Papers with unsupervised machine translation
Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English (D19-52)
Copied to clipboard
Benjamin Marie, Hour Kaing, Aye Myat Mon, Chenchen Ding, Atsushi Fujita, Masao Utiyama, Eiichiro Sumita
| Challenge: | Using cleaned and normalized noisy monolingual data, supervised neural and statistical machine translation systems performed among the best for the four translation directions. |
| Approach: | They present supervised and unsupervised machine translation systems for the WAT2019 Myanmar-English and Khmer-English translation tasks. |
| Outcome: | The proposed systems performed among the best for the four translation directions. |
QiuNiu: A Chinese Lyrics Generation System with Passage-Level Input (2022.acl-demo)
Copied to clipboard
| Challenge: | Existing systems based on attributes or keywords render lyrics generation very limited . previous studies focused on generating lyrics based only on attributes and keywords . |
| Approach: | They propose to use Chinese passage-level text as input for lyrics generation . they initialize parameters with custom pretrained Chinese GPT-2 model and adopt a two-step process to fine-tune the model for better alignment between passage- level text and lyrics. |
| Outcome: | The proposed system is conditioned on passage-level text rather than attributes or keywords, rendering limited control over the content of the lyrics. |
Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings (2021.acl-srw)
Copied to clipboard
| Challenge: | Unsupervised cross-lingual word embedding methods learn a linear transformation matrix that maps two monolingual embeddable spaces that are separately trained with monolingual corpora. |
| Approach: | They propose a method that maps two monolingual embedding spaces that are separately trained with monolingual corpora using a pseudo-parallel corpus. |
| Outcome: | The proposed method outperforms other methods given the same amount of data and shows that using a pseudo-parallel corpus makes the source and target corpora (partially) parallel . |
An Effective Approach to Unsupervised Machine Translation (P19-1)
Copied to clipboard
| Challenge: | a recent research line has managed to train both unsupervised and unsupervised machine translation systems using monolingual corpora only. |
| Approach: | They propose to use monolingual corpora to train both unsupervised and unsupervised machine translation systems. |
| Outcome: | The proposed system achieves 22.5 BLEU points in English-to-German WMT 2014, 5.5 points more than the previous best unsupervised system, and 0.5 points more in the (supervised) shared task winner back in 2014. |
Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining (2020.acl-srw)
Copied to clipboard
| Challenge: | Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. |
| Approach: | They propose an unsupervised method to derive multilingual sentence embeddings using monolingual data. |
| Outcome: | The proposed method improves on two parallel corpus mining tasks and for other languages. |
Weakly-supervised Deep Cognate Detection Framework for Low-Resourced Languages Using Morphological Knowledge of Closely-Related Languages (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to cognate detection focus on orthographic, phonetic or contextual models, which under-perform for most under-resourced languages. |
| Approach: | They propose a language-agnostic weakly-supervised deep cognate detection framework for under-resourced languages using morphological knowledge from closely related languages. |
| Outcome: | The proposed framework outperforms state-of-the-art methods on cognate detection datasets across languages and can be extended to a wide range of languages from any language family. |
Multilingual Denoising Pre-training for Neural Machine Translation (2020.tacl-1)
Copied to clipboard
Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer
| Challenge: | Existing approaches to pre-train models focus on only English corpora, but this is not common in machine translation. |
| Approach: | They propose a sequence-to-sequence denoising auto-encoder pre-trained on monolingual corpora . they show that it produces significant performance gains across MT tasks . |
| Outcome: | The proposed model can achieve significant performance gains across a wide variety of MT tasks. |
Explicit Cross-lingual Pre-training for Unsupervised Machine Translation (D19-1)
Copied to clipboard
| Challenge: | Existing approaches to build initial unsupervised machine translation models with cross-lingual n-gram embeddings are inexplicit and limited. |
| Approach: | They propose a cross-lingual pre-training method that incorporates cross-linguistic training signals into pre-trained models by randomly choosing source n-grams in the input text stream. |
| Outcome: | The proposed method significantly improves the performance of unsupervised machine translation. |
Domain Mismatch Doesn’t Always Prevent Cross-lingual Transfer Learning (2022.lrec-1)
Copied to clipboard
| Challenge: | Recent studies have reported that domain mismatch prevents cross-lingual transfer . UBLI and UNMT do not work well when underlying monolingual corpora come from different domains . |
| Approach: | They show that a simple initialization regimen can overcome domain mismatch in cross-lingual transfer . they pre-train word embeddings on concatenated domain-mismatched corpora and use them as initializations . |
| Outcome: | The initialization regimen can overcome the domain mismatch effect in cross-lingual transfer learning . the initializations were used for MUSE UBLI, UN Parallel UNMT, and the SemEval 2017 task . |
On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation (2022.naacl-main)
Copied to clipboard
| Challenge: | Modern unsupervised machine translation systems reach reasonable translation quality under clean and controlled data conditions. |
| Approach: | They compare unsupervised and supervised machine translation systems of similar quality . they combine the benefits of both methods into a single system . |
| Outcome: | The proposed system improves adequacy and fluency as measured by human evaluators. |
Unsupervised Neural Machine Translation with Universal Grammar (2021.emnlp-main)
Copied to clipboard
| Challenge: | Unsupervised machine translation relies on parallel corpora for training, but performance still lags behind traditional supervised machine translators. |
| Approach: | They propose to leverage shared grammar clues to provide more explicit language parallel signals to enhance the training of unsupervised machine translation models. |
| Outcome: | The proposed models improve on a common language pair training task in English and german, and use embedding alignments and pretrained language models to synthesize pseudo parallel corpora. |
Unsupervised Joint Training of Bilingual Word Embeddings (P19-1)
Copied to clipboard
