Related papers: Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses

Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses

URL: http://arxiv.org/abs/2303.15587v1
Date: Mon, 27 Mar 2023 20:33:40 GMT
Title: Linguistically Informed ChatGPT Prompts to Enhance Japanese-Chinese Machine Translation: A Case Study on Attributive Clauses
Authors: Wenshi Gu
Abstract summary: This paper investigates the issue of correctly translating attributive clauses from Japanese to Chinese. A pre-edit scheme is proposed, which aims to enhance the accuracy of translation. A novel two-step prompt strategy is proposed, which has been demonstrated to improve the average translation accuracy score by over 35%.
Score: 0.0
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: In the field of Japanese-Chinese translation linguistics, the issue of correctly translating attributive clauses has persistently proven to be challenging. Present-day machine translation tools often fail to accurately translate attributive clauses from Japanese to Chinese. In light of this, this paper investigates the linguistic problem underlying such difficulties, namely how does the semantic role of the modified noun affect the selection of translation patterns for attributive clauses, from a linguistic perspective. To ad-dress these difficulties, a pre-edit scheme is proposed, which aims to enhance the accuracy of translation. Furthermore, we propose a novel two-step prompt strategy, which combines this pre-edit scheme with ChatGPT, currently the most widely used large language model. This prompt strategy is capable of optimizing translation input in zero-shot scenarios and has been demonstrated to improve the average translation accuracy score by over 35%.

Related papers

Understanding and Addressing the Under-Translation Problem from the Perspective of Decoding Objective [72.83966378613238]
Under-translation and over-translation remain two challenging problems in state-of-the-art Neural Machine Translation (NMT) systems. We conduct an in-depth analysis on the underlying cause of under-translation in NMT, providing an explanation from the perspective of decoding objective. We propose employing the confidence of predicting End Of Sentence (EOS) as a detector for under-translation, and strengthening the confidence-based penalty to penalize candidates with a high risk of under-translation.
arXiv Detail & Related papers (2024-05-29T09:25:49Z)
The Power of Question Translation Training in Multilingual Reasoning: Broadened Scope and Deepened Insights [108.40766216456413]
We propose a question alignment approach to bridge the gap between large language models' English and non-English performance. Experiment results show that the question alignment approach can be used to boost multilingual performance across diverse reasoning scenarios. To understand the mechanism of its success, we analyze representation space, chain-of-thought and translation data scales.
arXiv Detail & Related papers (2024-05-02T14:49:50Z)
Prompting ChatGPT for Translation: A Comparative Analysis of Translation Brief and Persona Prompts [0.0]
This paper discusses the effectiveness of incorporating the conceptual tool of translation brief and the personas of translator and author into prompt design for translation tasks in ChatGPT. Findings suggest that, although certain elements are constructive in facilitating human-to-human communication for translation tasks, their effectiveness is limited for improving translation quality in ChatGPT. This accentuates the need for explorative research on how translation theorists and practitioners can develop the current set of conceptual tools rooted in the human-to-human communication paradigm for translation purposes in this emerging workflow involving human-to-human interaction.
arXiv Detail & Related papers (2024-02-29T21:05:38Z)
Crossing the Threshold: Idiomatic Machine Translation through Retrieval Augmentation and Loss Weighting [66.02718577386426]
We provide a simple characterization of idiomatic translation and related issues. We conduct a synthetic experiment revealing a tipping point at which transformer-based machine translation models correctly default to idiomatic translations. To improve translation of natural idioms, we introduce two straightforward yet effective techniques.
arXiv Detail & Related papers (2023-10-10T23:47:25Z)
Optimizing Machine Translation through Prompt Engineering: An Investigation into ChatGPT's Customizability [0.0]
The study reveals that the inclusion of suitable prompts in large-scale language models like ChatGPT can yield flexible translations. The research scrutinizes the changes in translation quality when prompts are used to generate translations that meet specific conditions.
arXiv Detail & Related papers (2023-08-02T19:11:04Z)
Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation [66.33340583035374]
We present a comprehensive study on the robustness of current text adversarial attacks to round-trip translation. We demonstrate that 6 state-of-the-art text-based adversarial attacks do not maintain their efficacy after round-trip translation. We introduce an intervention-based solution to this problem, by integrating Machine Translation into the process of adversarial example generation.
arXiv Detail & Related papers (2023-07-24T04:29:43Z)
Decomposed Prompting for Machine Translation Between Related Languages using Large Language Models [55.35106713257871]
We introduce DecoMT, a novel approach of few-shot prompting that decomposes the translation process into a sequence of word chunk translations. We show that DecoMT outperforms the strong few-shot prompting BLOOM model with an average improvement of 8 chrF++ scores across the examined languages.
arXiv Detail & Related papers (2023-05-22T14:52:47Z)
Interactive-Chain-Prompting: Ambiguity Resolution for Crosslingual Conditional Generation with Interaction [38.73550742775257]
A source query in one language may yield several translation options in another language without any extra context. We propose a novel method interactive-chain prompting that reduces translations into a list of subproblems addressing ambiguities. We create a dataset exhibiting different linguistic phenomena which leads to ambiguities at inference for four languages.
arXiv Detail & Related papers (2023-01-24T21:08:13Z)
Example-Based Machine Translation from Text to a Hierarchical Representation of Sign Language [1.3999481573773074]
This article presents an original method for Text-to-Sign Translation. It compensates data scarcity using a domain-specific parallel corpus of alignments between text and hierarchical formal descriptions of Sign Language videos in AZee. Based on the detection of similarities present in the source text, the proposed algorithm exploits matches and substitutions of aligned segments to build multiple candidate translations. The resulting translations are in the form of AZee expressions, designed to be used as input to avatar systems.
arXiv Detail & Related papers (2022-05-06T15:48:43Z)
Self-Attention with Cross-Lingual Position Representation [112.05807284056337]
Position encoding (PE) is used to preserve the word order information for natural language processing tasks, generating fixed position indices for input sequences. Due to word order divergences in different languages, modeling the cross-lingual positional relationships might help SANs tackle this problem. We augment SANs with emphcross-lingual position representations to model the bilingually aware latent structure for the input sentence.
arXiv Detail & Related papers (2020-04-28T05:23:43Z)

This list is automatically generated from the titles and abstracts of the papers in this site.