目录
1. Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting, ACL 2020 [PDF] 摘要
3. The TALP-UPC Machine Translation Systems for WMT19 News Translation Task: Pivoting Techniques for Low Resource MT, ACL 2019 [PDF] 摘要
4. Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages, EMNLP 2019 [PDF] 摘要
6. From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots, IJCAI 2019 [PDF] 摘要
9. Exploring Key Concept Paraphrasing Based on Pivot Language Translation for Question Retrieval, AAAI 2015 [PDF] 摘要
11. Improving Pivot-Based Statistical Machine Translation by Pivoting the Co-occurrence Count of Phrase Pairs, EMNLP 2014 [PDF] 摘要
摘要
1. Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting [PDF] 返回目录
ACL 2020.
Po-Yao Huang, Junjie Hu, Xiaojun Chang, Alexander Hauptmann
Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora only. However, it is still challenging to associate source-target sentences in the latent space. As people speak different languages biologically share similar visual systems, the potential of achieving better alignment through visual content is promising yet under-explored in unsupervised multimodal MT (MMT). In this paper, we investigate how to utilize visual content for disambiguation and promoting latent space alignment in unsupervised MMT. Our model employs multimodal back-translation and features pseudo visual pivoting in which we learn a shared multilingual visual-semantic embedding space and incorporate visually-pivoted captioning as additional weak supervision. The experimental results on the widely used Multi30K dataset show that the proposed model significantly improves over the state-of-the-art methods and generalizes well when images are not available at the testing time.
ACL 2020.
Po-Yao Huang, Junjie Hu, Xiaojun Chang, Alexander Hauptmann
Unsupervised machine translation (MT) has recently achieved impressive results with monolingual corpora only. However, it is still challenging to associate source-target sentences in the latent space. As people speak different languages biologically share similar visual systems, the potential of achieving better alignment through visual content is promising yet under-explored in unsupervised multimodal MT (MMT). In this paper, we investigate how to utilize visual content for disambiguation and promoting latent space alignment in unsupervised MMT. Our model employs multimodal back-translation and features pseudo visual pivoting in which we learn a shared multilingual visual-semantic embedding space and incorporate visually-pivoted captioning as additional weak supervision. The experimental results on the widely used Multi30K dataset show that the proposed model significantly improves over the state-of-the-art methods and generalizes well when images are not available at the testing time.
2. Unsupervised Pivot Translation for Distant Languages [PDF] 返回目录
ACL 2019.
Yichong Leng, Xu Tan, Tao Qin, Xiang-Yang Li, Tie-Yan Liu
Unsupervised neural machine translation (NMT) has attracted a lot of attention recently. While state-of-the-art methods for unsupervised translation usually perform well between similar languages (e.g., English-German translation), they perform poorly between distant languages, because unsupervised alignment does not work well for distant languages. In this work, we introduce unsupervised pivot translation for distant languages, which translates a language to a distant language through multiple hops, and the unsupervised translation on each hop is relatively easier than the original direct translation. We propose a learning to route (LTR) method to choose the translation path between the source and target languages. LTR is trained on language pairs whose best translation path is available and is applied on the unseen language pairs for path selection. Experiments on 20 languages and 294 distant language pairs demonstrate the advantages of the unsupervised pivot translation for distant languages, as well as the effectiveness of the proposed LTR for path selection. Specifically, in the best case, LTR achieves an improvement of 5.58 BLEU points over the conventional direct unsupervised method.
ACL 2019.
Yichong Leng, Xu Tan, Tao Qin, Xiang-Yang Li, Tie-Yan Liu
Unsupervised neural machine translation (NMT) has attracted a lot of attention recently. While state-of-the-art methods for unsupervised translation usually perform well between similar languages (e.g., English-German translation), they perform poorly between distant languages, because unsupervised alignment does not work well for distant languages. In this work, we introduce unsupervised pivot translation for distant languages, which translates a language to a distant language through multiple hops, and the unsupervised translation on each hop is relatively easier than the original direct translation. We propose a learning to route (LTR) method to choose the translation path between the source and target languages. LTR is trained on language pairs whose best translation path is available and is applied on the unseen language pairs for path selection. Experiments on 20 languages and 294 distant language pairs demonstrate the advantages of the unsupervised pivot translation for distant languages, as well as the effectiveness of the proposed LTR for path selection. Specifically, in the best case, LTR achieves an improvement of 5.58 BLEU points over the conventional direct unsupervised method.
3. The TALP-UPC Machine Translation Systems for WMT19 News Translation Task: Pivoting Techniques for Low Resource MT [PDF] 返回目录
ACL 2019. the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
Noe Casas, José A. R. Fonollosa, Carlos Escolano, Christine Basta, Marta R. Costa-jussà
In this article, we describe the TALP-UPC research group participation in the WMT19 news translation shared task for Kazakh-English. Given the low amount of parallel training data, we resort to using Russian as pivot language, training subword-based statistical translation systems for Russian-Kazakh and Russian-English that were then used to create two synthetic pseudo-parallel corpora for Kazakh-English and English-Kazakh respectively. Finally, a self-attention model based on the decoder part of the Transformer architecture was trained on the two pseudo-parallel corpora.
