Pacific Asia Conference on Language, Information and Computation最新文献

Synthesis and Evaluation of a Domain-specific Large Data Set for Dungeons & Dragons 《龙与地下城》领域特定大型数据集的综合与评估

Pacific Asia Conference on Language, Information and Computation Pub Date : 2022-12-18 DOI: 10.48550/arXiv.2212.09080

Akila Peiris, Nisansa de Silva

引用次数: 2

Sinhala Sentence Embedding: A Two-Tiered Structure for Low-Resource Languages 僧伽罗语句子嵌入:低资源语言的两层结构

Pacific Asia Conference on Language, Information and Computation Pub Date : 2022-10-26 DOI: 10.48550/arXiv.2210.14472

Gihan Weeraprameshwara, Vihanga Jayawickrama, Nisansa de Silva, Yudhanjaya Wijeratne

{"title":"Sinhala Sentence Embedding: A Two-Tiered Structure for Low-Resource Languages","authors":"Gihan Weeraprameshwara, Vihanga Jayawickrama, Nisansa de Silva, Yudhanjaya Wijeratne","doi":"10.48550/arXiv.2210.14472","DOIUrl":"https://doi.org/10.48550/arXiv.2210.14472","url":null,"abstract":"In the process of numerically modeling natural languages, developing language embeddings is a vital step. However, it is challenging to develop functional embeddings for resource-poor languages such as Sinhala, for which sufficiently large corpora, effective language parsers, and any other required resources are difficult to find. In such conditions, the exploitation of existing models to come up with an efficacious embedding methodology to numerically represent text could be quite fruitful. This paper explores the effectivity of several one-tiered and two-tiered embedding architectures in representing Sinhala text in the sentiment analysis domain. With our findings, the two-tiered embedding architecture where the lower-tier consists of a word embedding and the upper-tier consists of a sentence embedding has been proven to perform better than one-tier word embeddings, by achieving a maximum F1 score of 88.04% in contrast to the 83.76% achieved by word embedding models. Furthermore, embeddings in the hyperbolic space are also developed and compared with Euclidean embeddings in terms of performance. A sentiment data set consisting of Facebook posts and associated reactions have been used for this research. To effectively compare the performance of different embedding systems, the same deep neural network structure has been trained on sentiment data with each of the embedding systems used to encode the text associated.","PeriodicalId":122542,"journal":{"name":"Pacific Asia Conference on Language, Information and Computation","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115626818","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

Cross-strait Variations on Two Near-synonymous Loanwords xie2shang1 and tan2pan4: A Corpus-based Comparative Study 两个近义外来词“谢上”和“吐槽”的两岸差异:基于语料库的比较研究

Pacific Asia Conference on Language, Information and Computation Pub Date : 2022-10-09 DOI: 10.48550/arXiv.2210.04161

Yueyue Huang, Chu-Ren Huang

{"title":"Cross-strait Variations on Two Near-synonymous Loanwords xie2shang1 and tan2pan4: A Corpus-based Comparative Study","authors":"Yueyue Huang, Chu-Ren Huang","doi":"10.48550/arXiv.2210.04161","DOIUrl":"https://doi.org/10.48550/arXiv.2210.04161","url":null,"abstract":"This study attempts to investigate cross-strait variations on two typical synonymous loanwords in Chinese, i.e. xie2shang1 and tan2pan4, drawn on MARVS theory. Through a comparative analysis, the study found some distributional, eventual, and contextual similarities and differences across Taiwan and Mainland Mandarin. Compared with the underused tan2pan4, xie2shang1 is significantly overused in Taiwan Mandarin and vice versa in Mainland Mandarin. Additionally, though both words can refer to an inchoative process in Mainland and Taiwan Mandarin, the starting point for xie2shang1 in Mainland Mandarin is somewhat blurring compared with the usage in Taiwan Mandarin. Further on, in Taiwan Mandarin, tan2pan4 can be used in economic and diplomatic contexts, while xie2shang1 is used almost exclusively in political contexts. In Mainland Mandarin, however, the two words can be used in a hybrid manner within political contexts; moreover, tan2pan4 is prominently used in diplomatic contexts with less reference to economic activities, while xie2sahng1 can be found in both political and legal contexts, emphasizing a role of mediation.","PeriodicalId":122542,"journal":{"name":"Pacific Asia Conference on Language, Information and Computation","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122264722","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SMTCE: A Social Media Text Classification Evaluation Benchmark and BERTology Models for Vietnamese 越南社会媒体文本分类评价基准与BERTology模型

Pacific Asia Conference on Language, Information and Computation Pub Date : 2022-09-21 DOI: 10.48550/arXiv.2209.10482

