中文
相关论文

相关论文: Evaluating Layers of Representation in Neural Mach…

200 篇论文

Neural machine translation (MT) models obtain state-of-the-art performance while maintaining a simple, end-to-end architecture. However, little is known about what these models learn about source and target languages during the training…

计算与语言 · 计算机科学 2018-10-23 Yonatan Belinkov , Nadir Durrani , Fahim Dalvi , Hassan Sajjad , James Glass

Despite the recent success of deep neural networks in natural language processing (NLP), their interpretability remains a challenge. We analyze the representations learned by neural machine translation models at various levels of…

计算与语言 · 计算机科学 2019-11-04 Yonatan Belinkov , Nadir Durrani , Fahim Dalvi , Hassan Sajjad , James Glass

Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite…

计算与语言 · 计算机科学 2021-09-06 Elena Voita , Rico Sennrich , Ivan Titov

End-to-end neural machine translation has overtaken statistical machine translation in terms of translation quality for some language pairs, specially those with large amounts of parallel data. Besides this palpable improvement, neural…

计算与语言 · 计算机科学 2017-11-16 Cristina España-Bonet , Ádám Csaba Varga , Alberto Barrón-Cedeño , Josef van Genabith

Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…

计算与语言 · 计算机科学 2019-08-22 Rongxiang Weng , Heng Yu , Shujian Huang , Weihua Luo , Jiajun Chen

We train neural machine translation (NMT) models from English to six target languages, using NMT encoder representations to predict ancestor constituent labels of source language words. We find that NMT encoders learn similar source syntax…

计算与语言 · 计算机科学 2020-05-19 Tyler A. Chang , Anna N. Rafferty

Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split a source sequence with different word segmentors or…

计算与语言 · 计算机科学 2019-06-05 Fengshun Xiao , Jiangtong Li , Hai Zhao , Rui Wang , Kehai Chen

Recent years have witnessed the rapid advance in neural machine translation (NMT), the core of which lies in the encoder-decoder architecture. Inspired by the recent progress of large-scale pre-trained language models on machine translation…

计算与语言 · 计算机科学 2021-06-28 Shuo Wang , Zhaopeng Tu , Zhixing Tan , Wenxuan Wang , Maosong Sun , Yang Liu

Advanced neural machine translation (NMT) models generally implement encoder and decoder as multiple layers, which allows systems to model complex functions and capture complicated linguistic structures. However, only the top layers of…

计算与语言 · 计算机科学 2018-10-25 Zi-Yi Dou , Zhaopeng Tu , Xing Wang , Shuming Shi , Tong Zhang

Recent advances in Neural Machine Translation (NMT) show that adding syntactic information to NMT systems can improve the quality of their translations. Most existing work utilizes some specific types of linguistically-inspired tree…

计算与语言 · 计算机科学 2018-08-29 Xinyi Wang , Hieu Pham , Pengcheng Yin , Graham Neubig

Compared to sentence-level systems, document-level neural machine translation (NMT) models produce a more consistent output across a document and are able to better resolve ambiguities within the input. There are many works on…

计算与语言 · 计算机科学 2023-06-09 Christian Herold , Hermann Ney

Neural language models learn word representations, or embeddings, that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models, a recently-developed class of neural…

计算与语言 · 计算机科学 2015-04-06 Felix Hill , Kyunghyun Cho , Sebastien Jean , Coline Devin , Yoshua Bengio

Neural language models learn word representations that capture rich linguistic and conceptual information. Here we investigate the embeddings learned by neural machine translation models. We show that translation-based embeddings outperform…

计算与语言 · 计算机科学 2014-11-14 Felix Hill , KyungHyun Cho , Sebastien Jean , Coline Devin , Yoshua Bengio

Pretrained language models (PLMs) have produced substantial improvements in discourse-aware neural machine translation (NMT), for example, improved coherence in spoken language translation. However, the underlying reasons for their strong…

计算与语言 · 计算机科学 2023-06-01 Zhihong Huang , Longyue Wang , Siyou Liu , Derek F. Wong

Document-level machine translation incorporates inter-sentential dependencies into the translation of a source sentence. In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation…

计算与语言 · 计算机科学 2020-03-31 Pei Zhang , Xu Zhang , Wei Chen , Jian Yu , Yanfeng Wang , Deyi Xiong

Neural Machine Translation (NMT) is a new approach to machine translation that has made great progress in recent years. However, recent studies show that NMT generally produces fluent but inadequate translations (Tu et al. 2016b; Tu et al.…

计算与语言 · 计算机科学 2017-01-02 Xing Wang , Zhengdong Lu , Zhaopeng Tu , Hang Li , Deyi Xiong , Min Zhang

Machine translation (MT) systems translate text between different languages by automatically learning in-depth knowledge of bilingual lexicons, grammar and semantics from the training examples. Although neural machine translation (NMT) has…

计算与语言 · 计算机科学 2020-04-29 Shilin He , Xing Wang , Shuming Shi , Michael R. Lyu , Zhaopeng Tu

Neural machine translation (NMT) models learn representations containing substantial linguistic information. However, it is not clear if such information is fully distributed or if some of it can be attributed to individual neurons. We…

计算与语言 · 计算机科学 2018-11-06 Anthony Bau , Yonatan Belinkov , Hassan Sajjad , Nadir Durrani , Fahim Dalvi , James Glass

Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various…

计算与语言 · 计算机科学 2020-10-20 Jingjing Huo , Christian Herold , Yingbo Gao , Leonard Dahlmann , Shahram Khadivi , Hermann Ney

Machine translation systems require semantic knowledge and grammatical understanding. Neural machine translation (NMT) systems often assume this information is captured by an attention mechanism and a decoder that ensures fluency. Recent…

计算与语言 · 计算机科学 2018-05-29 Ke Tran , Yonatan Bisk
‹ 上一页 1 2 3 10 下一页 ›