Related papers: Mitigating Data Imbalance and Representation Degen…
In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-based statistical methods, thus quickly becoming the state of the art in machine translation (MT). However, NMT systems are limited in…
Current Neural Machine Translation (NMT) employs a language-specific encoder to represent the source sentence and adopts a language-specific decoder to generate target translation. This language-dependent design leads to large-scale network…
Conventional retrieval-augmented neural machine translation (RANMT) systems leverage bilingual corpora, e.g., translation memories (TMs). Yet, in many settings, monolingual corpora in the target language are often available. This work…
Neural machine translation (NMT) has recently gained widespread attention because of its high translation accuracy. However, it shows poor performance in the translation of long sentences, which is a major issue in low-resource languages.…
Multimodal machine translation (MMT) aims to improve translation quality by incorporating information from other modalities, such as vision. Previous MMT systems mainly focus on better access and use of visual information and tend to…
Large language models have significantly advanced Multilingual Machine Translation (MMT), yet scaling to many languages while keeping quality robust across directions remains challenging. In this paper, we identify a failure mode of…
The long-tail distribution of the visual world poses great challenges for deep learning based classification models on how to handle the class imbalance problem. Existing solutions usually involve class-balancing strategies, e.g., by loss…
Multi-source translation systems translate from multiple languages to a single target language. By using information from these multiple sources, these systems achieve large gains in accuracy. To train these systems, it is necessary to have…
Cross-lingual cross-modal retrieval has garnered increasing attention recently, which aims to achieve the alignment between vision and target language (V-T) without using any annotated V-T data pairs. Current methods employ machine…
Class imbalance, which is also called long-tailed distribution, is a common problem in classification tasks based on machine learning. If it happens, the minority data will be overwhelmed by the majority, which presents quite a challenge…
Real-world data typically follow a long-tailed distribution, where a few majority categories occupy most of the data while most minority categories contain a limited number of samples. Classification models minimizing cross-entropy struggle…
The many-to-many multilingual neural machine translation can be regarded as the process of integrating semantic features from the source sentences and linguistic features from the target sentences. To enhance zero-shot translation, models…
Neural machine translation (NMT) systems require large amounts of high quality in-domain parallel corpora for training. State-of-the-art NMT systems still face challenges related to out-of-vocabulary words and dealing with low-resource…
Understanding representation transfer in multilingual neural machine translation (MNMT) can reveal the reason for the zero-shot translation deficiency. In this work, we systematically analyze the representational issue of MNMT models. We…
While neural machine translation (NMT) has become the new paradigm, the parameter optimization requires large-scale parallel data which is scarce in many domains and language pairs. In this paper, we address a new translation scenario in…
Machine Translation System (MTS) serves as an effective tool for communication by translating text or speech from one language to another language. The need of an efficient translation system becomes obvious in a large multilingual…
Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…
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…
Multilingual machine translation (MMT), trained on a mixture of parallel and monolingual data, is key for improving translation in low-resource language pairs. However, the literature offers conflicting results on the performance of…
Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often…