Псевдодеректер
material
ID: pseudodata
Related Papers
Stronger Baselines for Grammatical Error Correction Using a Pretrained Encoder-Decoder Model
AbstractStudies on grammatical error correction (GEC) have reported on the effectiveness of pretraining a Seq2Seq model with a large amount of pseudodata. However, this approach requires time-consuming pretraining of GEC …...
Fine-grained Entity Typing without Knowledge Base
AbstractExisting work on Fine-grained Entity Typing (FET) typically trains automatic models on the datasets obtained by using Knowledge Bases (KB) as distant supervision. However, the reliance on KB means this …...
NJUNLP’s Participation for the WMT2022 Quality Estimation Shared Task
AbstractThis paper presents submissions of the NJUNLP team in WMT 2022Quality Estimation shared task 1, where the goal is to predict the sentence-level and word-level quality for target machine translations. …...