ACL 2019. the Fourth Conference on Machine Translation (Volume 2: Shared Task Papers, Day 1)
Noe Casas, José A. R. Fonollosa, Carlos Escolano, Christine Basta, Marta R. Costa-jussà
In this article, we describe the TALP-UPC research group participation in the WMT19 news translation shared task for Kazakh-English. Given the low amount of parallel training data, we resort to using Russian as pivot language, training subword-based statistical translation systems for Russian-Kazakh and Russian-English that were then used to create two synthetic pseudo-parallel corpora for Kazakh-English and English-Kazakh respectively. Finally, a self-attention model based on the decoder part of the Transformer architecture was trained on the two pseudo-parallel corpora.
4. Pivot-based Transfer Learning for Neural Machine Translation between Non-English Languages [PDF] 返回目录
EMNLP 2019.
Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney
We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i.e., source-pivot and pivot-target, leading to a significant improvement in source-target translation. We propose three methods to increase the relation among source, pivot, and target languages in the pre-training: 1) step-wise training of a single model for different language pairs, 2) additional adapter component to smoothly connect pre-trained encoder and decoder, and 3) cross-lingual encoder training via autoencoding of the pivot language. Our methods greatly outperform multilingual models up to +2.6% BLEU in WMT 2019 French-German and German-Czech tasks. We show that our improvements are valid also in zero-shot/zero-resource scenarios.
EMNLP 2019.
Yunsu Kim, Petre Petrov, Pavel Petrushkov, Shahram Khadivi, Hermann Ney
We present effective pre-training strategies for neural machine translation (NMT) using parallel corpora involving a pivot language, i.e., source-pivot and pivot-target, leading to a significant improvement in source-target translation. We propose three methods to increase the relation among source, pivot, and target languages in the pre-training: 1) step-wise training of a single model for different language pairs, 2) additional adapter component to smoothly connect pre-trained encoder and decoder, and 3) cross-lingual encoder training via autoencoding of the pivot language. Our methods greatly outperform multilingual models up to +2.6% BLEU in WMT 2019 French-German and German-Czech tasks. We show that our improvements are valid also in zero-shot/zero-resource scenarios.
5. Zero-Resource Neural Machine Translation with Monolingual Pivot Data [PDF] 返回目录
EMNLP 2019. the 3rd Workshop on Neural Generation and Translation
Anna Currey, Kenneth Heafield
Zero-shot neural machine translation (NMT) is a framework that uses source-pivot and target-pivot parallel data to train a source-target NMT system. An extension to zero-shot NMT is zero-resource NMT, which generates pseudo-parallel corpora using a zero-shot system and further trains the zero-shot system on that data. In this paper, we expand on zero-resource NMT by incorporating monolingual data in the pivot language into training; since the pivot language is usually the highest-resource language of the three, we expect monolingual pivot-language data to be most abundant. We propose methods for generating pseudo-parallel corpora using pivot-language monolingual data and for leveraging the pseudo-parallel corpora to improve the zero-shot NMT system. We evaluate these methods for a high-resource language pair (German-Russian) using English as the pivot. We show that our proposed methods yield consistent improvements over strong zero-shot and zero-resource baselines and even catch up to pivot-based models in BLEU (while not requiring the two-pass inference that pivot models require).
EMNLP 2019. the 3rd Workshop on Neural Generation and Translation
Anna Currey, Kenneth Heafield
Zero-shot neural machine translation (NMT) is a framework that uses source-pivot and target-pivot parallel data to train a source-target NMT system. An extension to zero-shot NMT is zero-resource NMT, which generates pseudo-parallel corpora using a zero-shot system and further trains the zero-shot system on that data. In this paper, we expand on zero-resource NMT by incorporating monolingual data in the pivot language into training; since the pivot language is usually the highest-resource language of the three, we expect monolingual pivot-language data to be most abundant. We propose methods for generating pseudo-parallel corpora using pivot-language monolingual data and for leveraging the pseudo-parallel corpora to improve the zero-shot NMT system. We evaluate these methods for a high-resource language pair (German-Russian) using English as the pivot. We show that our proposed methods yield consistent improvements over strong zero-shot and zero-resource baselines and even catch up to pivot-based models in BLEU (while not requiring the two-pass inference that pivot models require).
6. From Words to Sentences: A Progressive Learning Approach for Zero-resource Machine Translation with Visual Pivots [PDF] 返回目录
IJCAI 2019.
Shizhe Chen, Qin Jin, Jianlong Fu
The neural machine translation model has suffered from the lack of large-scale parallel corpora. In contrast, we humans can learn multi-lingual translations even without parallel texts by referring our languages to the external world. To mimic such human learning behavior, we employ images as pivots to enable zero-resource translation learning. However, a picture tells a thousand words, which makes multi-lingual sentences pivoted by the same image noisy as mutual translations and thus hinders the translation model learning. In this work, we propose a progressive learning approach for image-pivoted zero-resource machine translation. Since words are less diverse when grounded in the image, we first learn word-level translation with image pivots, and then progress to learn the sentence-level translation by utilizing the learned word translation to suppress noises in image-pivoted multi-lingual sentences. Experimental results on two widely used image-pivot translation datasets, IAPR-TC12 and Multi30k, show that the proposed approach significantly outperforms other state-of-the-art methods.
