AI Used to Fill in Missing Words in Ancient Writings
2022-03-17
LRC
TXT
大字
小字
滚动
全页
1Researchers have developed an artificial intelligence (AI) system to help fill in missing words in ancient writings.
2The system is designed to help historians restore the writings and identify when and where they were written.
3Many ancient populations used writings, also known as inscriptions, to document different parts of their lives.
4The inscriptions have been found on materials such as rock, ceramic and metal.
5The writings often contained valuable information about how ancient people lived and how they structured their societies.
6But in many cases, the objects containing such inscriptions have been damaged over the centuries.
7This left major parts of the inscriptions missing and difficult to identify and understand.
8In addition, many of the inscribed objects were moved from areas where they were first created.
9This makes it difficult for scientists to discover when and where the writings were made.
10The new AI-based method serves as a technological tool to help researchers repair missing inscriptions and estimate the true origins of the records.
11The researchers, led by Alphabet's AI company DeepMind, call their tool Ithaca.
12In a statement, the researchers said the system is "the first deep neural network that can restore the missing text of damaged inscriptions."
13A neural network is a machine learning computer system built to act like the human brain.
14The findings were recently reported in a study in the publication Nature.
15Researchers from other organizations - including the University of Oxford,
16Ca' Foscari University of Venice and Athens University of Economics and Business - also took part in the study.
17The team said it trained Ithaca on the largest collection of data containing Greek inscriptions from the non-profit Packard Humanities Institute in California.
18Feeding this data into the system is designed to help the tool use past writings to predict missing letters and words in damaged inscriptions.
19The researchers reported that in experiments with damaged writings, Ithaca was able to correctly predict missing inscription elements 62 percent of the time.
20In addition, the tool was 71 percent correct in identifying where the inscriptions first came from.
21And, the system was able to effectively date writings to within 30 years, the team said.
22Yannis Assael is a research scientist with DeepMind who helped lead the study.
23He said in a statement that Ithaca was designed to "support historians to expand and deepen our understanding of ancient history."
24When historians work on their own, the success rate for restoring damaged inscriptions is about 25 percent.
25But when humans teamed up with Ithaca to assist in their work, the success rate jumped to 72 percent, Assael said.
26Thea Sommerschield was another lead researcher on the project.
27She is the Marie Curie Fellow at Ca' Foscari University of Venice.
28Sommerschield said she hopes systems like Ithaca "can unlock the cooperative potential" between AI and humans in future restoration work involving important ancient inscriptions.
29She said the system had already provided new information to help researchers reexamine important periods in Greek history.
30In one case, Ithaca confirmed new evidence presented by historians about the dating of a series of important Greek decrees.
31The decrees were first thought to have been written before 446/445 BCE.
32But the new evidence suggested a date in the 420s BCE. Ithaca predicted a date of 421 BCE.
33Sommerschield said that the date change may seem small.
34But it has "significant implications for our understanding of the political history of Classical Athens," she added.
35The team is currently working on other versions of Ithaca trained on other ancient languages.
36DeepMind has launched a free, interactive tool based on the system for use by researchers, educators, museum workers and the public.
37I'm Bryan Lynn.
1Researchers have developed an artificial intelligence (AI) system to help fill in missing words in ancient writings. 2The system is designed to help historians restore the writings and identify when and where they were written. 3Many ancient populations used writings, also known as inscriptions, to document different parts of their lives. The inscriptions have been found on materials such as rock, ceramic and metal. The writings often contained valuable information about how ancient people lived and how they structured their societies. 4But in many cases, the objects containing such inscriptions have been damaged over the centuries. This left major parts of the inscriptions missing and difficult to identify and understand. 5In addition, many of the inscribed objects were moved from areas where they were first created. This makes it difficult for scientists to discover when and where the writings were made. 6The new AI-based method serves as a technological tool to help researchers repair missing inscriptions and estimate the true origins of the records. 7The researchers, led by Alphabet's AI company DeepMind, call their tool Ithaca. In a statement, the researchers said the system is "the first deep neural network that can restore the missing text of damaged inscriptions." A neural network is a machine learning computer system built to act like the human brain. 8The findings were recently reported in a study in the publication Nature. Researchers from other organizations - including the University of Oxford, Ca' Foscari University of Venice and Athens University of Economics and Business - also took part in the study. 9The team said it trained Ithaca on the largest collection of data containing Greek inscriptions from the non-profit Packard Humanities Institute in California. Feeding this data into the system is designed to help the tool use past writings to predict missing letters and words in damaged inscriptions. 10The researchers reported that in experiments with damaged writings, Ithaca was able to correctly predict missing inscription elements 62 percent of the time. In addition, the tool was 71 percent correct in identifying where the inscriptions first came from. And, the system was able to effectively date writings to within 30 years, the team said. 11Yannis Assael is a research scientist with DeepMind who helped lead the study. He said in a statement that Ithaca was designed to "support historians to expand and deepen our understanding of ancient history." 12When historians work on their own, the success rate for restoring damaged inscriptions is about 25 percent. But when humans teamed up with Ithaca to assist in their work, the success rate jumped to 72 percent, Assael said. 13Thea Sommerschield was another lead researcher on the project. She is the Marie Curie Fellow at Ca' Foscari University of Venice. Sommerschield said she hopes systems like Ithaca "can unlock the cooperative potential" between AI and humans in future restoration work involving important ancient inscriptions. 14She said the system had already provided new information to help researchers reexamine important periods in Greek history. 15In one case, Ithaca confirmed new evidence presented by historians about the dating of a series of important Greek decrees. The decrees were first thought to have been written before 446/445 BCE. But the new evidence suggested a date in the 420s BCE. Ithaca predicted a date of 421 BCE. 16Sommerschield said that the date change may seem small. But it has "significant implications for our understanding of the political history of Classical Athens," she added. 17The team is currently working on other versions of Ithaca trained on other ancient languages. DeepMind has launched a free, interactive tool based on the system for use by researchers, educators, museum workers and the public. 18I'm Bryan Lynn. 19Bryan Lynn wrote this story for VOA Learning English, based on reports from DeepMind, the University of Oxford, the University of Venice and Nature. 20We want to hear from you. Write to us in the Comments section, and visit our Facebook page. 21_______________________________________________________ 22Words in This Story 23artificial intelligence (AI) - n. the development of computer systems with the ability to perform work that normally requires human intelligence 24restore - v. to make something good exist again 25ceramic - n. objects made by shaping and heating clay 26society - n. a large group of people who live in the same country and share the same laws, traditions, etc. 27origins - n. the cause of something or where something comes from 28potential - n. a possibility when the necessary conditions exist 29decree - n. an official order for something 30significant - adj. important or noticeable 31implication - n. a result or effect