Luan Nguyen, Kiet Van Nguyen, N. Nguyen

{"title":"SMTCE: A Social Media Text Classification Evaluation Benchmark and BERTology Models for Vietnamese","authors":"Luan Nguyen, Kiet Van Nguyen, N. Nguyen","doi":"10.48550/arXiv.2209.10482","DOIUrl":"https://doi.org/10.48550/arXiv.2209.10482","url":null,"abstract":"Text classification is a typical natural language processing or computational linguistics task with various interesting applications. As the number of users on social media platforms increases, data acceleration promotes emerging studies on Social Media Text Classification (SMTC) or social media text mining on these valuable resources. In contrast to English, Vietnamese, one of the low-resource languages, is still not concentrated on and exploited thoroughly. Inspired by the success of the GLUE, we introduce the Social Media Text Classification Evaluation (SMTCE) benchmark, as a collection of datasets and models across a diverse set of SMTC tasks. With the proposed benchmark, we implement and analyze the effectiveness of a variety of multilingual BERT-based models (mBERT, XLM-R, and DistilmBERT) and monolingual BERT-based models (PhoBERT, viBERT, vELECTRA, and viBERT4news) for tasks in the SMTCE benchmark. Monolingual models outperform multilingual models and achieve state-of-the-art results on all text classification tasks. It provides an objective assessment of multilingual and monolingual BERT-based models on the benchmark, which will benefit future studies about BERTology in the Vietnamese language.","PeriodicalId":122542,"journal":{"name":"Pacific Asia Conference on Language, Information and Computation","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134471005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

UIT-ViCoV19QA: A Dataset for COVID-19 Community-based Question Answering on Vietnamese Language unit - vicov19qa:基于越南语的COVID-19社区问答数据集

Pacific Asia Conference on Language, Information and Computation Pub Date : 2022-09-14 DOI: 10.48550/arXiv.2209.06668

T. M. Thai, Ngan Ha-Thao Chu, A. T. Vo, Son T. Luu

引用次数: 2

Zero-shot and few-shot approaches for tokenization, tagging, and dependency parsing of Tagalog text 他加禄语文本的标记化、标记和依赖解析的零射击和少射击方法

Pacific Asia Conference on Language, Information and Computation Pub Date : 2022-08-03 DOI: 10.48550/arXiv.2208.01814

Angelina A. Aquino, Franz A. de Leon

引用次数: 0

Data Augmentation to Address Out-of-Vocabulary Problem in Low-Resource Sinhala-English Neural Machine Translation 解决低资源僧伽罗语-英语神经机器翻译中词汇缺失问题的数据扩充

Pacific Asia Conference on Language, Information and Computation Pub Date : 2022-05-18 DOI: 10.48550/arXiv.2205.08722

Aloka Fernando, Surangika Ranathunga

{"title":"Data Augmentation to Address Out-of-Vocabulary Problem in Low-Resource Sinhala-English Neural Machine Translation","authors":"Aloka Fernando, Surangika Ranathunga","doi":"10.48550/arXiv.2205.08722","DOIUrl":"https://doi.org/10.48550/arXiv.2205.08722","url":null,"abstract":"OutofVocabulary (OOV) is a problem for Neural Machine Translation (NMT). OOV refers to words with a low occurrence in the training data, or to those that are absent from the training data. To alleviate this, word or phrasebased Data Augmentation (DA) tech niques have been used. However, existing DA techniques have addressed only one of these OOV types and limit to considering either syntactic constraints or semantic constraints. We present a word and phrase replacement based DA technique that consider both types of OOV, by augmenting (1) rare words in the ex isting parallel corpus, and (2) new words from a bilingual dictionary. During augmentation, we consider both syntactic and semantic prop erties of the words to guarantee fluency in the synthetic sentences. This technique was ex perimented with low resource SinhalaEnglish language pair. We observe with only semantic constraints in the DA, the results are compara ble with the scores obtained considering syn tactic constraints, and is favourable for low resourced languages that lacks linguistic tool support. Additionally, results can be further improved by considering both syntactic and semantic constraints.","PeriodicalId":122542,"journal":{"name":"Pacific Asia Conference on Language, Information and Computation","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133114783","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

UCSYNLP-Lab Machine Translation Systems for WAT 2018 UCSYNLP-Lab WAT 2018机器翻译系统

Pacific Asia Conference on Language, Information and Computation Pub Date : 2019-11-01 DOI: 10.18653/v1/d19-5226

Yi Mon Shwe Sin, T. Oo, Hsu Myat Mo, Win Pa Pa, Khim Mar Soe, Ye Kyaw Thu

引用次数: 3

Relating Keywords to the Top Ten News of the Year in Korean Newspapers 与韩国报纸年度十大新闻相关的关键词

Pacific Asia Conference on Language, Information and Computation Pub Date : 2014-12-01 DOI: 10.20988/lfp.2017.41..113

Jae-Woong Choe

引用次数: 0

Set Expansion using Sibling Relations between Semantic Categories 使用语义类别之间的兄弟关系设置扩展

Pacific Asia Conference on Language, Information and Computation Pub Date : 2012-11-01 DOI: 10.5715/JNLP.20.273

Sho Takase, Naoaki Okazaki, Kentaro Inui

引用次数: 1