Lexicons and Minimum Risk Training for Neural Machine Translation: NAIST-CMU at WAT2016

By Graham Neubig. 2016

28 citations recorded by the source corpus.

This year, the Nara Institute of Science and Technology (NAIST)/Carnegie Mellon University (CMU) submission to the Japanese-English translation track of the 2016 Workshop on Asian Translation was based on attentional neural machine translation (NMT) models. In addition to the standard NMT model, we make a number of improvements, most notably the use of discrete translation lexicons to improve probability estimates, and the use of minimum risk training to optimize the MT system for BLEU score. As a result, our system achieved the highest translation evaluation scores for the task.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

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 Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Structured Attention Networks (2017, methodology): “This differs from prior NMTbased approaches to Japanese-English translation, which typically run Japanese word segmentation as a preprocessing step (Neubig, 2016).”
On the Weaknesses of Reinforcement Learning for Neural Machine Translation (2019, methodology): “…the more common scenario studied by contemporary RL methods, which focuses mostly on much smaller discrete action spaces (e.g., video games (Mnih et al., 2015, 2016)), or continuous action spaces of relatively low dimensions (e.g., simulation of robotic con-trol tasks (Lillicrap et al., 2015)).”
Improving Word Sense Disambiguation in Neural Machine Translation with Sense Embeddings (2017, background): “, 2015) has recently emerged as the new state of the art in machine translation, producing top-ranked systems in recent shared tasks (Luong and Manning, 2015; Sennrich et al., 2016a; Neubig, 2016).”
Sequence-to-Dependency Neural Machine Translation (2017, background): “Recently, neural machine translation (NMT) has achieved better performance than SMT in many language pairs (Luong et al., 2015a; Zhang et al., 2016; Shen et al., 2016; Wu et al., 2016; Neubig, 2016).”
Neural Machine Translation: A Review (2019, methodology): “The decoder makes use of K NMT networks rather than only one which are either trained independently (Sutskever et al., 2014; Neubig, 2016; Wu et al., 2016) or share some amount of training iterations (Sennrich et al.”
Correcting Length Bias in Neural Machine Translation (2018, methodology): “A third simple method used by various authors (Och and Ney, 2002; He et al., 2016; Neubig, 2016) is a tunable reward added for each output word.”
Improved Neural Machine Translation with Chinese Phonologic Features (2018, background): “Recently, neural machine translation (NMT) has achieved better performance than SMT in many language pairs [13,16,19,24,27].”
Chunk-based Decoder for Neural Machine Translation (2017, background): “, 2014b) and has now overtaken the classical, complex statistical machine translation (SMT) in terms of performance and simplicity (Sennrich et al., 2016; Luong and Manning, 2016; Cromieres et al., 2016; Neubig, 2016).”