Machine translation focuses mainly on high-resource languages (HRLs), while low-resource languages (LRLs) like Taiwanese Hokkien are relatively under-explored. The study aims to address this gap by developing a dual translation model between Taiwanese Hokkien and both Traditional Mandarin Chinese and English. We employ a pre-trained LLaMA 2-7B model specialized in Traditional Mandarin Chinese to leverage the orthographic similarities between Taiwanese Hokkien Han and Traditional Mandarin Chinese. Our comprehensive experiments involve translation tasks across various writing systems of Taiwanese Hokkien as well as between Taiwanese Hokkien and other HRLs. We find that the use of a limited monolingual corpus still further improves the model’s Taiwanese Hokkien capabilities. We then utilize our translation model to standardize all Taiwanese Hokkien writing systems into Hokkien Han, resulting in further performance improvements. Additionally, we introduce an evaluation method incorporating back-translation and GPT-4 to ensure reliable translation quality assessment even for LRLs. The study contributes to narrowing the resource gap for Taiwanese Hokkien and empirically investigates the advantages and limitations of pre-training and fine-tuning based on LLaMA 2.

In natural language processing (NLP), code-mixing (CM) is a challenging task, especially when the mixed languages include dialects. In Southeast Asian countries such as Singapore, Indonesia, and Malaysia, Hokkien-Mandarin is the most widespread code-mixed language pair among Chinese immigrants, and it is also common in Taiwan. However, dialects such as Hokkien often have a scarcity of resources and the lack of an official writing system, limiting the development of dialect CM research. In this paper, we propose a method to construct a Hokkien-Mandarin CM dataset to mitigate the limitation, overcome the morphological issue under the Sino-Tibetan language family, and offer an efficient Hokkien word segmentation method through a linguistics-based toolkit. Furthermore, we use our proposed dataset and employ transfer learning to train the XLM (cross-lingual language model) for translation tasks. To fit the code-mixing scenario, we adapt XLM slightly. We found that by using linguistic knowledge, rules, and language tags, the model produces good results on CM data translation while maintaining monolingual translation quality.

Code-mixing refers to the mixed use of multiple languages. It is prevalent in multilingual societies and is also one of the most challenging natural language processing tasks. In this paper, we study Bahasa Rojak, a dialect popular in Malaysia that consists of English, Malay, and Chinese. Aiming to establish a model to deal with the code-mixing phenomena of Bahasa Rojak, we use data augmentation to automatically construct the first Bahasa Rojak corpus for pre-training language models, which we name the Bahasa Rojak Crawled Corpus (BRCC). We also develop a new pre-trained model called “Mixed XLM”. The model can tag the language of the input token automatically to process code-mixing input. Finally, to test the effectiveness of the Mixed XLM model pre-trained on BRCC for social media scenarios where code-mixing is found frequently, we compile a new Bahasa Rojak sentiment analysis dataset, SentiBahasaRojak, with a Kappa value of 0.77.

Automatic fact verification has attracted recent research attention as the increasing dissemination of disinformation on social media platforms. The FEVEROUS shared task introduces a benchmark for fact verification, in which a system is challenged to verify the given claim using the extracted evidential elements from Wikipedia documents. In this paper, we propose our 3rd place three-stage system consisting of document retrieval, element retrieval, and verdict inference for the FEVEROUS shared task. By considering the context relevance in the fact extraction and verification task, our system achieves 0.29 FEVEROUS score on the development set and 0.25 FEVEROUS score on the blind test set, both outperforming the FEVEROUS baseline.

Cross-language article linking (CLAL) is the task of finding corresponding article pairs of different languages across encyclopedias. This task is a difficult disambiguation problem in which one article must be selected among several candidate articles with similar titles and contents. Existing works focus on engineering text-based or link-based features for this task, which is a time-consuming job, and some of these features are only applicable within the same encyclopedia. In this paper, we address these problems by proposing cross-encyclopedia entity embedding. Unlike other works, our proposed method does not rely on known cross-language pairs. We apply our method to CLAL between English Wikipedia and Chinese Baidu Baike. Our features improve performance relative to the baseline by 29.62%. Tested 30 times, our system achieved an average improvement of 2.76% over the current best system (26.86% over baseline), a statistically significant result.

Cross-language article linking (CLAL) is the task of finding corresponding article pairs across encyclopedias of different languages. In this paper, we present Encyclolink, a web-based CLAL search interface designed to help users find equivalent encyclopedia articles in Baidu Baike for a given English Wikipedia article title query. Encyclolink is powered by our cross-encyclopedia entity embedding CLAL system (0.8 MRR). The browser-based Interface provides users with a clear and easily readable preview of the contents of retrieved articles for comparison.

In the paper, we propose an information retrieval based (IR-based) Question Answering (QA) system to assist online customer service staffs respond users in the telecom domain. When user asks a question, the system retrieves a set of relevant answers and ranks them. Moreover, our system uses a novel reranker to enhance the ranking result of information retrieval. It employs the word2vec model to represent the sentences as vectors. It also uses a sub-category feature, predicted by the k-nearest neighbor algorithm. Finally, the system returns the top five candidate answers, making online staffs find answers much more efficiently.

The study of drug-drug interaction (DDI) is important in the drug discovering. Both PubMed and DrugBank are rich resources to retrieve DDI information which is usually represented in plain text. Automatically extracting DDI pairs from text improves the quality of drug discov-ering. In this paper, we presented a study that focuses on the DDI classification. We normalized the drug names, and developed both sentence-level and corpus-level features for DDI classification. A classifier ensemble approach is used for the unbalance DDI labels problem. Our approach achieved an F-score of 65.4% on SemEval 2013 DDI test set. The experimental results also show the effects of proposed corpus-level features in the DDI task.