ListNet-based MT Rescoring

Abstract

The log-linear combination of different features is an important component of SMT systems. It allows for the easy integartion of models into the system and is used during decoding as well as for nbest list rescoring. With the recent success of more complex models like neural network-based translation models, n-best list rescoring attracts again more attention. In this work, we present a new technique to train the log-linear model based on the ListNet algorithm. This technique scales to many features, considers the whole list and not single entries during learning and can also be applied to more complex models than a log-linear combination. Using the new learning approach, we improve the translation quality of a largescale system by 0.8 BLEU points during rescoring and generate translations which are up to 0.3 BLEU points better than other learning techniques such as MERT or MIRA.

The Karlsruhe Institute of Technology Systems for the News Translation Task in WMT 2017

“…Similar to the ensemble methods we can reach a good performance by using equal weights. In a second approach, we use the ListNet algorithms (Cao et al, 2007;Niehues et al, 2015) to find the optimial weights for the individual models.…”

“…In order to find the optimal weights for the different models, we use the ListNet algorithm (Cao et al, 2007;Niehues et al, 2015). This technique defines a probability distribution on the permutations of the list based on the scores of the individual models and another one based on a reference metric.…”

The KIT-LIMSI Translation System for WMT 2015

“…As it is done in the baseline decoder, we used a log-linear combination of all features. We trained the model using the ListNet algorithm (Niehues et al, 2015;Cao et al, 2007).…”

The Karlsruhe Institute of Technology Translation Systems for the WMT 2015

“…We trained the weights for the log-linear combination used during rescoring using the ListNet algorithm (Cao et al, 2007;Niehues et al, 2015). This technique defines a probability distribution on the permutations of the list based on the scores of the log-linear model and one based on a reference metric.…”