Articles

AbstractContext-aware neural machine translation (NMT) incorporates contextual information of surrounding texts, that can improve the translation quality of document-level machine translation. Many existing works on context-aware NMT have focused on developing new model architectures for incorporating additional contexts and have shown some promising results. However, most of existing works rely …...

AbstractQuality Estimation, as a crucial step of quality control for machine translation, has been explored for years. The goal is to to investigate automatic methods for estimating the quality of machine translation results without reference translations. In this year’s WMT QE shared task, we utilize the large-scale XLM-Roberta pre-trained model …...

AbstractSimultaneous translation is a task in which translation begins before the speaker has finished speaking, so it is important to decide when to start the translation process. However, deciding whether to read more input words or start to translate is difficult for language pairs with different word orders such as …...

AbstractThis paper presents the NICT Kyoto submission for the WMT’21 Quality Estimation (QE) Critical Error Detection shared task (Task 3). Our approach relies mainly on QE model pretraining for which we used 11 language pairs, three sentence-level and three word-level translation quality metrics. Starting from an XLM-R checkpoint, we perform …...

AbstractThis paper describes Papago submission to the WMT 2021 Quality Estimation Task 1: Sentence-level Direct Assessment. Our multilingual Quality Estimation system explores the combination of Pretrained Language Models and Multi-task Learning architectures. We propose an iterative training pipeline based on pretraining with large amounts of in-domain synthetic data and finetuning …...

AbstractRecent work in simultaneous machine translation is often trained with conventional full sentence translation corpora, leading to either excessive latency or necessity to anticipate as-yet-unarrived words, when dealing with a language pair whose word orders significantly differ. This is unlike human simultaneous interpreters who produce largely monotonic translations at the …...

AbstractLarge web-crawled corpora represent an excellent resource for improving the performance of Neural Machine Translation (NMT) systems across several language pairs. However, since these corpora are typically extremely noisy, their use is fairly limited. Current approaches to deal with this problem mainly focus on filtering using heuristics or single features …...

AbstractRecently a number of approaches have been proposed to improve translation performance for document-level neural machine translation (NMT). However, few are focusing on the subject of lexical translation consistency. In this paper we apply “one translation per discourse” in NMT, and aim to encourage lexical translation consistency for document-level NMT. …...

AbstractScheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus bridging the gap between training and inference. However, vanilla scheduled sampling is merely based on training …...

AbstractNon-autoregressive neural machine translation, which decomposes the dependence on previous target tokens from the inputs of the decoder, has achieved impressive inference speedup but at the cost of inferior accuracy. Previous works employ iterative decoding to improve the translation by applying multiple refinement iterations. However, a serious drawback is that …...

AbstractWe present a simple and effective pretraining strategy – bidirectional training (BiT) for neural machine translation. Specifically, we bidirectionally update the model parameters at the early stage and then tune the model normally. To achieve bidirectional updating, we simply reconstruct the training samples from “src→tgt” to “src+tgt→tgt+src” without any complicated …...

AbstractInspired by mutual information (MI) based feature selection in SVMs and logistic regression, in this paper, we propose MI-based layer-wise pruning: for each layer of a multi-layer neural network, neurons with higher values of MI with respect to preserved neurons in the upper layer are preserved. Starting from the top …...

By using the diplomatic discourse interpreting corpus this study investigates gender effects on interpreters’ style in the framework of multidimensional analysis. The results showed that female and male interpreters share similar interpreting style in regard to dimensional functions of their interpreted texts, characterized by informational production, non-narrative concerns, elaborated reference, …...

Recent publications have highlighted the combination of large-grained and fine- grained indices to tap into syntactic complexity. Yet few studies have examined the writing produced by more advanced academic writers from a cross-linguistic perspective. This paper reports a corpus- based comparison of the native speaker (NS) and the Chinese advanced …...

Speaker verification is an essential task in speech processing with great authentication and surveillance applications. Large-scale datasets have hugely contributed to the suc- cess of neural networks for speaker verifica- tion. However, in low-resource languages, building such massive datasets is infeasible. This paper aims at proposing a speaker verifi- cation …...

Near synonym has become a central issue for lexicon and semantics for the nuances in meaning, distribution and context. This study, drawing upon the MARVS frame- work of Huang et al. (2000) and Chang et al. (2000), aims to carry out the de- scriptive lexical-semantic analysis, elabo- rate the similarities …...

Knowledge-grounded dialogue generation is the process of formulating an informed re- sponse based on both the conversation con- text and external knowledge. Multi-modality in dialogue systems has paved the way for more robust conversational bots. Any multi- modal system seeks to bridge the gap between language and vision by combining …...

Solving natural language inference (NLI) with formal semantics and automated theorem proving has the merit of high precision and interpretability. However, they suffer from non-logical inference such as lexical infer- ence. To overcome this weakness, we propose a human-in-the-loop mechanism in which the user provides non-logical knowledge to the theorem …...

Natural language inference (NLI) is the task of identifying the inferential relation between a text pair. Although neural-based approaches have recently achieved high performance on the NLI task, they are unable to explain their reasoning processes. Symbolic ap- proaches, on the other hand, have the ad- vantage that the reasoning …...

Previous studies conducted within Western schizophrenic patients with formal thought disorder (FTD) have shown that abnormalities occur at different levels of linguistic structures. However, linguistic manifestation of FTD in Mandarin Chinese is rarely discussed in the literature. The principal question concerned in this preliminary study is to explore how people …...