Related papers: Translation Artifacts in Cross-lingual Transfer Le…
Translations systematically diverge from texts originally produced in the target language, a phenomenon widely referred to as translationese. Translationese has been attributed to production tendencies (e.g. interference, simplification),…
Most studies on word-level Quality Estimation (QE) of machine translation focus on language-specific models. The obvious disadvantages of these approaches are the need for labelled data for each language pair and the high cost required to…
Multilingual modelling can improve machine translation for low-resource languages, partly through shared subword representations. This paper studies the role of subword segmentation in cross-lingual transfer. We systematically compare the…
Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We…
Translating in real-time, a.k.a. simultaneous translation, outputs translation words before the input sentence ends, which is a challenging problem for conventional machine translation methods. We propose a neural machine translation (NMT)…
Most Transformer language models are primarily pretrained on English text, limiting their use for other languages. As the model sizes grow, the performance gap between English and other languages with fewer compute and data resources…
Given a document in a source language, cross-lingual summarization (CLS) aims at generating a concise summary in a different target language. Unlike monolingual summarization (MS), naturally occurring source-language documents paired with…
This paper studies the relative importance of attention heads in Transformer-based models to aid their interpretability in cross-lingual and multi-lingual tasks. Prior research has found that only a few attention heads are important in each…
Shared multilingual representations are essential for cross-lingual tasks and knowledge transfer across languages. This study looks at the impact of parallel data, i.e. translated sentences, in pretraining as a signal to trigger…
Prior research has investigated the impact of various linguistic features on cross-lingual transfer performance. In this study, we investigate the manner in which this effect can be mapped onto the representation space. While past studies…
Current approaches to cross-lingual sentiment analysis try to leverage the wealth of labeled English data using bilingual lexicons, bilingual vector space embeddings, or machine translation systems. Here we show that it is possible to use a…
Natural language tasks like Named Entity Recognition (NER) in the clinical domain on non-English texts can be very time-consuming and expensive due to the lack of annotated data. Cross-lingual transfer (CLT) is a way to circumvent this…
Large-scale generative models show an impressive ability to perform a wide range of Natural Language Processing (NLP) tasks using in-context learning, where a few examples are used to describe a task to the model. For Machine Translation…
Automatic speech recognition and spoken dialogue systems have made great advances through the use of deep machine learning methods. This is partly due to greater computing power but also through the large amount of data available in common…
Task-oriented personal assistants enable people to interact with a host of devices and services using natural language. One of the challenges of making neural dialogue systems available to more users is the lack of training data for all but…
Recent studies show that crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts. Models utilizing these superficial clues gain mirage advantages on the in-domain testing set,…
Sign Language Translation has attained considerable success recently, raising hopes for improved communication with the Deaf. A pre-processing step called tokenization improves the success of translations. Tokens can be learned from sign…
Machine translation (MT) is an important sub-field of natural language processing that aims to translate natural languages using computers. In recent years, end-to-end neural machine translation (NMT) has achieved great success and has…
Zero-resource cross-lingual transfer approaches aim to apply supervised models from a source language to unlabelled target languages. In this paper we perform an in-depth study of the two main techniques employed so far for cross-lingual…
Biases induced to text by generative models have become an increasingly large topic in recent years. In this paper we explore how machine translation might introduce a bias in sentiments as classified by sentiment analysis models. For this,…