【文件属性】：
文件名称：Deep QA（IBM Watson）
文件大小：21.59MB
文件格式：ZIP
更新时间：2021-08-10 14:15:32
QA Watson watson deep learnin
IBM Watson的技术实现详解
IBM Watson是认知计算系统的杰出代表，也是一个技术平台。认知计算代表一种全新的计算模式，它包含信息分析，自然语言处理和机器学习领域的大量技术创新，能够助力决策者从大量非结构化数据中揭示非凡的洞察。Watson 在美国最受欢迎的智力问答电视节目《危险边缘》(Jeopardy)中亮相，一举打败了人类智力竞赛冠军。如今，Watson 已经发展为一个商业化、基于云的认知系统，应用到各行各业中。
This is Watson
IBM Research took on the grand challenge of building a computer system that could compete with champions at the game of Jeopardy!. The open-domain question-answering system dubbed Watson beat the two highest ranked players in a nationally televised two-game Jeopardy! match. This special issue provides a deep technical overview of the ideas and accomplishments that positioned our team to take on the Jeopardy! challenge, build Watson, and ultimately triumph. It describes the nature of the question-answering challenge represented by Jeopardy! and details our technical approach.
【文件预览】：
Deep QA（IBM Watson）
----17 in the game - the interface between watson and jeopardy.pdf(735KB)
----14 a framework for merging and ranking answers.pdf(1.56MB)
----04 textual resource acquision.pdf(1.25MB)
----09 relation extraction and scoring.pdf(1.41MB)
----05 automatic knowledge extration.pdf(839KB)
----07 typing candidate answers.pdf(2.21MB)
----16 simulation, learning, optimization in game strategy.pdf(965KB)
----10 structured data and inference.pdf(752KB)
----README.md(1KB)
----06 finding needles - search and candidate generation.pdf(2.06MB)
----00 Table of Contents.pdf(50KB)
----12 identifying implicit relationships.pdf(171KB)
----11 special questions.pdf(407KB)
----03 Deep parsing.pdf(631KB)
----08 textual evidence gatherint.pdf(209KB)
----02 question analysis.pdf(915KB)
----15 making watson fast.pdf(3.31MB)
----01 Intro.pdf(2.94MB)
----00 Cover.pdf(1.52MB)
----13 fact-based question decomposition.pdf(503KB)