Related papers: NAIST-SIC-Aligned: an Aligned English-Japanese Sim…
In Simultaneous Machine Translation (SiMT) systems, training with a simultaneous interpretation (SI) corpus is an effective method for achieving high-quality yet low-latency systems. However, it is very challenging to curate such a corpus…
Simultaneous interpretation (SI), the translation of one language to another in real time, starts translation before the original speech has finished. Its evaluation needs to consider both latency and quality. This trade-off is challenging…
This paper analyzes the features of monotonic translations, which follow the word order of the source language, in simultaneous interpreting (SI). Word order differences are one of the biggest challenges in SI, especially for language pairs…
Multimodal neural machine translation (NMT) has become an increasingly important area of research over the years because additional modalities, such as image data, can provide more context to textual data. Furthermore, the viability of…
Sentence-level (SL) machine translation (MT) has reached acceptable quality for many high-resourced languages, but not document-level (DL) MT, which is difficult to 1) train with little amount of DL data; and 2) evaluate, as the main…
Simultaneous speech translation (SimulST) translates partial speech inputs incrementally. Although the monotonic correspondence between input and output is preferable for smaller latency, it is not the case for distant language pairs such…
In this paper, we propose a two-phase training approach where pre-trained large language models are continually pre-trained on parallel data and then supervised fine-tuned with a small amount of high-quality parallel data. To investigate…
Objective: Today's neural machine translation (NMT) can achieve near human-level translation quality and greatly facilitates international communications, but the lack of parallel corpora poses a key problem to the development of…
Lecture transcript translation helps learners understand online courses, however, building a high-quality lecture machine translation system lacks publicly available parallel corpora. To address this, we examine a framework for parallel…
Simultaneous Machine Translation (SiMT) aims to yield a real-time partial translation with a monotonically growing the source-side context. However, there is a counterintuitive phenomenon about the context usage between training and…
Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT with four…
Simultaneous machine translation (SimulMT) models start translation before the end of the source sentence, making the translation monotonically aligned with the source sentence. However, the general full-sentence translation test set is…
The massive amounts of web-mined parallel data contain large amounts of noise. Semantic misalignment, as the primary source of the noise, poses a challenge for training machine translation systems. In this paper, we first introduce a…
Lectures translation is a case of spoken language translation and there is a lack of publicly available parallel corpora for this purpose. To address this, we examine a language independent framework for parallel corpus mining which is a…
While the progress of machine translation of written text has come far in the past several years thanks to the increasing availability of parallel corpora and corpora-based training technologies, automatic translation of spoken text and…
Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional encoder-decoder policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT…
The ability of transformers to perform precision tasks such as question answering, Natural Language Inference (NLI) or summarising, have enabled them to be ranked as one of the best paradigm to address Natural Language Processing (NLP)…
Recent machine translation algorithms mainly rely on parallel corpora. However, since the availability of parallel corpora remains limited, only some resource-rich language pairs can benefit from them. We constructed a parallel corpus for…
The effectiveness of a statistical machine translation system (SMT) is very dependent upon the amount of parallel corpus used in the training phase. For low-resource language pairs there are not enough parallel corpora to build an accurate…
Web-crawled data provides a good source of parallel corpora for training machine translation models. It is automatically obtained, but extremely noisy, and recent work shows that neural machine translation systems are more sensitive to…