More Like this

1. Effect of Chinese characters on machine learning for Chinese author name disambiguation: A counterfactual evaluation

   https://doi.org/10.1177/01655515211018171  

   Kim, Jinseok; Kim, Jenna; Kim, Jinmo (January 2021, Journal of Information Science)

   null (Ed.)

   Chinese author names are known to be more difficult to disambiguate than other ethnic names because they tend to share surnames and forenames, thus creating many homonyms. In this study, we demonstrate how using Chinese characters can affect machine learning for author name disambiguation. For analysis, 15K author names recorded in Chinese are transliterated into English and simplified by initialising their forenames to create counterfactual scenarios, reflecting real-world indexing practices in which Chinese characters are usually unavailable. The results show that Chinese author names that are highly ambiguous in English or with initialised forenames tend to become less confusing if their Chinese characters are included in the processing. Our findings indicate that recording Chinese author names in native script can help researchers and digital libraries enhance authority control of Chinese author names that continue to increase in size in bibliographic data. 

   more » « less
2. Automatic Reconstruction of Ancient Chinese Pronunciations

   https://doi.org/10.18653/v1/2024.findings-emnlp.325  

   Huang, Zhige; Jin, Haoan; Wu, Mengyue; Zhu, Kenny Q (January 2024, Association for Computational Linguistics)
3. Rational Sentence Interpretation in Mandarin Chinese

   https://doi.org/10.1111/cogs.13383  

   Zhan, Meilin; Chen, Sihan; Levy, Roger; Lu, Jiayi; Gibson, Edward (December 2023, Cognitive Science)

   Abstract Previous work has shown that English native speakers interpret sentences as predicted by a noisy‐channel model: They integrate both the real‐world plausibility of the meaning—the prior—and the likelihood that the intended sentence may be corrupted into the perceived sentence. In this study, we test the noisy‐channel model in Mandarin Chinese, a language taxonomically different from English. We present native Mandarin speakers sentences in a written modality (Experiment 1) and an auditory modality (Experiment 2) in three pairs of syntactic alternations. The critical materials are literally implausible but require differing numbers and types of edits in order to form more plausible sentences. Each sentence is followed by a comprehension question that allows us to infer whether the speakers interpreted the item literally, or made an inference toward a more likely meaning. Similar to previous research on related English constructions, Mandarin participants made the most inferences for implausible materials that could be inferred as plausible by deleting a single morpheme or inserting a single morpheme. Participants were less likely to infer a plausible meaning for materials that could be inferred as plausible by making an exchange across a preposition. And participants were least likely to infer a plausible meaning for materials that could be inferred as plausible by making an exchange across a main verb. Moreover, we found more inferences in written materials than spoken materials, possibly a result of a lack of word boundaries in written Chinese. Overall, the fact that the results were so similar to those found in related constructions in English suggests that the noisy‐channel proposal is robust. 

   more » « less
4. Chinese UMR annotation: Can LLMs help?

   Sun, Haibo; Xue, Nianwen; Zhao, Jin; Yue, Liulu; Sun, Yao; Xue, Keer; Wu, Jiawei (May 2024, ELRA and ICCL)

   Bonial, Claire; Bonn, Julia; Hwang, Jena D (Ed.)

   We explore using LLMs, GPT-4 specifically, to generate draft sentence-level Chinese Uniform Meaning Representations (UMRs) that human annotators can revise to speed up the UMR annotation process. In this study, we use few-shot learning and Think-Aloud prompting to guide GPT-4 to generate sentence-level graphs of UMR. Our experimental results show that compared with annotating UMRs from scratch, using LLMs as a preprocessing step reduces the annotation time by two thirds on average. This indicates that there is great potential for integrating LLMs into the pipeline for complicated semantic annotation tasks. 

   more » « less
5. Chinese UMR annotation: Can LLMs help?

   Sun, Haibo; Xue, Nianwen; Zhao, Jin; Yue, Liulu; Sun, Yao; Xu, Keer; Wu, Jiawei (May 2024, ELRA and ICCL)

   Bonial, Claire; Bonn, Julia; Hwang, Jena D (Ed.)

   We explore using LLMs, GPT-4 specifically, to generate draft sentence-level Chinese Uniform Meaning Representations (UMRs) that human annotators can revise to speed up the UMR annotation process. In this study, we use few-shot learning and Think-Aloud prompting to guide GPT-4 to generate sentence-level graphs of UMR. Our experimental results show that compared with annotating UMRs from scratch, using LLMs as a preprocessing step reduces the annotation time by two thirds on average. This indicates that there is great potential for integrating LLMs into the pipeline for complicated semantic annotation tasks. 

   more » « less