Related papers: A Study of Syntactic Multi-Modality in Non-Autoreg…
Cross-lingual transfer is an effective way to build syntactic analysis tools in low-resource languages. However, transfer is difficult when transferring to typologically distant languages, especially when neither annotated target data nor…
Transfer learning across heterogeneous data distributions (a.k.a. domains) and distinct tasks is a more general and challenging problem than conventional transfer learning, where either domains or tasks are assumed to be the same. While…
Syntax has been proven to be remarkably effective in neural machine translation (NMT). Previous models obtained syntax information from syntactic parsing tools and integrated it into NMT models to improve translation performance. In this…
In sequence prediction tasks like neural machine translation, training with cross-entropy loss often leads to models that overgeneralize and plunge into local optima. In this paper, we propose an extended loss function called \emph{dual…
Accurately modeling idiomatic or non-compositional language has been a longstanding challenge in Natural Language Processing (NLP). This is partly because these expressions do not derive their meanings solely from their constituent words,…
Non-autoregressive (NAR) text-to-speech synthesis relies on length alignment between text sequences and audio representations, constraining naturalness and expressiveness. Existing methods depend on duration modeling or pseudo-alignment…
In the field of Natural Language Processing, there are many tasks that can be tackled effectively using the cross-entropy (CE) loss function. However, the task of dialog generation poses unique challenges for CE loss. This is because CE…
Cross-modal retrieval has drawn wide interest for retrieval across different modalities of data. However, existing methods based on DNN face the challenge of insufficient cross-modal training data, which limits the training effectiveness…
Significant improvements in end-to-end speech translation (ST) have been achieved through the application of multi-task learning. However, the extent to which auxiliary tasks are highly consistent with the ST task, and how much this…
A neural multimodal machine translation (MMT) system is one that aims to perform better translation by extending conventional text-only translation models with multimodal information. Many recent studies report improvements when equipping…
Scalability issue plays a crucial role in productionizing modern recommender systems. Even lightweight architectures may suffer from high computational overload due to intermediate calculations, limiting their practicality in real-world…
Back translation is one of the most widely used methods for improving the performance of neural machine translation systems. Recent research has sought to enhance the effectiveness of this method by increasing the 'diversity' of the…
Entropic optimal transport (EOT) in continuous spaces with quadratic cost is a classical tool for solving the domain translation problem. In practice, recent approaches optimize a weak dual EOT objective depending on a single potential, but…
In real-world systems, scaling has been critical for improving the translation quality in autoregressive translation (AT), which however has not been well studied for non-autoregressive translation (NAT). In this work, we bridge the gap by…
We explore the performance of latent variable models for conditional text generation in the context of neural machine translation (NMT). Similar to Zhang et al., we augment the encoder-decoder NMT paradigm by introducing a continuous latent…
End-to-End Speech Translation (E2E-ST) has seen significant advancements, yet current models are primarily benchmarked on curated, "clean" datasets. This overlooks critical real-world challenges, such as morphological robustness to…
The dominant neural machine translation (NMT) models apply unified attentional encoder-decoder neural networks for translation. Traditionally, the NMT decoders adopt recurrent neural networks (RNNs) to perform translation in a left-toright…
Machine translation (MT) of user-generated content (UGC) poses unique challenges, including handling slang, emotion, and literary devices like irony and sarcasm. Evaluating the quality of these translations is challenging as current metrics…
Neural machine translation (NMT), a new approach to machine translation, has achieved promising results comparable to those of traditional approaches such as statistical machine translation (SMT). Despite its recent success, NMT cannot…
Multi-task learning (MTL) is a widely explored paradigm that enables the simultaneous learning of multiple tasks using a single model. Despite numerous solutions, the key issues of optimization conflict and task imbalance remain…