Related papers: Margin-based Parallel Corpus Mining with Multiling…
This paper presents an effective approach for parallel corpus mining using bilingual sentence embeddings. Our embedding models are trained to produce similar representations exclusively for bilingual sentence pairs that are translations of…
We learn a joint multilingual sentence embedding and use the distance between sentences in different languages to filter noisy parallel data and to mine for parallel data in large news collections. We are able to improve a competitive…
In this paper, we present an approach to learn multilingual sentence embeddings using a bi-directional dual-encoder with additive margin softmax. The embeddings are able to achieve state-of-the-art results on the United Nations (UN)…
Existing models of multilingual sentence embeddings require large parallel data resources which are not available for low-resource languages. We propose a novel unsupervised method to derive multilingual sentence embeddings relying only on…
We describe an unsupervised method to create pseudo-parallel corpora for machine translation (MT) from unaligned text. We use multilingual BERT to create source and target sentence embeddings for nearest-neighbor search and adapt the model…
Multilingual pretraining typically lacks explicit alignment signals, leading to suboptimal cross-lingual alignment in the representation space. In this work, we show that training standard pretrained models for cross-lingual alignment with…
Lecture transcript translation helps learners understand online courses, however, building a high-quality lecture machine translation system lacks publicly available parallel corpora. To address this, we examine a framework for parallel…
A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through…
In this paper we propose a novel method of augmenting parallel text corpora which promises good quality and is also capable of producing many fold larger corpora than the seed corpus we start with. We do not need any additional monolingual…
Web-crawled data provides a good source of parallel corpora for training machine translation models. It is automatically obtained, but extremely noisy, and recent work shows that neural machine translation systems are more sensitive to…
We show that margin-based bitext mining in a multilingual sentence space can be applied to monolingual corpora of billions of sentences. We are using ten snapshots of a curated common crawl corpus (Wenzek et al., 2019) totalling 32.7…
Parallel sentences are a relatively scarce but extremely useful resource for many applications including cross-lingual retrieval and statistical machine translation. This research explores our new methodologies for mining such data from…
Parallel texts are a relatively rare language resource, however, they constitute a very useful research material with a wide range of applications. This study presents and analyses new methodologies we developed for obtaining such data from…
Recent advances in cross-lingual word embeddings have primarily relied on mapping-based methods, which project pretrained word embeddings from different languages into a shared space through a linear transformation. However, these…
Parallel sentences are a relatively scarce but extremely useful resource for many applications including cross-lingual retrieval and statistical machine translation. This research explores our methodology for mining such data from…
Recent machine translation algorithms mainly rely on parallel corpora. However, since the availability of parallel corpora remains limited, only some resource-rich language pairs can benefit from them. We constructed a parallel corpus for…
Objective: Today's neural machine translation (NMT) can achieve near human-level translation quality and greatly facilitates international communications, but the lack of parallel corpora poses a key problem to the development of…
Recent studies have highlighted the potential of exploiting parallel corpora to enhance multilingual large language models, improving performance in both bilingual tasks, e.g., machine translation, and general-purpose tasks, e.g., text…
We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to force the source and…
With a large amount of parallel data, neural machine translation systems are able to deliver human-level performance for sentence-level translation. However, it is costly to label a large amount of parallel data by humans. In contrast,…