Coverage-based Neural Machine Translation

By Zhaopeng Tu, Zhengdong Lu, Yang Liu, Xiaohua Liu, Hang Li. 2016

69 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation (2016, background): “Though this can be addressed in principle by training a “copy model” to mimic a traditional alignment model [31], or by using the attention mechanism to copy rare words [37], these approaches are both unreliable at scale, since the quality of the alignments varies across languages, and the latent…”
Exploiting Source-side Monolingual Data in Neural Machine Translation (2016, methodology): “Most of the existing methods mainly focus on designing better alignment mechanisms (attention model) for the decoder network (Cheng et al., 2016a; Luong et al., 2015b; Cohn et al., 2016; Feng et al., 2016; Tu et al., 2016; Mi et al., 2016a; Mi et al., 2016b), better objective functions for BLEU eval”
Distraction-Based Neural Networks for Modeling Document (2016, methodology): “The model in [Tu et al., 2016] also uses history attention weights, but we use history here to force distraction in order to avoid redundancy, which is not a concern in the machine translation task.”
Coverage Embedding Models for Neural Machine Translation (2016, background): “Tu et al. (2016) is the most relevant one.”
Variational Neural Machine Translation (2016, methodology): “…learning better attentional structures (Luong et al., 2015a), integrating SMT techniques (Cheng et al., 2015; Shen et al., 2015; Feng et al., 2016; Tu et al., 2016), character-level NMT (Ling et al., 2015; Costa-Juss`a and Fonol-losa, 2016), the exploitation of monolingual corpora (Gulcehre et…”
Neural Machine Translation With GRU-Gated Attention Model (2020, methodology): “In addition to the RNNSearch model [2], we also compare our proposed model against another two advanced systems: Moses [29], an open-source state-of-the-art phrase-based SMT system, and Coverage [12], an improved attention-based NMT model with coverage mechanism.”
Decoding with Value Networks for Neural Machine Translation (2017, background): “Context-Coverage (CC) Module: It is often observed that the more context covered in the attention model, the better translation we will generate [14, 15].”
Why Catalan-Spanish Neural Machine Translation? Analysis, comparison and combination with standard Rule and Phrase-based technologies (2017, methodology): “The example of missing determiners could be solved using coverage neural MT (Tu et al., 2016); wrong translations may be reduced using a language model (Gulcehre et al., 2017); and out-of-vocabulary words may be reduced using existing approaches such as Byte Pair Encoding (BPE) (Sennrich et al.,…”
Syntactically Guided Neural Machine Translation (2016, background): “The NMT beam decoder does not have an explicit mechanism for tracking source coverage, and there is evidence that may lead to both ‘over-translation’ and ‘under-translation’ (Tu et al., 2016).”
Interactive Visualization and Manipulation of Attention-based Neural Machine Translation (2017, methodology): “Since the component behaves like alignment in traditional SMT, it has been proposed to utilize attention during training (Cheng et al., 2015; Tu et al., 2016b) or during decoding (Wu et al., 2016).”