Articles

AbstractIn monolingual dense retrieval, lots of works focus on how to distill knowledge from cross-encoder re-ranker to dual-encoder retriever and these methods achieve better performance due to the effectiveness of cross-encoder re-ranker. However, we find that the performance of the cross-encoder re-ranker is heavily influenced by the number of training …...

AbstractIn this paper we revisit automatic metrics for paraphrase evaluation and obtain two findings that disobey conventional wisdom: (1) Reference-free metrics achieve better performance than their reference-based counterparts. (2) Most commonly used metrics do not align well with human annotation. Underlying reasons behind the above findings are explored through additional …...

AbstractPre-trained multilingual language models play an important role in cross-lingual natural language understanding tasks. However, existing methods did not focus on learning the semantic structure of representation, and thus could not optimize their performance. In this paper, we propose Multi-level Multilingual Knowledge Distillation (MMKD), a novel method for improving multilingual …...

AbstractThere is a growing body of work in recent years to develop pre-trained language models (PLMs) for the Arabic language. This work addresses two major problems in existing Arabic PLMs that limit the progress of the Arabic NLU and NLG fields. First, existing Arabic PLMs are not well-explored and their …...

AbstractOpinion summarization of multiple reviews suffers from the lack of reference summaries for training. Most previous approaches construct multiple reviews and their summary based on textual similarities between reviews,resulting in information mismatch between the review input and the summary. In this paper, we convert each review into a mixof structured …...

Warning: This paper contains examples of the language that some people may find offensive. Transformer-based Language models have achieved state-of-the-art performance on a wide range of Natural Language Process- ing (NLP) tasks. This work will examine the effectiveness of transformer language models like BERT, RoBERTa, ALBERT, and DistilBERT on existing …...

“The Filipino Sign Language Act” of RA 11106 states the declaration of Filipino Sign Language (FSL) as the National Sign Language of Filipino deaf citizens. However, the lack of awareness prevails as with the cyberbullying case of Mininio Buhat. This paper takes an initial step into raising awareness with Zee, …...

Visual Question Answering (VQA) has arisen in recent public interest thanks to its appli- cability in many different fields. However, it requires understanding the combination of pictures and questions, which is highly chal- lenging in both vision and language process- ing. Many previous works have achieved re- markable results to …...

Existing knowledge graph-based learning methods for word sense disambiguation use word-to-word relations to learn models, but do not learn using the hierarchical relations of word senses in a single word. In addition, even when defining sentences in a Japanese dictionary are applied, the accuracy of judging the hierarchical relationship of …...

In Word Sense Disambiguation (WSD), several studies have proposed systems that incorporate dictionary glosses. The use of glosses expressed in short sentences can improve the accuracy of the WSD system. However, since many glosses are short sentences, additional lexical information could improve accuracy. In this study, we propose a method …...

AbstractThis paper describes Tencent AI Lab - Shanghai Jiao Tong University (TAL-SJTU) Low-Resource Translation systems for the WMT22 shared task. We participate in the general translation task on English-Livonian.Our system is based on M2M100 with novel techniques that adapt it to the target language pair.(1) Cross-model word embedding alignment: inspired …...

AbstractThis paper describes Lan-Bridge Translation systems for the WMT 2022 General Translation shared task. We participate in 18 language directions: English to and from Czech, German, Ukrainian, Japanese, Russian, Chinese, English to Croatian, French to German, Yakut to and from Russian and Ukrainian to and from Czech.To develop systems covering …...

AbstractManifold’s English-Chinese System at WMT22 is an ensemble of 4 models trained by different configurations with scheduled sampling-based fine-tuning. The four configurations are DeepBig (XenC), DeepLarger (XenC), DeepBig-TalkingHeads (XenC) and DeepBig (LaBSE). Concretely, DeepBig extends Transformer-Big to 24 encoder layers. DeepLarger has 20 encoder layers and its feed-forward network (FFN) …...

AbstractThis paper describes the Inria ALMAnaCH team submission to the WMT 2022 general translation shared task. Participating in the language directions cs,ru,uk→en and cs↔uk, we experiment with the use of a dedicated Latin-script transcription convention aimed at representing all Slavic languages involved in a way that maximises character- and word-level …...

AbstractThis paper presents the system description of Samsung R&D Institute Poland participation in WMT 2022 for General MT solution for medium and low resource languages: Russian and Croatian. Our approach combines iterative noised/tagged back-translation and iterative distillation. We investigated different monolingual resources and compared their influence on final translations. We …...

AbstractIn this paper, we describe our NAIST-NICT-TIT submission to the WMT22 general machine translation task. We participated in this task for the English ↔ Japanese language pair. Our system is characterized as an ensemble of Transformer big models, k-nearest-neighbor machine translation (kNN-MT) (Khandelwal et al., 2021), and reranking.In our translation …...

AbstractThis document describes a fine-grained linguistically motivated analysis of 29 machine translation systems submitted at the Shared Task of the 7th Conference of Machine Translation (WMT22). This submission expands the test suite work of previous years by adding the language direction of English–Russian. As a result, evaluation takes place for …...

AbstractThis paper presents Lingua Custodia’s submission to the WMT22 shared task on Word Level Auto-completion (WLAC). We consider two directions, namely German-English and English-German.The WLAC task in Neural Machine Translation (NMT) consists in predicting a target word given few human typed characters, the source sentence to translate, as well as …...

AbstractTranslation suggestion (TS) models are used to automatically provide alternative suggestions for incorrect spans in sentences generated by machine translation. This paper introduces the system used in our submission to the WMT’22 Translation Suggestion shared task. Our system is based on the ensemble of different translation architectures, including Transformer, SA-Transformer, …...

AbstractThis paper describes the Transn’s submissions to the WMT2022 shared task on TranslationSuggestion. Our team participated on two tasks: Naive Translation Suggestion and TranslationSuggestion with Hints, focusing on two language directions Zh→En and En→Zh. Apart from the golden training data provided by the shared task, we utilized synthetic corpus to …...