Quality Estimation (QE) for machine translation aims to evaluate translation quality without reference translations. The WMT 2022 competition introduced a novel QE task focused on predicting MQM labels, i.e. human annotations for the locations, ...

How to effectively model global context has been a critical challenge for document-level neural machine translation (NMT). Both preceding and global context have been carefully explored in the sequence-to-sequence (seq2seq) framework. However, previous ...

Sentence alignment is a basic task in natural language processing which aims to extract high-quality parallel sentences automatically. Motivated by the observation that aligned sentence pairs contain a larger number of aligned words than unaligned ...

Sentence alignment provides multi-lingual or cross-lingual natural language processing (NLP) applications with high-quality parallel sentence pairs. Normally, an aligned sentence pair contains multiple aligned words, which intuitively play ...

There are a large number of expression forms and semantic information in natural language, which contain fake, speculative, and fuzzy statements. Identifying event factuality is vital to various natural language applications, such as information ...

Document-level Machine Translation (MT) has been drawing more and more attention due to its potential of resolving sentence-level ambiguities and inconsistencies with the benefit of wide-range context. However, the lack of simple yet effective ...

Tense is a small element to a sentence, however, error tense can raise odd grammars and result in misunderstanding. Recently, tense has drawn attention in many natural language processing applications. However, most of current Statistical Machine ...

N-gram-based metrics have been used widely in automatic evaluation of machine translation. However, most of them also lose merits due to the strict policy of matching of n-grams. Especially, the policy of exact matching leads to take synonyms as totally ...

Statistical machine translation systems are usually trained on a large amount of bilingual sentence pairs and translate one sentence at a time, ignoring document-level information. In this paper, we propose a cache-based approach to document-level ...

With the development of grid service technology, the grid service matching becomes a hot-spot. Service matching is one of the key technologies that can effectively improve the reuse of resources. After analyzing the reason of the lack of communication ...

Currently, there are many researches focusing on grid scheduling and more and more scheduling algorithms were proposed. However, those algorithms are not satisfied with the requirement of the grid for ignoring its characteristics of dynamics, autonomy, ...

Information Service in the Grid provides the ability to discover and monitor resources which is fundamental for the Grid infrastructure. A framework of a tree-based Grid Information Service (TGIS) is proposed in this paper. This framework is based on GT ...