Related papers: Multilingual Document-Level Translation Enables Ze…
Multi-lingual contextualized embeddings, such as multilingual-BERT (mBERT), have shown success in a variety of zero-shot cross-lingual tasks. However, these models are limited by having inconsistent contextualized representations of…
Neural Machine Translation (NMT) can be improved by including document-level contextual information. For this purpose, we propose a hierarchical attention model to capture the context in a structured and dynamic manner. The model is…
We present a document-level neural machine translation model which takes both source and target document context into account using memory networks. We model the problem as a structured prediction problem with interdependencies among the…
Zero-shot cross-lingual transfer is when a multilingual model is trained to perform a task in one language and then is applied to another language. Although the zero-shot cross-lingual transfer approach has achieved success in various…
Multilingual Neural Machine Translation (MNMT) models leverage many language pairs during training to improve translation quality for low-resource languages by transferring knowledge from high-resource languages. We study the quality of a…
Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by…
Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training…
Existing work in document-level neural machine translation commonly concatenates several consecutive sentences as a pseudo-document, and then learns inter-sentential dependencies. This strategy limits the model's ability to leverage…
Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document. Recent works in context-aware NMT consider only a few previous sentences as context and may…
Cross-lingual transfer has become a crucial aspect of multilingual NLP, as it allows for models trained on resource-rich languages to be applied to low-resource languages more effectively. Recently massively multilingual pre-trained…
Multilingual language models achieve impressive zero-shot accuracies in many languages in complex tasks such as Natural Language Inference (NLI). Examples in NLI (and equivalent complex tasks) often pertain to various types of sub-tasks,…
For many (minority) languages, the resources needed to train large models are not available. We investigate the performance of zero-shot transfer learning with as little data as possible, and the influence of language similarity in this…
Zero-shot translation is a promising direction for building a comprehensive multilingual neural machine translation~(MNMT) system. However, its quality is still not satisfactory due to off-target issues. In this paper, we aim to understand…
How to achieve neural machine translation with limited parallel data? Existing techniques often rely on large-scale monolingual corpora, which is impractical for some low-resource languages. In this paper, we turn to connect several…
Massively Multilingual Transformer based Language Models have been observed to be surprisingly effective on zero-shot transfer across languages, though the performance varies from language to language depending on the pivot language(s) used…
Multi-lingual language models (LM), such as mBERT, XLM-R, mT5, mBART, have been remarkably successful in enabling natural language tasks in low-resource languages through cross-lingual transfer from high-resource ones. In this work, we try…
Code-switching is a common phenomenon among multilingual speakers, where alternation between two or more languages occurs within the context of a single conversation. While multilingual humans can seamlessly switch back and forth between…
End-to-end neural machine translation has overtaken statistical machine translation in terms of translation quality for some language pairs, specially those with large amounts of parallel data. Besides this palpable improvement, neural…
Machine translation has an undesirable propensity to produce "translationese" artifacts, which can lead to higher BLEU scores while being liked less by human raters. Motivated by this, we model translationese and original (i.e. natural)…
Many document-level neural machine translation (NMT) systems have explored the utility of context-aware architecture, usually requiring an increasing number of parameters and computational complexity. However, few attention is paid to the…