检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Spencer, Piyapath T. Kongborrirak, Nanthipat Language and Information Technology Programme Faculty of Arts CU Thailand LMU Munich Germany

ISBN: (纸本)9798891761964

In the present-day documenting and preserving endangered languages, the application of Large language Models (LLMs) presents a promising approach. This paper explores how LLMs, particularly through in-context learning, can assist in generating grammatical information for low-resource languages with a limited amount of data. We take Moklen as a case study to evaluate the efficacy of LLMs in producing coherent grammatical rules and lexical entries using only bilingual dictionaries and parallel sentences of the unknown language without building the model from scratch. Our methodology involves organising the existing linguistic data and prompting to efficiently enable to generate formal XLE grammar. Our results demonstrate that LLMs can successfully capture key grammatical structures and lexical information, although challenges such as the potential for English grammatical biases remain. This study highlights the potential of LLMs to enhance language documentation efforts, providing a cost-effective solution to generate linguistic data and contributing to the preservation of endangered languages. © 2025 Association for Computational Linguistics.

关键词： Context free languages

来源：评论

学校读者我要写书评

暂无评论

Can LLMs Help Create Grammar?: Automating Grammar Creation for Endangered languages with In-Context Learning

arXiv

引用

arXiv 2024年

作者： Spencer, Piyapath T. Kongborrirak, Nanthipat Language and Information Technology Programme Faculty of Arts CU Thailand LMU Munich Germany

Yes! In the present-day documenting and preserving endangered languages, the application of Large language Models (LLMs) presents a promising approach. This paper explores how LLMs, particularly through in-context learning, can assist in generating grammatical information for low-resource languages with limited amount of data. We takes Moklen as a case study to evaluate the efficacy of LLMs in producing coherent grammatical rules and lexical entries using only bilingual dictionaries and parallel sentences of the unknown language without building the model from scratch. Our methodology involves organising the existing linguistic data and prompting to efficiently enable to generate formal XLE grammar. Our results demonstrate that LLMs can successfully capture key grammatical structures and lexical information, although challenges such as the potential for English grammatical biases remain. This study highlights the potential of LLMs to enhance language documentation efforts, providing a cost-effective solution for generating linguistic data and contributing to the preservation of endangered languages. © 2024, CC BY.

关键词： Context free languages

来源：评论

学校读者我要写书评

暂无评论

Human-Centric NLP or AI-Centric Illusion?: A Critical Investigation

arXiv

引用

arXiv 2024年

作者： Spencer, Piyapath T. Language and Information Technology Programme Faculty of Arts CU Thailand LMU Munich Germany

Human-Centric NLP often claims to prioritise human needs and values, yet many implementations reveal an underlying AI-centric focus. Through an analysis of case studies in language modelling, behavioural testing, and multi-modal alignment, this study identifies a significant gap between the ideas of human-centricity and actual practices. Key issues include misalignment with human-centred design principles, the reduction of human factors to mere benchmarks, and insufficient consideration of real-world impacts. The discussion explores whether Human-Centric NLP embodies true human-centred design, emphasising the need for interdisciplinary collaboration and ethical considerations. The paper advocates for a redefinition of Human-Centric NLP, urging a broader focus on real-world utility and societal implications to ensure that language technologies genuinely serve and empower users. © 2024, CC BY.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Global, regional, and national sex-specific burden and control of the HIV epidemic, 1990–2019, for 204 countries and territories: the Global Burden of Diseases Study 2019

