【论文推荐】最新六篇机器翻译相关论文—综述、卷积Encoder-Decoder神经网络、字翻译、自编码器、神经短语、RNNs

2018 年 2 月 19 日 专知 专知内容组
【论文推荐】最新六篇机器翻译相关论文—综述、卷积Encoder-Decoder神经网络、字翻译、自编码器、神经短语、RNNs

【导读】专知内容组整理了最近六篇机器翻译(Machine Translation)相关文章,为大家进行介绍,欢迎查看!

1. Machine Translation Using Semantic Web Technologies: A Survey使用语义Web技术的机器翻译:综述




作者Diego Moussallem,Matthias Wauer,Axel-Cyrille Ngonga Ngomo  

摘要A large number of machine translation approaches have been developed recently with the aim of migrating content easily across languages. However, the literature suggests that many obstacles must be dealt with to achieve better automatic translations. A central issue that machine translation systems must handle is ambiguity. A promising way of overcoming this problem is using semantic web technologies. This article presents the results of a systematic review of approaches that rely on semantic web technologies within machine translation approaches for translating texts. Overall, our survey suggests that while semantic web technologies can enhance the quality of machine translation outputs for various problems, the combination of both is still in its infancy.

期刊:arXiv, 2018年2月1日

网址

http://www.zhuanzhi.ai/document/bcd6dafe31ab36a787f959b78e6b2368

2. A Multilayer Convolutional Encoder-Decoder Neural Network for Grammatical Error Correction多层卷积Encoder-Decoder神经网络的语法错误校正




作者Shamil Chollampatt,Hwee Tou Ng

摘要We improve automatic correction of grammatical, orthographic, and collocation errors in text using a multilayer convolutional encoder-decoder neural network. The network is initialized with embeddings that make use of character N-gram information to better suit this task. When evaluated on common benchmark test data sets (CoNLL-2014 and JFLEG), our model substantially outperforms all prior neural approaches on this task as well as strong statistical machine translation-based systems with neural and task-specific features trained on the same data. Our analysis shows the superiority of convolutional neural networks over recurrent neural networks such as long short-term memory (LSTM) networks in capturing the local context via attention, and thereby improving the coverage in correcting grammatical errors. By ensembling multiple models, and incorporating an N-gram language model and edit features via rescoring, our novel method becomes the first neural approach to outperform the current state-of-the-art statistical machine translation-based approach, both in terms of grammaticality and fluency.

期刊:arXiv, 2018年1月26日

网址

http://www.zhuanzhi.ai/document/caa822579b312238bc527d955ddabf16

3. Word Translation Without Parallel Data(无并行数据的字翻译




作者Alexis Conneau,Guillaume Lample,Marc'Aurelio Ranzato,Ludovic Denoyer,Hervé Jégou

摘要State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised way. Without using any character information, our model even outperforms existing supervised methods on cross-lingual tasks for some language pairs. Our experiments demonstrate that our method works very well also for distant language pairs, like English-Russian or English-Chinese. We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine translation. Our code, embeddings and dictionaries are publicly available.


期刊:arXiv, 2018年1月30日

网址

http://www.zhuanzhi.ai/document/3cb1a972758f75404747b1fd4288bd57

4. Discrete Autoencoders for Sequence Models离散自编码器的序列模型




作者Łukasz Kaiser,Samy Bengio

摘要Recurrent models for sequences have been recently successful at many tasks, especially for language modeling and machine translation. Nevertheless, it remains challenging to extract good representations from these models. For instance, even though language has a clear hierarchical structure going from characters through words to sentences, it is not apparent in current language models. We propose to improve the representation in sequence models by augmenting current approaches with an autoencoder that is forced to compress the sequence through an intermediate discrete latent space. In order to propagate gradients though this discrete representation we introduce an improved semantic hashing technique. We show that this technique performs well on a newly proposed quantitative efficiency measure. We also analyze latent codes produced by the model showing how they correspond to words and phrases. Finally, we present an application of the autoencoder-augmented model to generating diverse translations.


期刊:arXiv, 2018年1月30日

网址

http://www.zhuanzhi.ai/document/fe80983b18aca3bb2c492a10e9287c36

5. Towards Neural Phrase-based Machine Translation基于神经短语的机器翻译




作者Po-Sen Huang,Chong Wang,Sitao Huang,Dengyong Zhou,Li Deng

摘要In this paper, we present Neural Phrase-based Machine Translation (NPMT). Our method explicitly models the phrase structures in output sequences using Sleep-WAke Networks (SWAN), a recently proposed segmentation-based sequence modeling method. To mitigate the monotonic alignment requirement of SWAN, we introduce a new layer to perform (soft) local reordering of input sequences. Different from existing neural machine translation (NMT) approaches, NPMT does not use attention-based decoding mechanisms. Instead, it directly outputs phrases in a sequential order and can decode in linear time. Our experiments show that NPMT achieves superior performances on IWSLT 2014 German-English/English-German and IWSLT 2015 English-Vietnamese machine translation tasks compared with strong NMT baselines. We also observe that our method produces meaningful phrases in output languages.


