Related papers: LCS: A Language Converter Strategy for Zero-Shot N…
Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…
Sign Language Translation (SLT) aims to automatically convert visual sign language videos into spoken language text and vice versa. While recent years have seen rapid progress, the true sources of performance improvements often remain…
Neural machine translation (NMT) takes deterministic sequences for source representations. However, either word-level or subword-level segmentations have multiple choices to split a source sequence with different word segmentors or…
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)…
Multilingual neural machine translation systems learn to map sentences of different languages into a common representation space. Intuitively, with a growing number of seen languages the encoder sentence representation grows more flexible…
Code-switching (CS) speech translation (ST) aims to translate speech that alternates between multiple languages into a target language text, posing significant challenges due to the complexity of semantic modeling and the scarcity of CS…
Pre-trained multilingual language encoders, such as multilingual BERT and XLM-R, show great potential for zero-shot cross-lingual transfer. However, these multilingual encoders do not precisely align words and phrases across languages.…
Language models (LMs) are bound to their tokenizer, which maps raw text to a sequence of vocabulary items (tokens). This restricts their flexibility: for example, LMs trained primarily on English may still perform well in other natural and…
Sign language translation (SLT) addresses the problem of translating information from a sign language in video to a spoken language in text. Existing studies, while showing progress, are often limited to narrow domains and/or few sign…
Label smoothing and vocabulary sharing are two widely used techniques in neural machine translation models. However, we argue that simply applying both techniques can be conflicting and even leads to sub-optimal performance. When allocating…
End-to-end Spoken Language Understanding (SLU) models are made increasingly large and complex to achieve the state-ofthe-art accuracy. However, the increased complexity of a model can also introduce high risk of over-fitting, which is a…
Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to…
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…
In a multilingual neural machine translation model that fully shares parameters across all languages, an artificial language token is usually used to guide translation into the desired target language. However, recent studies show that…
Instruction tuning (IT) is widely used to teach pretrained large language models (LLMs) to follow arbitrary instructions, but is under-studied in multilingual settings. In this work, we conduct a systematic study of zero-shot cross-lingual…
In neural machine translation, a source sequence of words is encoded into a vector from which a target sequence is generated in the decoding phase. Differently from statistical machine translation, the associations between source words and…
Recent research has shown that independently trained encoders and decoders, combined through a shared fixed-size representation, can achieve competitive performance in speech-to-text translation. In this work, we show that this type of…
Machine transliteration is the process of automatically transforming the script of a word from a source language to a target language, while preserving pronunciation. Sequence to sequence learning has recently emerged as a new paradigm in…
Learning what to share between tasks has been a topic of great importance recently, as strategic sharing of knowledge has been shown to improve downstream task performance. This is particularly important for multilingual applications, as…
Cross-lingual adaptation has proven effective in spoken language understanding (SLU) systems with limited resources. Existing methods are frequently unsatisfactory for intent detection and slot filling, particularly for distant languages…