IJCAI 2019.
Shizhe Chen, Qin Jin, Jianlong Fu
The neural machine translation model has suffered from the lack of large-scale parallel corpora. In contrast, we humans can learn multi-lingual translations even without parallel texts by referring our languages to the external world. To mimic such human learning behavior, we employ images as pivots to enable zero-resource translation learning. However, a picture tells a thousand words, which makes multi-lingual sentences pivoted by the same image noisy as mutual translations and thus hinders the translation model learning. In this work, we propose a progressive learning approach for image-pivoted zero-resource machine translation. Since words are less diverse when grounded in the image, we first learn word-level translation with image pivots, and then progress to learn the sentence-level translation by utilizing the learned word translation to suppress noises in image-pivoted multi-lingual sentences. Experimental results on two widely used image-pivot translation datasets, IAPR-TC12 and Multi30k, show that the proposed approach significantly outperforms other state-of-the-art methods.
7. Joint Training for Pivot-based Neural Machine Translation [PDF] 返回目录
IJCAI 2017.
Yong Cheng, Qian Yang, Yang Liu, Maosong Sun, Wei Xu
While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be alleviated by exploiting a pivot language to bridge the source and target languages, the source-to-pivot and pivot-to-target translation models are usually independently trained. In this work, we introduce a joint training algorithm for pivot-based neural machine translation. We propose three methods to connect the two models and enable them to interact with each other during training. Experiments on Europarl and WMT corpora show that joint training of source-to-pivot and pivot-to-target models leads to significant improvements over independent training across various languages.
IJCAI 2017.
Yong Cheng, Qian Yang, Yang Liu, Maosong Sun, Wei Xu
While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be alleviated by exploiting a pivot language to bridge the source and target languages, the source-to-pivot and pivot-to-target translation models are usually independently trained. In this work, we introduce a joint training algorithm for pivot-based neural machine translation. We propose three methods to connect the two models and enable them to interact with each other during training. Experiments on Europarl and WMT corpora show that joint training of source-to-pivot and pivot-to-target models leads to significant improvements over independent training across various languages.
8. Multimodal Pivots for Image Caption Translation [PDF] 返回目录
ACL 2016. Long Papers
Julian Hitschler, Shigehiko Schamoni, Stefan Riezler
ACL 2016. Long Papers
Julian Hitschler, Shigehiko Schamoni, Stefan Riezler
9. Exploring Key Concept Paraphrasing Based on Pivot Language Translation for Question Retrieval [PDF] 返回目录
AAAI 2015. AI and the Web
Weinan Zhang, Zhaoyan Ming, Yu Zhang, Ting Liu, Tat-Seng Chua
Question retrieval in current community-based question answering (CQA) services does not, in general, work well for long and complex queries. One of the main difficulties lies in the word mismatch between queries and candidate questions. Existing solutions try to expand the queries at word level, but they usually fail to consider concept level enrichment. In this paper, we explore a pivot language translation based approach to derive the paraphrases of key concepts. We further propose a unified question retrieval model which integrates the keyconcepts and their paraphrases for the query question. Experimental results demonstrate that the paraphrase enhanced retrieval model significantly outperforms the state-of-the-art models in question retrieval.
AAAI 2015. AI and the Web
Weinan Zhang, Zhaoyan Ming, Yu Zhang, Ting Liu, Tat-Seng Chua
Question retrieval in current community-based question answering (CQA) services does not, in general, work well for long and complex queries. One of the main difficulties lies in the word mismatch between queries and candidate questions. Existing solutions try to expand the queries at word level, but they usually fail to consider concept level enrichment. In this paper, we explore a pivot language translation based approach to derive the paraphrases of key concepts. We further propose a unified question retrieval model which integrates the keyconcepts and their paraphrases for the query question. Experimental results demonstrate that the paraphrase enhanced retrieval model significantly outperforms the state-of-the-art models in question retrieval.
10. Improving Pivot Translation by Remembering the Pivot [PDF] 返回目录
ACL 2015. Short Papers
Akiva Miura, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura
ACL 2015. Short Papers
Akiva Miura, Graham Neubig, Sakriani Sakti, Tomoki Toda, Satoshi Nakamura
11. Improving Pivot-Based Statistical Machine Translation by Pivoting the Co-occurrence Count of Phrase Pairs [PDF] 返回目录
EMNLP 2014.
Xiaoning Zhu, Zhongjun He, Hua Wu, Conghui Zhu, Haifeng Wang, Tiejun Zhao
EMNLP 2014.
Xiaoning Zhu, Zhongjun He, Hua Wu, Conghui Zhu, Haifeng Wang, Tiejun Zhao
注：论文列表使用AC论文搜索器整理！