相关论文: Shared Heritage, Distinct Writing: Rethinking Reso…
The intangible cultural heritage (ICH) of China, a cultural asset transmitted across generations by various ethnic groups, serves as a significant testament to the evolution of human civilization and holds irreplaceable value for the…
Realizing general-purpose language intelligence has been a longstanding goal for natural language processing, where standard evaluation benchmarks play a fundamental and guiding role. We argue that for general-purpose language intelligence…
The information provided by historical documents has always been indispensable in the transmission of human civilization, but it has also made these books susceptible to damage due to various factors. Thanks to recent technology, the…
The quality and size of a pretraining dataset significantly influence the performance of large language models (LLMs). While there have been numerous efforts in the curation of such a dataset for English users, there is a relative lack of…
Realignment is a promising strategy to improve cross-lingual transfer in multilingual language models. However, empirical results are mixed and often unreliable, particularly for typologically distant or low-resource languages (LRLs)…
We present our demonstration of two machine translation applications to historical documents. The first task consists in generating a new version of a historical document, written in the modern version of its original language. The second…
Handwritten word recognition and spotting of low-resource scripts are difficult as sufficient training data is not available and it is often expensive for collecting data of such scripts. This paper presents a novel cross language platform…
This paper explores how older adults, particularly aging migrants in urban China, can engage AI-assisted co-creation to express personal narratives that are often fragmented, underrepresented, or difficult to verbalize. Through a pilot…
Text summarization refers to the process that generates a shorter form of text from the source document preserving salient information. Many existing works for text summarization are generally evaluated by using recall-oriented understudy…
Recent years have seen big advances in the field of sentence-level quality estimation (QE), largely as a result of using neural-based architectures. However, the majority of these methods work only on the language pair they are trained on…
We investigate how large language models perform on low-resource languages by benchmarking eight LLMs across five experimental conditions in English, Kazakh, and Mongolian. Using 50 hand-crafted questions spanning factual, reasoning,…
Different from the writing systems of many Romance and Germanic languages, some languages or language families show complex conjunct forms in character composition. For such cases where the conjuncts consist of the components representing…
This paper presents our process for developing a sample-efficient language model for a conversational Hinglish chatbot. Hinglish, a code-mixed language that combines Hindi and English, presents a unique computational challenge due to…
Digital gift-giving has become a key means of maintaining social relationships, but most existing research has focused on gifting within global e-commerce or social media platforms. The emergence of messenger-based gifting in East Asia,…
Generative models are known to have reduced performance in different global cultural contexts and languages. While continual data updates have been commonly conducted to improve overall model performance, bolstering and evaluating this…
China has a long and rich history, encompassing a vast cultural heritage that includes diverse multimodal information, such as silk patterns, Dunhuang murals, and their associated historical narratives. Cross-modal retrieval plays a pivotal…
Quality estimation (QE) plays a crucial role in machine translation (MT) workflows, as it serves to evaluate generated outputs that have no reference translations and to determine whether human post-editing or full retranslation is…
Recently, significant public efforts have been directed towards developing low-cost models with capabilities akin to ChatGPT, thereby fostering the growth of open-source conversational models. However, there remains a scarcity of…
Knowledge Editing (KE) has emerged as a promising paradigm for updating facts in Large Language Models (LLMs) without retraining. However, progress in Multilingual Knowledge Editing (MKE) is currently hindered by biased evaluation…
Multilingual understanding is crucial for the cross-cultural applicability of Large Language Models (LLMs). However, evaluation benchmarks designed for Hong Kong's unique linguistic landscape, which combines Traditional Chinese script with…