相关论文: Parallel Attention Forcing for Machine Translation

Transformer-based models have emerged as a leading architecture for natural language processing, natural language generation, and image generation tasks. A fundamental element of the transformer architecture is self-attention, which allows…

Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training…

Lattices are an efficient and effective method to encode ambiguity of upstream systems in natural language processing tasks, for example to compactly capture multiple speech recognition hypotheses, or to represent multiple linguistic…

Recent studies show that the attention heads in Transformer are not equal. We relate this phenomenon to the imbalance training of multi-head attention and the model dependence on specific heads. To tackle this problem, we propose a simple…

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

Multi-Task Learning (MTL) is widely-accepted in Natural Language Processing as a standard technique for learning multiple related tasks in one model. Training an MTL model requires having the training data for all tasks available at the…

This work investigates the alignment problem in state-of-the-art multi-head attention models based on the transformer architecture. We demonstrate that alignment extraction in transformer models can be improved by augmenting an additional…

While current state-of-the-art NMT models, such as RNN seq2seq and Transformers, possess a large number of parameters, they are still shallow in comparison to convolutional models used for both text and vision applications. In this work we…

Neural Machine Translation (NMT) models are known to suffer from noisy inputs. To make models robust, we generate adversarial augmentation samples that attack the model and preserve the source-side semantic meaning at the same time. To…

Attention mechanisms represent a fundamental paradigm shift in neural network architectures, enabling models to selectively focus on relevant portions of input sequences through learned weighting functions. This monograph provides a…

Simultaneous machine translation (SimulMT) speeds up the translation process by starting to translate before the source sentence is completely available. It is difficult due to limited context and word order difference between languages.…

Standard context-aware neural machine translation (NMT) typically relies on parallel document-level data, exploiting both source and target contexts. Concatenation-based approaches in particular, still a strong baseline for document-level…

Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging,…

Deep neural networks, including recurrent networks, have been successfully applied to human activity recognition. Unfortunately, the final representation learned by recurrent networks might encode some noise (irrelevant signal components,…

Large Language Model (LLM) based text-to-speech (TTS) systems have demonstrated remarkable capabilities in handling large speech datasets and generating natural speech for new speakers. However, LLM-based TTS models are not robust as the…

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…

Pivot-based neural machine translation (NMT) is commonly used in low-resource setups, especially for translation between non-English language pairs. It benefits from using high resource source-pivot and pivot-target language pairs and an…

This paper rethinks translation memory augmented neural machine translation (TM-augmented NMT) from two perspectives, i.e., a probabilistic view of retrieval and the variance-bias decomposition principle. The finding demonstrates that…

Neural Machine Translation (NMT) can be used to generate fluent output. As such, language models have been investigated for incorporation with NMT. In prior investigations, two models have been used: a translation model and a language…

Learned self-attention functions in state-of-the-art NLP models often correlate with human attention. We investigate whether self-attention in large-scale pre-trained language models is as predictive of human eye fixation patterns during…