Delu (Daniel) KONG

Delu (Daniel) KONG

He/Him

Lecturer in translation studies and computational linguistics

Talks and presentations

See a map of all the places I've given a talk!

Decoding Machine Translationese in English-Chinese News: LLMs vs. NMTs

June 28, 2025

Conference presentation, MT Summit 2025, Research: Technical track, Uni Mail, Geneva, The Switherland

This study explores Machine Translationese (MTese)—the linguistic peculiarities of machine translation outputs—focusing on the under-researched English-to-Chinese language pair in news texts. We construct a large dataset consisting of 4 sub-corpora and employ a comprehensive five-layer feature set. A chi-square ranking algorithm is applied for feature selection in both classification and clustering tasks. Our findings confirm the presence of MTese in both Neural Machine Translation systems (NMTs) and Large Language Models (LLMs). Original Chinese texts are nearly perfectly distinguishable from both LLM and NMT outputs. Notable linguistic patterns in MT outputs are shorter sentence lengths and increased use of adversative conjunctions. Comparing LLMs and NMTs, we achieve approximately 70% classification accuracy, with LLMs exhibiting greater lexical diversity and NMTs using more brackets. Additionally, translation-specific LLMs show lower lexical diversity but higher usage of causal conjunctions compared to generic LLMs. Lastly, we find no significant differences between LLMs developed by Chinese firms and their foreign counterparts.

Comments: 14 pages, 5 figures, 6 tables. Accepted in MT Summit 2025, Research: Technical track. Official version may be accessed later in the ACL Anthology.

PPT: Download here

Can Peter Pan Survive MT? A Stylometric Study of LLMs, NMTs, and HTs in Children’s Literature Translation

June 27, 2025

Symposium presentation, 2nd Workshop on Creative-text Translation and Technology, MT Summit 2025, Uni Mail, Geneva, The Switherland

This study evaluates the performance of machine translations (MTs) versus human translations (HTs) in English-to-Chinese children’s literature translation (CLT) from a stylometric perspective. A Peter Pan corpus was constructed, including 21 translations: 7 HTs, 7 large language model translations (LLMs), and 7 neural machine translation outputs (NMTs). The analysis uses both a generic feature set (lexical, syntactic, readability, n-gram features) and a creative text translation (CTT-specific) feature set (repetition, rhythm, translatability, miscellaneous), totaling 447 linguistic features.

Stylometric analysis using classification and clustering techniques reveals that, for generic features, HTs and MTs differ significantly in conjunction word distributions and the ratio of 1-word-gram-YiYang. NMTs and LLMs differ in descriptive word usage and adverb ratios. For CTT-specific features, LLMs outperform NMTs in distribution and align more closely with HTs in stylistic characteristics, highlighting the potential of LLMs in CLT.

Comments: 19 pages, 8 figures, 4 tables. Accepted at the 2nd Workshop on Creative-text Translation and Technology, co-located with MT Summit 2025. Official paper may later be accessed from ACL Anthology.

PPT: Link

Detecting Language Features of ‘Machine-Translationese’ through Machine Learning: Original Chinese News Text vs. Machine-Translated Chinese News Text

June 13, 2024

Conference presentation, International Conference on Chinese News Discourse in the Digital Era, University of Nottingham Ningbo China, 199 Taikang East Road, Ningbo, Zhejiang, China

Abstract:
This presentation investigates the linguistic features of “Machine-Translationese” (MTese) in English-to-Chinese machine-translated news texts. Through machine learning approaches, we identify and quantify distinctive characteristics that differentiate machine-translated Chinese news texts from originally authored Chinese news texts. Our methodology employs clustering techniques to visualize these differentiating features, revealing systematic patterns in MTese.