease the inference time cost.

niansong1996 commented 3 years ago

@chatc Can you add some comments on what's the typical setting and what speed should people expect.