Predictor-Estimator using Multilevel Task Learning with Stack Propagation for Neural Quality Estimation

By Hyun Kim, Jong-Hyeok Lee, Seung-Hoon Na. 2017

145 citations recorded by the source corpus.

In this paper, we present a two-stage neural quality estimation model that uses multilevel task learning for translation quality estimation (QE) at the sentence, word, and phrase levels. Our approach is based on an end-to-end stacked neural model named Predictor-Estimator , which has two stages consisting of a neural word prediction model and neural QE model. To efﬁciently train the two-stage model, a stack propagation method is applied, thereby enabling us to jointly learn the word prediction model and QE model in a single learning mode. In addition, we deploy multilevel task learning with stack propagation, where the training examples available for all QE subtasks (i.e., sentence/word/phrase levels) are used to train a Predictor-Estimator for a speciﬁc sub-task. All of our submissions to the QE task of WMT17 are ensembles that combine a set of neural models trained under different settings of varying dimensionali-ties and shufﬂing training examples, eventually achieving the best performances for all subtasks at the sentence, word, and phrase levels.

Subfields: Artificial Intelligence, Natural Language Processing, Machine Translation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Natural Language Processing

In Machine Translation

Citations in the corpus

Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning (2018, methodology): “, 2017) and (Kim et al., 2017) are unsuitable for the direct use in this task since they rely on linguistic input features, stacked architecFigure 1: Rating interface for 5-point ratings.”
Findings of the 2017 Conference on Machine Translation (WMT17) (2017, methodology): “POSTECH (T1, T2, T3): POSTECH’s submissions to the sentence/word/phrase-level QE tasks are based on predictor-estimator architecture (Kim et al., 2017; Kim and Lee, 2016), which is the two-stage end-to-end ID Participating team CDACM Centre for Development of Advanced Computing, India (Patel and M,…”
Membership Inference Attacks on Sequence-to-Sequence Models: Is My Data In Your Machine Translation System? (2019, methodology): “We applied the Predictor-Estimator (Kim et al., 2017) implemented in an open source QE framework OpenKiwi (Kepler et al.”
Unsupervised Quality Estimation for Neural Machine Translation (2020, methodology): “We used publicly available MT datasets such as Paracrawl (Es-plà et al., 2019) and Europarl (Koehn, 2005).”