昝亞娟

Interesting Engineering reports on a machine learning program that researchers have taught to spot likely archaeological sites from satellite imagery， thus informing archaeologists on where they can direct their digging attention.

Interesting Engineering provides the context for how the AI program works. Scientists used almost 5，000 known Mesopotamiam archaeological sites to train the model on the shapes of these sites from satellite photos. Afterwards， the program learned to generalize and spot these shapes and patterns on new satellite imagery.

However， there was a catch. Although 5，000 sites may seem like a lot， in the context of machine learning it wasnt necessarily sufficient data. “The dataset， while may be considered a very large one for near eastern archaeology with its almost 5，000 sites， is hardly sufficient for training a model as large as the state-of-the-art ones we see in use today and， perhaps more significantly， contains many cases that are visible only on certain old imagery，” the researchers who trained the model wrote.

The solution was a novel form of cooperation between the researchers and artificial intelligence. In addition to letting the program learn on its own， scientists kept experienced humans involved in the training and evaluating the output. The result produced a model that can spot Mesopotamian sites with 80 percent accuracy.

AI models have been supporting archaeologists in other ways for some time now. For example， as Arkeonews reports， Turkish researchers fed photographs of ancient Hittite tablets into a machine learning algorithm. The program decoded and translated the ancient language with more than 75 percent accuracy.

Zeynel Karacagil， a project coordinator told Arkeonews， “The rate of 75.66 percent in the first phase is a great success for the academic community and our country. It is the first time that cuneiforms in Hittite have been translated in this manner. It is a source of pride for us to achieve such success for the first time with our local and national researchers.”

（材料出自“Goodnet”網(wǎng)站，有刪改）

1. What can a machine learning program do to help archaeologists？

A. To analyze the data collected by the AI program.

B. To provide them with better satellite photos.

C. To direct their attention to likely archaeological sites.

D. To collect sufficient data for satellites.

2. What does the underlined sentence in Paragraph 3 mean？

A. The satellite images are not clear.

B. The calculating was not precise.

C. The result was satisfactory.

D. There was a problem.

3. Why did the researchers and computers work together？

A. To increase work efficiency.

B. To improve accuracy.

C. To save energy.

D. To reduce cost.

4. What is Zeynel Karacagils attitude towards the AI program？

A. Favorable.B. Doubtful.

C. Cautious.D. Neutral.

1.C。解析：細(xì)節(jié)理解題。根據(jù)材料第一段，我們可知，Interesting Engineering報(bào)道了一個(gè)機(jī)器學(xué)習(xí)程序，研究人員已經(jīng)教會(huì)它從衛(wèi)星圖像中發(fā)現(xiàn)可能存在的考古遺址。故最佳答案為C。

2.D。解析：推理判斷題。根據(jù)材料第三段第二句，我們可知，雖然5000個(gè)考古地點(diǎn)看起來很多，但在當(dāng)前背景下，這并不一定是足夠的數(shù)據(jù)。換言之，這個(gè)人工智能程序存在一個(gè)問題。故最佳答案為D。

3.B。解析：推理判斷題。根據(jù)材料第四段的最后一句“The result produced a model that can spot Mesopotamian sites with 80 percent accuracy.”，我們可知，人和計(jì)算機(jī)合作的結(jié)果是制作出了一個(gè)模型，它發(fā)現(xiàn)美索不達(dá)米亞遺址的準(zhǔn)確率達(dá)80%。故最佳答案為B。

4.A。解析：推理判斷題。根據(jù)材料最后一段，我們可知，Zeynel Karacagil對(duì)人工智能給予高度評(píng)價(jià)。故最佳答案為A。