Modeling Coherence for Neural Machine Translation with Dynamic and Topic Caches

By Shaohui Kuang, Deyi Xiong, Weihua Luo, Guodong Zhou. 2017

101 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

Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation (2020, methodology): “Complementary to this, Kuang et al. (2018) introduces two caches, one lexical and the other topical, to store information from context pertinent to translating future sentences.”
Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense (2023, methodology): “…modify the generative algorithm to encode hidden information unique to the API (Appendix E.1); (2) statistical outlier detection methods, which do not modify the generative algorithm but look for inherent artifacts in generated text (Appendix E.2); and (3) classiﬁers trained to discriminate…”
A Survey of the Usages of Deep Learning for Natural Language Processing (2020, background): “Notable recent advancements include using caching to provide networks with greater context than simply the individual sentences being translated [261], the ability to better handle rare words [262], [263], and the ability to translate to and from understudied languages, such as those that are polysy”
A Comprehensive Survey of Grammar Error Correction (2020, unknown): “To be more specific, the final possibility of choosing the next word 𝜔 is composed of two parts, the possibility of generation softmax and the possibility of copying the word from source sentence where 𝛼 and 𝑝 (𝜔) are calculated with copy attention between encoder’s output 𝐻 𝑒𝑛𝑐 and decoder’”
Pretrained Language Models for Document-Level Neural Machine Translation (2019, background): “…Machine Translation (NMT) is drawing more attention from researchers studying on incorporating contexts into translation models (Wang et al., 2017; Jean et al., 2017; Tiedemann and Scherrer, 2017; Voita et al., 2018; Zhang et al., 2018; Miculicich et al., 2018; Kuang et al., 2018; Tu et al., 2018).”
Encouraging Lexical Translation Consistency for Document-Level Neural Machine Translation (2021, background): “As a way to encourage lexical translation consistency, Kuang et al. (2017) and Tu et al. (2018) cache recently translated words and/or their translations for translating future sentences.”
A Comprehensive Survey of Grammatical Error Correction (2021, background): “Integrating cross-sentence context is common in the researches about neural machine translation [62, 77, 133], where different sizes of contexts are considered.”