This study investigates the translation performance of two large language models–ChatGPT-4o and DeepSeek-V3–in translating English academic papers on on language, culture, and literature into Chinese at the discourse level. Using a corpus of 11 academic texts totaling 3,498 sentences, we evaluated translation quality through automatic metrics (COMET-KIWI), lexical diversity indicators, and syntactic complexity measures. Our findings reveal an interesting contrast\colon while DeepSeek-V3 achieves higher overall quality scores, GPT-4o produces translations with consistently greater lexical richness (higher type-token ratio, standardized TTR, average sentence length, and word entropy) and syntactic complexity across all five measured metrics, such as Incomplete Dependency Theory Metric (IDT), Dependency Locality Theory Metric (DLT), Combined IDT+DLT Metric (IDT+DLT), Left-Embeddedness (LE), and Nested Nouns Distance (NND). Particularly notable are GPT-4o’s higher scores in Left-Embeddedness and Nested Nouns Distance metrics, which are specifically relevant to Chinese linguistic patterns. The divergence between automatic quality estimation and linguistic complexity metrics highlights the multifaceted nature of translation quality assessment.

This research explores the interaction between human translators and Large Language Models (LLMs) during post-editing (PE). The study examines the impact of syntactic complexity on the PE processes and performance, specifically when working with the raw translation output generated by GPT-4. We selected four English source texts (STs) from previous American Translators Association (ATA) certification examinations. Each text is about 10 segments, with 250 words. GPT-4 was employed to translate the four STs from English into simplified Chinese. The empirical experiment simulated the authentic work environment of PE, using professional computer-assisted translation (CAT) tool, Trados. The experiment involved 46 participants with different levels of translation expertise (30 student translators and 16 expert translators), producing altogether 2162 segments of PE versions. We implemented five syntactic complexity metrics in the context of PE for quantitative analysis.

Knowledge graphs applications, in industry and academia, motivate substantial research directions towards large-scale information extraction from various types of resources. Nowadays, most of the available knowledge graphs are either in English or multilingual. In this paper, we introduce RezoJDM16k, a French knowledge graph dataset based on RezoJDM. With 16k nodes, 832k triplets, and 53 relation types, RezoJDM16k can be employed in many NLP downstream tasks for the French language such as machine translation, question-answering, and recommendation systems. Moreover, we provide strong knowledge graph embedding baselines that are used in link prediction tasks for future benchmarking. Compared to the state-of-the-art English knowledge graph datasets used in link prediction, RezoJDM16k shows a similar promising predictive behavior.

Finding Missing Categories in Incomplete Utterances This paper introduces an efficient algorithm (O(n4 )) for finding a missing category in an incomplete utterance by using unification technique as when learning categorial grammars, and dynamic programming as in Cocke–Younger–Kasami algorithm. Using syntax/semantic interface of categorial grammar, this work can be used for deriving possible semantic readings of an incomplete utterance. The paper illustrates the problem with running examples.