One of the difficulties of neural machine translation (NMT) is the recall and appropriate translation of low-frequency words or phrases. In this paper, we propose a simple, fast, and effective method for recalling previously seen translation examples and incorporating them into the NMT decoding process. Specifically, for an input sentence, we use a search engine to retrieve sentence pairs whose source sides are similar with the input sentence, and then collect n-grams that are both in the retrieved target sentences and aligned with words that match in the source sentences, which we call "translation pieces". We compute pseudoprobabilities for each retrieved sentence based on similarities between the input sentence and the retrieved source sentences, and use these to weight the retrieved translation pieces. Finally, an existing NMT model is used to translate the input sentence, with an additional bonus given to outputs that contain the collected translation pieces. We show our method improves NMT translation results up to 6 BLEU points on three narrow domain translation tasks where repetitiveness of the target sentences is particularly salient. It also causes little increase in the translation time, and compares favorably to another alternative retrievalbased method with respect to accuracy, speed, and simplicity of implementation.1 Note that there are existing retrieval-based methods for phrase-based and hierarchical phrase-based translation (Lopez, 2007;Germann, 2015). However, these methods do not improve translation quality but rather aim to improve the efficiency of the translation models.
Instance weighting has been widely applied to phrase-based machine translation domain adaptation. However, it is challenging to be applied to Neural Machine Translation (NMT) directly, because NMT is not a linear model. In this paper, two instance weighting technologies, i.e., sentence weighting and domain weighting with a dynamic weight learning strategy, are proposed for NMT domain adaptation. Empirical results on the IWSLT English-German/French tasks show that the proposed methods can substantially improve NMT performance by up to 2.7-6.7 BLEU points, outperforming the existing baselines by up to 1.6-3.6 BLEU points.
Constituent parsing is typically modeled by a chart-based algorithm under probabilistic context-free grammars or by a transition-based algorithm with rich features. Previous models rely heavily on richer syntactic information through lexicalizing rules, splitting categories, or memorizing long histories. However enriched models incur numerous parameters and sparsity issues, and are insufficient for capturing various syntactic phenomena. We propose a neural network structure that explicitly models the unbounded history of actions performed on the stack and queue employed in transition-based parsing, in addition to the representations of partially parsed tree structure. Our transition-based neural constituent parsing achieves performance comparable to the state-of-the-art parsers, demonstrating F1 score of 90.68% for English and 84.33% for Chinese, without reranking, feature templates or additional data to train model parameters.
Neural machine translation (NMT) with recurrent neural networks, has proven to be an effective technique for end-to-end machine translation. However, in spite of its promising advances over traditional translation methods, it typically suffers from an issue of unbalanced outputs, that arise from both the nature of recurrent neural networks themselves, and the challenges inherent in machine translation. To overcome this issue, we propose an agreement model for neural machine translation and show its effectiveness on large-scale Japaneseto-English and Chinese-to-English translation tasks. Our results show the model can achieve improvements of up to 1.4 BLEU over the strongest baseline NMT system. With the help of an ensemble technique, this new end-to-end NMT approach finally outperformed phrasebased and hierarchical phrase-based Moses baselines by up to 5.6 BLEU points.
This paper proposes the automatic generation of Fill-in-the-Blank Questions (FBQs) together with testing based on Item Response Theory (IRT) to measure English proficiency. First, the proposal generates an FBQ from a given sentence in English. The position of a blank in the sentence is determined, and the word at that position is considered as the correct choice. The candidates for incorrect choices for the blank are hypothesized through a thesaurus. Then, each of the candidates is verified by using the Web. Finally, the blanked sentence, the correct choice and the incorrect choices surviving the verification are together laid out to form the FBQ. Second, the proficiency of nonnative speakers who took the test consisting of such FBQs is estimated through IRT.Our experimental results suggest that: (1) the generated questions plus IRT estimate the non-native speakers' English proficiency; (2) while on the other hand, the test can be completed almost perfectly by English native speakers; and (3) the number of questions can be reduced by using item information in IRT.The proposed method provides teachers and testers with a tool that reduces time and expenditure for testing English proficiency.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.