Related papers: An Efficient Approach for Machine Translation on L…
Many-to-one neural machine translation systems improve over one-to-one systems when training data is scarce. In this paper, we design and test a novel algorithm for selecting the language of minibatches when training such systems. The…
The success of Neural Machine Translation (NMT) largely depends on the availability of large bitext training corpora. Due to the lack of such large corpora in low-resource language pairs, NMT systems often exhibit poor performance. Extra…
In this paper, we address the task of improving pair-wise machine translation for specific low resource Indian languages. Multilingual NMT models have demonstrated a reasonable amount of effectiveness on resource-poor languages. In this…
In this paper, we describe our submission to the WMT19 low-resource parallel corpus filtering shared task. Our main approach is based on the LASER toolkit (Language-Agnostic SEntence Representations), which uses an encoder-decoder…
Despite the recent developments in the field of cross-modal retrieval, there has been less research focusing on low-resource languages due to the lack of manually annotated datasets. In this paper, we propose a noise-robust cross-lingual…
Cross-lingual transfer is important for developing high-quality chatbots in multiple languages due to the strongly imbalanced distribution of language resources. A typical approach is to leverage off-the-shelf machine translation (MT)…
Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However,…
Multilingual sentence representations pose a great advantage for low-resource languages that do not have enough data to build monolingual models on their own. These multilingual sentence representations have been separately exploited by few…
Multilingual Neural Machine Translation (MNMT) enables one system to translate sentences from multiple source languages to multiple target languages, greatly reducing deployment costs compared with conventional bilingual systems. The MNMT…
When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample…
Although the curse of multilinguality significantly restricts the language abilities of multilingual models in monolingual settings, researchers now still have to rely on multilingual models to develop state-of-the-art systems in Vietnamese…
Resources for the non-English languages are scarce and this paper addresses this problem in the context of machine translation, by automatically extracting parallel sentence pairs from the multilingual articles available on the Internet. In…
Machine translation for Vietnamese-English in the medical domain is still an under-explored research area. In this paper, we introduce MedEV -- a high-quality Vietnamese-English parallel dataset constructed specifically for the medical…
Multilingual models have been widely used for cross-lingual transfer to low-resource languages. However, the performance on these languages is hindered by their underrepresentation in the pretraining data. To alleviate this problem, we…
Machine Translation (MT) has been widely used for cross-lingual classification, either by translating the test set into English and running inference with a monolingual model (translate-test), or translating the training set into the target…
This paper investigates the challenges and potential solutions for improving machine learning systems for low-resource languages. State-of-the-art models in natural language processing (NLP), text-to-speech (TTS), speech-to-text (STT), and…
Unsupervised neural machine translation (UNMT) that relies solely on massive monolingual corpora has achieved remarkable results in several translation tasks. However, in real-world scenarios, massive monolingual corpora do not exist for…
Neural Machine Translation (NMT) performs poor on the low-resource language pair $(X,Z)$, especially when $Z$ is a rare language. By introducing another rich language $Y$, we propose a novel triangular training architecture (TA-NMT) to…
The scarcity of large parallel corpora is an important obstacle for neural machine translation. A common solution is to exploit the knowledge of language models (LM) trained on abundant monolingual data. In this work, we propose a novel…
In natural language processing, pre-trained language models have become essential infrastructures. However, these models often suffer from issues such as large size, long inference time, and challenging deployment. Moreover, most mainstream…