期刊:arXiv, 2018年1月30日

网址

http://www.zhuanzhi.ai/document/9440528ac5ff943a94076c8f0c44e5fe

6. SEARNN: Training RNNs with Global-Local LossesSEARNN: 全局-局部损失的RNNs训练




作者Rémi Leblond,Jean-Baptiste Alayrac,Anton Osokin,Simon Lacoste-Julien

摘要We propose SEARNN, a novel training algorithm for recurrent neural networks (RNNs) inspired by the "learning to search" (L2S) approach to structured prediction. RNNs have been widely successful in structured prediction applications such as machine translation or parsing, and are commonly trained using maximum likelihood estimation (MLE). Unfortunately, this training loss is not always an appropriate surrogate for the test error: by only maximizing the ground truth probability, it fails to exploit the wealth of information offered by structured losses. Further, it introduces discrepancies between training and predicting (such as exposure bias) that may hurt test performance. Instead, SEARNN leverages test-alike search space exploration to introduce global-local losses that are closer to the test error. We first demonstrate improved performance over MLE on two different tasks: OCR and spelling correction. Then, we propose a subsampling strategy to enable SEARNN to scale to large vocabulary sizes. This allows us to validate the benefits of our approach on a machine translation task.

期刊:arXiv, 2018年1月30日

网址

http://www.zhuanzhi.ai/document/34ff9ebef7e6d6cd6f887ab10588bec1

-END-

专 · 知

人工智能领域主题知识资料查看获取【专知荟萃】人工智能领域26个主题知识资料全集(入门/进阶/论文/综述/视频/专家等)

同时欢迎各位用户进行专知投稿,详情请点击

诚邀】专知诚挚邀请各位专业者加入AI创作者计划了解使用专知!

请PC登录www.zhuanzhi.ai或者点击阅读原文,注册登录专知,获取更多AI知识资料

请扫一扫如下二维码关注我们的公众号,获取人工智能的专业知识!

请加专知小助手微信(Rancho_Fang),加入专知主题人工智能群交流!


点击“阅读原文”,使用专知

登录查看更多
6

相关内容

机器翻译(Machine Translation)涵盖计算语言学和语言工程的所有分支,包含多语言方面。特色论文涵盖理论,描述或计算方面的任何下列主题:双语和多语语料库的编写和使用,计算机辅助语言教学,非罗马字符集的计算含义,连接主义翻译方法,对比语言学等。 官网地址:http://dblp.uni-trier.de/db/journals/mt/

In spite of the recent success of neural machine translation (NMT) in standard benchmarks, the lack of large parallel corpora poses a major practical problem for many language pairs. There have been several proposals to alleviate this issue with, for instance, triangulation and semi-supervised learning techniques, but they still require a strong cross-lingual signal. In this work, we completely remove the need of parallel data and propose a novel method to train an NMT system in a completely unsupervised manner, relying on nothing but monolingual corpora. Our model builds upon the recent work on unsupervised embedding mappings, and consists of a slightly modified attentional encoder-decoder model that can be trained on monolingual corpora alone using a combination of denoising and backtranslation. Despite the simplicity of the approach, our system obtains 15.56 and 10.21 BLEU points in WMT 2014 French-to-English and German-to-English translation. The model can also profit from small parallel corpora, and attains 21.81 and 15.24 points when combined with 100,000 parallel sentences, respectively. Our implementation is released as an open source project.

0
6
下载
预览

A large number of machine translation approaches have been developed recently with the aim of migrating content easily across languages. However, the literature suggests that many obstacles must be dealt with to achieve better automatic translations. A central issue that machine translation systems must handle is ambiguity. A promising way of overcoming this problem is using semantic web technologies. This article presents the results of a systematic review of approaches that rely on semantic web technologies within machine translation approaches for translating texts. Overall, our survey suggests that while semantic web technologies can enhance the quality of machine translation outputs for various problems, the combination of both is still in its infancy.

0
8
下载
预览
小贴士
相关资讯
相关VIP内容
专知会员服务
46+阅读 · 2020年3月19日
机器翻译深度学习最新综述
专知会员服务
76+阅读 · 2020年2月20日
AAAI2020接受论文列表,1591篇论文目录全集
专知会员服务
91+阅读 · 2020年1月12日
六篇 EMNLP 2019【图神经网络(GNN)+NLP】相关论文
专知会员服务
61+阅读 · 2019年11月3日
强化学习最新教程,17页pdf
专知会员服务
75+阅读 · 2019年10月11日
[综述]深度学习下的场景文本检测与识别
专知会员服务
46+阅读 · 2019年10月10日
最新BERT相关论文清单,BERT-related Papers
专知会员服务
39+阅读 · 2019年9月29日
相关论文
A Survey and Taxonomy of Adversarial Neural Networks for Text-to-Image Synthesis
Jorge Agnese,Jonathan Herrera,Haicheng Tao,Xingquan Zhu
6+阅读 · 2019年10月21日
Neural Image Captioning
Elaina Tan,Lakshay Sharma
4+阅读 · 2019年7月2日
Jianfeng Gao,Michel Galley,Lihong Li
26+阅读 · 2018年9月21日
On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translation
Tamer Alkhouli,Gabriel Bretschner,Hermann Ney
3+阅读 · 2018年9月11日
Chenhui Chu,Rui Wang
13+阅读 · 2018年6月1日
Mikel Artetxe,Gorka Labaka,Eneko Agirre,Kyunghyun Cho
6+阅读 · 2018年2月26日
Diego Moussallem,Matthias Wauer,Axel-Cyrille Ngonga Ngomo
8+阅读 · 2018年2月1日
Łukasz Kaiser,Samy Bengio
6+阅读 · 2018年1月29日
Shamil Chollampatt,Hwee Tou Ng
5+阅读 · 2018年1月26日
Parth Shah,Vishvajit Bakarola,Supriya Pati
20+阅读 · 2018年1月17日
Top
微信扫码咨询专知VIP会员