引用

The Lancet HIV 2021年第10期8卷 e633-e651页

作者： Jahagirdar, Deepa Walters, Magdalene K. Novotney, Amanda Brewer, Edmond D. Frank, Tahvi D. Carter, Austin Biehl, Molly H. Abbastabar, Hedayat Abhilash, E.S. Abu-Gharbieh, Eman Abu-Raddad, Laith Jamal Adekanmbi, Victor Adeyinka, Daniel Adedayo Adnani, Qorinah Estiningtyas Sakilah Afzal, Saira Aghababaei, Soodabeh Ahinkorah, Bright Opoku Ahmad, Sajjad Ahmadi, Keivan Ahmadi, Sepideh Ahmadpour, Ehsan Ahmed, Muktar Beshir Rashid, Tarik Ahmed Salih, Yusra Ahmed Aklilu, Addis Akram, Tayyaba Akunna, Chisom Joyqueenet Al Hamad, Hanadi Alahdab, Fares Alanezi, Fahad Mashhour Aleksandrova, Ekaterina A. Alene, Kefyalew Addis Ali, Liaqat Alipour, Vahid Almustanyir, Sami Alvis-Guzman, Nelson Ameyaw, Edward Kwabena Amu, Hubert Andrei, Catalina Liliana Andrei, Tudorel Anvari, Davood Arabloo, Jalal Aremu, Olatunde Arulappan, Judie Atnafu, Desta Debalkie Quintanilla, Beatriz Paulina Ayala Ayza, Muluken Altaye Azari, Samad Darshan, B.B. Banach, Maciej Bärnighausen, Till Winfried Barra, Fabio Barrow, Amadou Basu, Sanjay Bazargan-Hejazi, Shahrzad Belay, Habtamu Gebrehana Berheto, Tezera Moshago Bezabhe, Woldesellassie Mequanint Bezabih, Yihienew Mequanint Bhagavathula, Akshaya Srikanth Bhardwaj, Nikha Bhardwaj, Pankaj Bhattacharyya, Krittika Bibi, Sadia Bijani, Ali Bisignano, Catherine Bolarinwa, Obasanjo Afolabi Boloor, Archith Boltaev, Azizbek A. Briko, Nikolay Ivanovich Buonsenso, Danilo Burkart, Katrin Butt, Zahid A. Cao, Chao Charan, Jaykaran Chatterjee, Souranshu Chattu, Soosanna Kumary Chattu, Vijay Kumar Choudhari, Sonali Gajanan Chu, Dinh-Toi Couto, Rosa A.S. Cowden, Richard G. Dachew, Berihun Assefa Dadras, Omid Dagnew, Amare Belachew Dahlawi, Saad M.A. Dai, Xiaochen Dandona, Lalit Dandona, Rakhi das Neves, José Degenhardt, Louisa Demeke, Feleke Mekonnen Desta, Abebaw Alemayehu Deuba, Keshab Dhamnetiya, Deepak Dhungana, Govinda Prasad Dianatinasab, Mostafa Diaz, Daniel Djalalinia, Shirin Doan, Linh Phuong Dorostkar, Fariba Edinur, Hisham Atan Effiong, Andem Eftekharzadeh, Sahar El Sayed Zaki, Maysaa Elayedath, Rajesh Elhadi, Institute for Health Metrics and Evaluation University of Washington Seattle WA United States Department of Health Metrics Sciences School of Medicine University of Washington Seattle WA United States Division of Allergy and Infectious Diseases University of Washington Seattle WA United States Department of Global Health University of Washington Seattle WA United States School of Social Work University of Washington Seattle WA United States Department of Medicine University of Washington Seattle WA United States Vagelos College of Physicians and Surgeones Columbia University Medical Center New York NY United States Division of Data Analytics and Delivery for Impact WHO Geneva Switzerland Advanced Diagnostic and Interventional Radiology Research Centre Tehran University of Medical Sciences Tehran Iran Multiple Sclerosis Research Centre Tehran University of Medical Sciences Tehran Iran School of Public Health Tehran University of Medical Sciences Tehran Iran Department of Epidemiology and Biostatistics Tehran University of Medical Sciences Tehran Iran Paediatric Chronic Kidney Disease Research Centre Tehran University of Medical Sciences Tehran Iran Department of Psychiatry Tehran University of Medical Sciences Tehran Iran Metabolomics and Genomics Research Centre Tehran University of Medical Sciences Tehran Iran Sina Trauma and Surgery Research Centre Tehran University of Medical Sciences Tehran Iran Research Centre for Immunodeficiencies Tehran University of Medical Sciences Tehran Iran Non-Communicable Diseases Research Centre Tehran University of Medical Sciences Tehran Iran Department of Botany Sree Narayana Guru College Chelannur Kozhikode India Clinical Sciences Department University of Sharjah Sharjah United Arab Emirates Mass Communication Department University of Sharjah Sharjah United Arab Emirates Department of Health-Care Policy and Research Weill Cornell Medical College in Qatar Doha Qatar Department of Population Medicine Ca

Background: The sustainable development goals (SDGs) aim to end HIV/AIDS as a public health threat by 2030. Understanding the current state of the HIV epidemic and its change over time is essential to this effort. This study assesses the current sex-specific HIV burden in 204 countries and territories and measures progress in the control of the epidemic. Methods: To estimate age-specific and sex-specific trends in 48 of 204 countries, we extended the Estimation and Projection Package Age-Sex Model to also implement the spectrum paediatric model. We used this model in cases where age and sex specific HIV-seroprevalence surveys and antenatal care-clinic sentinel surveillance data were available. For the remaining 156 of 204 locations, we developed a cohort-incidence bias adjustment to derive incidence as a function of cause-of-death data from vital registration systems. The incidence was input to a custom Spectrum model. To assess progress, we measured the percentage change in incident cases and deaths between 2010 and 2019 (threshold >75% decline), the ratio of incident cases to number of people living with HIV (incidence-to-prevalence ratio threshold <0·03), and the ratio of incident cases to deaths (incidence-to-mortality ratio threshold <1·0). Findings: In 2019, there were 36·8 million (95% uncertainty interval [UI] 35·1–38·9) people living with HIV worldwide. There were 0·84 males (95% UI 0·78–0·91) per female living with HIV in 2019, 0·99 male infections (0·91–1·10) for every female infection, and 1·02 male deaths (0·95–1·10) per female death. Global progress in incident cases and deaths between 2010 and 2019 was driven by sub-Saharan Africa (with a 28·52% decrease in incident cases, 95% UI 19·58–35·43, and a 39·66% decrease in deaths, 36·49–42·36). Elsewhere, the incidence remained stable or increased, whereas deaths generally decreased. In 2019, the global incidence-to-prevalence ratio was 0·05 (95% UI 0·05–0·06) and the global incidence-to-mortality ratio was

