A novel and robust approach for pro-drop language translation

Abstract

A significant challenge for machine translation (MT) is the phenomena of dropped pronouns (DPs), where certain classes of pronouns are frequently dropped in the source language but should be retained in the target language. In response to this common problem, we propose a semi-supervised approach with a universal framework to recall missing pronouns in translation. Firstly, we build training data for DP generation in which the DPs are automatically labelled according to the alignment information from a parallel corpus. Secondly, we build a deep learning-based DP generator for input sentences in decoding when no corresponding references exist. More specifically, the generation has two phases: (1) DP position detection, which is modeled as a sequential labelling task with recurrent neural networks; and (2) DP prediction, which employs a multilayer perceptron with rich features. Finally, we integrate the above outputs into our statistical MT (SMT) system to recall missing pronouns by both extracting rules from the DP-labelled training data and translating the DPgenerated input sentences. To validate the robustness of our approach, we investigate our approach on both Chinese-English and Japanese-English corpora extracted from movie subtitles. Compared with an SMT baseline system, experimental results show that our approach achieves a significant improvement of +1.58 BLEU points in translation performance with 66% F-score for DP generation accuracy for Chinese-English, and nearly +1 BLEU point with 58% F-score for Japanese-English. We believe that this work could help both MT researchers and industries to boost the performance of MT systems between pro-drop and non-pro-drop languages.

Exploring the Role of First-Person Singular Pronouns in Detecting Suicidal Ideation: A Machine Learning Analysis of Clinical Transcripts

“…This is particularly relevant because one potential explanation for the absence of a significant association between subjective FPSPs and suicidal ideation could be the phenomenon of pro-drop in Chinese. Pro-drop is observed in languages such as Chinese and Japanese, where the subject of a sentence can be dropped without affecting the sentence’s meaning or grammatical structure [ 36 ]. Given that the data analyzed in this study consist of Chinese text, it is highly likely that the prevalence of pro-drop reduced the occurrence of subjective FPSPs, making it challenging to observe a significant effect.…”

PROSE: A Pronoun Omission Solution for Chinese-English Spoken Language Translation

“…Spoken Chinese Contains More Pro-drop Than Literary Language Formally, pro-drop refers to a reference position that is filled with amorphologically unrealized form, and is one of the most common referential options in many languages such as Chinese (Wang et al, 2018a), Japanese (Taira et al, 2012), Korean (Park et al, 2015), and Thai (Kawtrakul et al, 2002). Previous studies have revealed that spoken Chinese language tends to contain more pro-drops than literary language (Wang et al, 2016(Wang et al, , 2017Xu et al, 2021). However, quantitative studies on pro-drops in different genres of spoken Chinese, remain scarce.…”

A multi-level methodology for the automated translation of a coreference resolution dataset: an application to the Italian language

“…In particular, it results in the omission of the subject pronoun. As pointed out by recent studies, this misalignment produces difficulties in the translation process since the missing pronoun is challenging to be reproduced, and it affects the order of dependencies in the sentence [50,51]. For that reason, from a practical point of view, the refinement rules for the target language have been focused on improving the use of personal and possessive pronouns and, in addition, of possessive and demonstrative adjectives.…”