| Challenge: | Existing methods for unsupervised bilingual word embeddings are limited by the dissimilarity between the word embedded spaces. |
| Approach: | They propose a method that trains unsupervised bilingual word embeddings jointly on parallel data generated through unsupervised machine translation. |
| Outcome: | The proposed method outperforms unsupervised mapped bilingual word embeddings in cross-lingual NLP tasks. |
A Retrieve-and-Rewrite Initialization Method for Unsupervised Machine Translation (2020.acl-main)
Copied to clipboard
| Challenge: | Recent work shows successful methods for unsupervised machine translation (UMT) initialization stage is important since bad initialization may wrongly squeeze the search space and too much noise may hurt the final performance. |
| Approach: | They propose a retrieval and rewriting based method to better initialize unsupervised translation models. |
| Outcome: | The proposed method improves translation performance by over 4 BLEU scores. |
Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages (2024.acl-long)
Copied to clipboard
| Challenge: | Multilingual neural machine translation systems learn to map sentences of different languages into a common representation space. |
| Approach: | They propose a setup where we decouple learning of vocabulary and syntax and train to translate while keeping those word representations frozen. |
| Outcome: | The proposed setup achieves near parity with a supervised setting on the TED domain with varying number of languages seen by the encoder. |
On the Role of Parallel Data in Cross-lingual Transfer Learning (2023.findings-acl)
Copied to clipboard
| Challenge: | Existing multilingual models do not exploit the full potential of monolingual data, a new study finds . prior work has shown that parallel data is beneficial for cross-lingual learning, but it is unclear if it is the data itself or the modeling of parallel interactions that matters. |
| Approach: | They compare unsupervised machine translation to supervised machine translator and gold parallel data to generate synthetic parallel data. |
| Outcome: | The proposed model generated parallel data is better than supervised machine translation and gold parallel data in both general and task-specific settings. |
Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing models require large amounts of image-caption data for pre-training . existing models require expensive data collection and curation . |
| Approach: | They propose to conduct "mask-and-predict" pre-training on text-only and image-only corpora and introduce the object tags detected by an object recognition model as anchor points to bridge two modalities. |
| Outcome: | The proposed approach achieves performance close to a model pre-trained with aligned data, on four English benchmarks. |
Machine Translation With Weakly Paired Documents (D19-1)
Copied to clipboard
| Challenge: | Recent studies explore the possibility of unsupervised machine translation with monolingual data only. |
| Approach: | They propose a method to mine bilingual sentences from weakly paired documents . they use word distribution-level alignments to constrain word distributions of two weakly-paired documents. |
| Outcome: | The proposed method outperforms previous results on six translation tasks using weakly paired bilingual documents and a large number of bilingual sentences. |
Bilingual Lexicon Induction through Unsupervised Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Existing methods for bilingual lexicon induction use nearest neighbor or related retrieval methods to induce word translation pairs. |
| Approach: | They propose a method that aligns word embeddings in two languages and uses them to build a phrase-table and a language model to extract the bilingual lexicon. |
| Outcome: | The proposed method improves accuracy 6 points over nearest neighbor and 4 points over CSLS retrieval on the same cross-lingual embeddings. |
Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning (2020.acl-main)
Copied to clipboard
| Challenge: | Recent neural network models have achieved impressive performance on sentiment classification in English and other languages. |
| Approach: | They propose an unsupervised sentiment classification model that leverages an uncontrolled machine translation system and a language discriminator to learn a shared representation. |
| Outcome: | The proposed model outperforms other models on five language pairs. |
Paraphrase Generation as Unsupervised Machine Translation (2022.coling-1)
Copied to clipboard
| Challenge: | Existing methods for paraphrase generation rely on labeled datasets or are limited in narrow domains. |
| Approach: | They propose a paradigm for paraphrase generation by treating the task as unsupervised machine translation based on pairs of unlabeled monolingual sentences. |
| Outcome: | The proposed paradigm can generate paraphrases on a large unlabeled monolingual corpus without relying on bilingual sentence pairs. |
Quick Back-Translation for Unsupervised Machine Translation (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Unsupervised machine translation models are limited by the run-time of autoregressive inference during back-translation and lack of synthetic data efficiency. |
| Approach: | They propose a two-for-one improvement to Transformer back-translation: Quick Back-Translation (QBT). QBT re-purposes the encoder as a generative model, and uses encoder-generated sequences to train the decoder. |
| Outcome: | Experiments on various WMT benchmarks show that QBT dramatically outperforms standard back-translation only method in terms of training efficiency for comparable translation qualities. |
Generating Classical Chinese Poems from Vernacular Chinese (D19-1)
Copied to clipboard
| Challenge: | Existing models for classical Chinese poetry generation only allow users to use keywords to interfere with the meaning of generated poems. |
| Approach: | They propose a model to generate classical Chinese poems from vernacular . their model uses unsupervised machine translation to generate Chinese poems . human evaluation shows it can generate high-quality poems comparable to amateur poems - authors . |
| Outcome: | The proposed model improves the perplexity and BLEU of the proposed model compared with typical models and human evaluation shows it generates high-quality poems comparable to amateur poems. |
A Call for More Rigor in Unsupervised Cross-lingual Learning (2020.acl-main)
Copied to clipboard
| Challenge: | Existing research on unsupervised cross-lingual learning has focused on purely unsupervised learning without any parallel data for most of the world's languages. |
| Approach: | They propose to define "multilingual learning" as learning a common model for two or more languages from raw text, without any downstream task labels. |
| Outcome: | The proposed model is based on a model with no parallel data and abundant monolingual data. |