Related papers: Leveraging Discourse Rewards for Document-Level Ne…
It is well-known that document context is vital for resolving a range of translation ambiguities, and in fact the document setting is the most natural setting for nearly all translation. It is therefore unfortunate that machine translation…
We present Neural Machine Translation (NMT) training using document-level metrics with batch-level documents. Previous sequence-objective approaches to NMT training focus exclusively on sentence-level metrics like sentence BLEU which do not…
This paper presents a novel semantic-based phrase translation model. A pair of source and target phrases are projected into continuous-valued vector representations in a low-dimensional latent semantic space, where their translation score…
Recent advancements in large language models (LLMs) have demonstrated their remarkable capabilities across various language tasks. Inspired by the success of text-to-text translation refinement, this paper investigates how LLMs can improve…
Reinforcement learning from human feedback (RLHF) is a recent technique to improve the quality of the text generated by a language model, making it closer to what humans would generate. A core ingredient in RLHF's success in aligning and…
Pretrained language models (PLMs) have produced substantial improvements in discourse-aware neural machine translation (NMT), for example, improved coherence in spoken language translation. However, the underlying reasons for their strong…
The quality of a Neural Machine Translation system depends substantially on the availability of sizable parallel corpora. For low-resource language pairs this is not the case, resulting in poor translation quality. Inspired by work in…
The Transformer architecture has led to significant gains in machine translation. However, most studies focus on only sentence-level translation without considering the context dependency within documents, leading to the inadequacy of…
Reinforcement learning (RL) has been proven to be an effective and robust method for training neural machine translation systems, especially when paired with powerful reward models that accurately assess translation quality. However, most…
In Machine Translation, Large Language Models (LLMs) have generally underperformed compared to conventional encoder-decoder systems and thus see limited adoption. However, LLMs excel at modeling contextual information, making them a natural…
In an attempt to improve overall translation quality, there has been an increasing focus on integrating more linguistic elements into Machine Translation (MT). While significant progress has been achieved, especially recently with neural…
Document-level neural machine translation (DocNMT) achieves coherent translations by incorporating cross-sentence context. However, for most language pairs there's a shortage of parallel documents, although parallel sentences are readily…
Monolingual data has been demonstrated to be helpful in improving the translation quality of neural machine translation (NMT). The current methods stay at the usage of word-level knowledge, such as generating synthetic parallel data or…
Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various…
Cross-lingual text summarization aims at generating a document summary in one language given input in another language. It is a practically important but under-explored task, primarily due to the dearth of available data. Existing methods…
While recent advances in deep learning led to significant improvements in machine translation, neural machine translation is often still not able to continuously adapt to the environment. For humans, as well as for machine translation,…
Document-level machine translation manages to outperform sentence level models by a small margin, but have failed to be widely adopted. We argue that previous research did not make a clear use of the global context, and propose a new…
This paper describes the Microsoft Translator submissions to the WMT19 news translation shared task for English-German. Our main focus is document-level neural machine translation with deep transformer models. We start with strong…
Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zeroshot) translation directions not observed at training time. We…
Dense Retrieval (DR) models have proven to be effective for Document Retrieval and Information Grounding tasks. Usually, these models are trained and optimized for improving the relevance of top-ranked documents for a given query. Previous…