ComputEL: A workshop to explore the use of computational methods in the study of endangered language

2014年6月，在美国国家科学基金会（NSF）的支持下，第一次ComputEL研讨会与第52届计算语言学协会（ACL）年会上在马里兰州巴尔的摩举行。该讲习班的目标是作为计算机科学家和活跃于ACL的计算语言学家以及从事濒危语言工作的文献语言学家之间的初步会议点。这一建议旨在吸取第一次ComputEL研讨会的经验教训，并鼓励两个研究团体之间进行新的合作。当代记录世界濒危语言的努力依赖于现代记录技术的广泛使用，特别是数字音频和视频记录设备以及对这些设备产生的记录进行注释的软件。然而，尽管十多年来一直致力于濒危语言文献的资助项目，但支持参与这项工作的活动的技术环境仍然支离破碎，新技术的承诺在很大程度上仍未实现。此外，总体而言，计算机科学家的工作大多与纪实语言学家的日常工作脱节，这使得两组的知识很难相互交流。第二届ComputEL研讨会将通过汇集语言学家和计算机科学家来探讨如何创建计算技术和工具来更好地帮助分析濒危语言来解决这一问题。一个特别的重点将是如何促进这个过程，通过这个过程，这个领域的研究成果可以开发成软件，为那些记录该领域濒危语言的人提供良好的支持。该研讨会将与2016年10月在德克萨斯州奥斯汀举行的自然语言处理（EMNLP）经验方法会议同时举行。这将使它能够接触到比其他方式更广泛的受众，同时利用其地理位置的优势，吸引附近地区的参与者。第一天，与会者将参加闭门会议的一部分讨论，该会议旨在为改进计算方法在濒危语言研究中的应用制定近期议程。第二天将包括与EMNLP主要会议联合安排的研究报告。研讨会的论文将发表在计算语言学协会会议论文集上，并将制作一份总结闭门会议结论的额外报告。世界范围内较小的语言群体将受益于这一结果，这将有助于更好地记录和保存濒危语言。

In June 2014, with support from NSF, the first ComputEL workshop was held in conjunction with the 52nd Annual Meeting of the Association for Computational Linguistics (ACL) in Baltimore, Maryland. The goal of that workshop was to serve as an initial meeting point between computer scientists and computational linguists active in ACL and documentary linguists engaged in work on endangered languages. This proposal seeks to build on lessons learned in the first ComputEL workshop, and to encourage new collaborations between the two research communities. Contemporary efforts to document the world's endangered languages are dependent on the widespread availability of modern recording technologies, in particular digital audio and video recording devices and software to annotate the recordings that such devices produce. However, despite well over a decade of funding programs dedicated to the documentation of endangered languages, the technological landscape that supports the activities of those involved in this work remains fragmented, and the promises of new technology remain largely unfulfilled. Moreover, the efforts of computer scientists, on the whole, are mostly disconnected from the day-to-day work of documentary linguists, making it difficult for the knowledge of each group to inform the other. The second ComputEL workshop will address this state of affairs by bringing together field linguists and computer scientists to explore how computational techniques and tools can be created to better aid in the analysis of endangered languages. A particular focus will be on how to facilitate the process through which research results in this domain can be developed into software that is well-supported for use by those documenting endangered languages in the field. The workshop will be co-located with the Conference on Empirical Methods in Natural Language Processing (EMNLP) in Austin, Texas, in October 2016. This will allow it to reach a wider audience than would otherwise be possible, while taking advantage of its location to involve participants from nearby areas. On the first day, participants will take part in discussions as part of a closed meeting that will be designed to lay out a near-term agenda for the improved application of computational methods to the study of endangered languages. The second day will consist of research presentations scheduled jointly with the main EMNLP conference. The papers from the workshop will be published in the Association for Computational Linguistics conference proceedings, and an additional report will be produced summarizing the conclusions of the closed meeting. Smaller speaker communities worldwide will benefit from the results which will support better documentation and preservation of endangered languages.