自动内容提取
此词条暂由彩云小译翻译，翻译字数共388，人工整理：林家驹。
Automatic content extraction (ACE) is a research program for developing advanced information extraction technologies convened by the NIST from 1999 to 2008, succeeding MUC and preceding Text Analysis Conference.
自动内容提取(ACE)是由 NIST 在1999年至2008年间召开的一个研究项目，目的是开发先进的信息抽取/文本分析技术，后续还有 MUC 和之前的文本分析会议。
Goals and efforts
In general objective, the ACE program is motivated by and addresses the same issues as the MUC program that preceded it. The ACE program, however, defines the research objectives in terms of the target objects (i.e., the entities, the relations, and the events) rather than in terms of the words in the text. For example, the so-called "named entity" task, as defined in MUC, is to identify those words (on the page) that are names of entities. In ACE, on the other hand, the corresponding task is to identify the entity so named. This is a different task, one that is more abstract and that involves inference more explicitly in producing an answer. In a real sense, the task is to detect things that "aren't there".
总的来说，ACE 程序的动机和解决的问题与之前的 MUC 程序相同。然而，ACE 程序以目标对象(即实体、关系和事件)来定义研究目标，而不是以文本中的词语来定义。例如，在 MUC 中定义的所谓“命名实体”任务就是识别(页面上的)实体名称的单词。而在 ACE 中，相应的任务是标识如此命名的实体。后一个任务更加抽象，在产生答案时涉及更明确的推理。从某种意义上说，AUC检测的实体“并不在那里”。
While the ACE program is directed toward extraction of information from audio and image sources in addition to pure text, the research effort is restricted to information extraction from text. The actual transduction of audio and image data into text is not part of the ACE research effort, although the processing of ASR and OCR output from such transducers is.
虽然 ACE 项目的目标是从音频和图像资源中提取除纯文本以外的信息，但研究工作仅限于从文本中提取信息抽取。实际将音频和图像数据转换成文本并不是 ACE 研究工作的一部分，不过这些转换器输出的 ASR 和 OCR 的输出是 ACE 研究工作的一部分。
The effort involves:
- defining the research tasks in detail,
- collecting and annotating data needed for training, development, and evaluation,
- supporting the research with evaluation tools and research workshops
这项工作包括:
- 详细定义研究任务，
- 收集和注释数据集，包括训练集测试集等，
- 通过评估工具和研究工作坊支持研究。
Topics and exercises
Given a text in natural language, the ACE challenge is to detect:
- entities mentioned in the text, such as: persons, organizations, locations, facilities, weapons, vehicles, and geo-political entities.
- relations between entities, such as: person A is the manager of company B. Relation types include: role, part, located, near, and social.
- events mentioned in the text, such as: interaction, movement, transfer, creation and destruction
给定一个自然语言的文本，ACE 的挑战是检测: 文本中提到的
# 实体，如: 个人、组织、地点、设施、武器、车辆和地理政治实体。
# 实体之间的关系，例如: a 人是 b 公司的经理。关系类型包括: 角色、部分、位置、接近和社会。
# 文本中提到的事件，比如: 互动，运动，转移，创造和毁灭。
The program relates to English, Arabic and Chinese texts.
该计划涉及英语，阿拉伯语和中文文本。
The ACE corpus is one of the standard benchmarks for testing new information extraction algorithms.
ACE 语料库是测试新的信息抽取算法的标准基准之一。
References
- George Doddington@NIS T, Alexis Mitchell@LD C, Mark Przybocki@NIS T, Lance Ramshaw@BB N, Stephanie Strassel@LD C, Ralph Weischedel@BB N. The automatic content extraction (ACE) program–tasks, data, and evaluation. 2004
External links
- MUC - ACE's predecessor.
- ACE -{zh-cn:互联网档案馆; zh-tw:網際網路檔案館; zh-hk:互聯網檔案館;}-的存檔，存档日期2013-09-25. (LDC)
- ACE (NIST)
- MUC - ACE's predecessor.
- ACE (LDC)
- ACE (NIST)
- MUC-ACE 的前身。
- ACE (LDC)
- ACE (NIST)
Category:Information retrieval organizations
类别: 信息检索组织
This page was moved from wikipedia:en:Automatic content extraction. Its edit history can be viewed at 自动内容提取/edithistory