关键词：

来源：评论

学校读者我要写书评

暂无评论

Assessment of NER solutions against the first and second CALBC Silver Standard Corpus

引用

Journal of Biomedical Semantics 2011年第5期2卷 1-12页

作者： Rebholz-Schuhmann, Dietrich Yepes, Antonio Jimeno Li, Chen Kafkas, Senay Lewin, Ian Kang, Ning Corbett, Peter Milward, David Buyko, Ekaterina Beisswanger, Elena Hornbostel, Kerstin Kouznetsov, Alexandre Witte, René Laurila, Jonas B Baker, Christopher JO Kuo, Cheng-Ju Clematide, Simone Rinaldi, Fabio Farkas, Richárd Móra, György Hara, Kazuo Furlong, Laura I Rautschka, Michael Neves, Mariana Lara Pascual-Montano, Alberto Wei, Qi Collier, Nigel Chowdhury, Md Faisal Mahbub Lavelli, Alberto Berlanga, Rafael Morante, Roser Van Asch, Vincent Daelemans, Walter Marina, José Luís van Mulligen, Erik Kors, Jan Hahn, Udo European Bioinformatics Institute EMBL Outstation Hinxton Cambridge CB10 1SD United Kingdom Erasmus University Medical Center Dept. of Medical Informatics Rotterdam Netherlands St. John's Innovation Centre Linguamatics Ltd Cambridge United Kingdom Friedrich-Schiller-Universität Language and Information Engineering (JULIE) Lab Jena Germany University of New Brunswick Dept. of Computer Science and Applied Statistics Canada Concordia University Dept. of Computer Science and Software Engineering Montreal Canada Academia Sinica Institute of Information Science Taipei 115 Taiwan University of Zürich Switzerland Hungarian Academy of Sciences Research Group on Artificial Intelligence Hungary Nara Institute of Science and Technology Nara Japan IMIM (Hospital del Mar Research Institute) Universitat Pompeu Fabra Research Programme on Biomedical Informatics (GRIB) Barcelona Spain National Center for Biotechnology-CSIC Madrid Spain National Institute of Informatics Tokyo Japan Fondazione Bruno Kessler Trento Italy Universitat Jaume I Spain University of Antwerp CLiPS Belgium Complutense University of Madrid Spain

Background: Competitions in text mining have been used to measure the performance of automatic text processing solutions against a manually annotated gold standard corpus (GSC). The preparation of the GSC is time-consuming and costly and the final corpus consists at the most of a few thousand documents annotated with a limited set of semantic groups. To overcome these shortcomings, the CALBC project partners (PPs) have produced a large-scale annotated biomedical corpus with four different semantic groups through the harmonisation of annotations from automatic text mining solutions, the first version of the Silver Standard Corpus (SSC-I). The four semantic groups are chemical entities and drugs (CHED), genes and proteins (PRGE), diseases and disorders (DISO) and species (SPE). This corpus has been used for the First CALBC Challenge asking the participants to annotate the corpus with their text processing solutions. Results: All four PPs from the CALBC project and in addition, 12 challenge participants (CPs) contributed annotated data sets for an evaluation against the SSC-I. CPs could ignore the training data and deliver the annotations from their genuine annotation system, or could train a machine-learning approach on the provided pre-annotated data. In general, the performances of the annotation solutions were lower for entities from the categories CHED and PRGE in comparison to the identification of entities categorized as DISO and SPE. The best performance over all semantic groups were achieved from two annotation solutions that have been trained on the SSC-I. The data sets from participants were used to generate the harmonised Silver Standard Corpus II (SSC-II), if the participant did not make use of the annotated data set from the SSC-I for training purposes. The performances of the participants' solutions were again measured against the SSC-II. The performances of the annotation solutions showed again better results for DISO and SPE in comparison to CHED and P

关键词： Chemical Entity Cosine Similarity Semantic Type Semantic Group Annotate Corpus

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：