paper-with-me

홈 › Papers

GPT-4 vs. Human Translators: A Comprehensive Evaluation of Translation Quality Across Languages, Domains, and Expertise Levels

2024-07-04 · Jianhao Yan, Pingchuan Yan, Yulong Chen, Judy Li, Xianchao Zhu, Yue Zhang

This study comprehensively evaluates the translation quality of Large Language Models (LLMs), specifically GPT-4, against human translators of varying expertise levels across multiple language pairs and domains. Through carefully designed annotation rounds, we find that GPT-4 performs comparably to junior translators in terms of total errors made but lags behind medium and senior translators. We also observe the imbalanced performance across different languages and domains, with GPT-4's translation capability gradually weakening from resource-rich to resource-poor directions. In addition, we qualitatively study the translation given by GPT-4 and human translators, and find that GPT-4 translator suffers from literal translations, but human translators sometimes overthink the background information. To our knowledge, this study is the first to evaluate LLMs against human translators and analyze the systematic differences between their outputs, providing valuable insights into the current state of LLM-based translation and its potential limitations.

📄 PDF Abstract BibTeX arXiv:2407.03658

Code (0)

등록된 구현이 없습니다.

Tasks

Translation

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Multi-Head Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Residual Connection 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Similar Papers 제목 키워드 기반

Benchmarking GPT-4 against Human Translators: A Comprehensive Evaluation Across Languages, Domains, and Expertise Levels

2024-11-21 · Jianhao Yan, Pingchuan Yan, Yulong Chen, Jing Li 외

This study presents a comprehensive evaluation of GPT-4's translation capabilities compared to human translators of varying expertise levels. Through systematic human evaluation using the MQM schema, we assess translatio…

BenchmarkingMachine TranslationTranslation

Computer Assisted Translation with Neural Quality Estimation and Automatic Post-Editing

2020-09-19 · Findings of the Association for Computational Linguistics 2020 · Jiayi Wang, Ke Wang, Niyu Ge, Yangbing Shi 외

With the advent of neural machine translation, there has been a marked shift towards leveraging and consuming the machine translation results. However, the gap between machine translation systems and human translators ne…

Automatic Post-EditingMachine TranslationTranslation

A Bayesian approach to translators' reliability assessment

2022-03-14 · Marco Miccheli, Andrej Leban, Andrea Tacchella, Andrea Zaccaria 외

Translation Quality Assessment (TQA) is a process conducted by human translators and is widely used, both for estimating the performance of (increasingly used) Machine Translation, and for finding an agreement between tr…

Machine TranslationTranslation

Error Span Annotation: A Balanced Approach for Human Evaluation of Machine Translation

2024-06-17 · Tom Kocmi, Vilém Zouhar, Eleftherios Avramidis, Roman Grundkiewicz 외

High-quality Machine Translation (MT) evaluation relies heavily on human judgments. Comprehensive error classification methods, such as Multidimensional Quality Metrics (MQM), are expensive as they are time-consuming and…

Machine TranslationTranslation

Involving Language Professionals in the Evaluation of Machine Translation

2012-05-01 · LREC 2012 5 · Eleftherios Avramidis, Aljoscha Burchardt, Christian Federmann, Maja Popovi{\'c} 외

Significant breakthroughs in machine translation only seem possible if human translators are taken into the loop. While automatic evaluation and scoring mechanisms such as BLEU have enabled the fast development of system…

Machine TranslationTranslation