Humans Outperform Machines at the Bilingual Shannon Game

نویسندگان

  • Marjan Ghazvininejad
  • Kevin Knight
چکیده

We provide an upper bound for the amount of information a human translator adds to an original text, i.e., how many bits of information we need to store a translation, given the original. We do this by creating a Bilingual Shannon Game that elicits character guesses from human subjects, then developing models to estimate the entropy of those guess sequences.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Communication between Humans and Machines in a Hybrid Inspection System

Recently, 100% inspection using automated systems has seen more frequent application than traditional sampling inspection using human inspectors. Nevertheless, humans still outperform machines in most attribute inspection tasks. Studies have shown that hybrid inspection systems where humans work corporately with machines might achieve superior system performance than either humans or machines a...

متن کامل

Developing a based-on play cognitive-behavioral educational package and determining its effectiveness on improving the language disorders and social adjustment of bilingual children

Background: The present study was conducted with the aim of developing a game-based cognitive-behavioral educational package and determining its effectiveness on improving the receptive language disorders and social adjustment of bilingual children. Methods:  The current study was applied in terms of purpose and in terms of the nature of the data, it was semi-experimental with a pre-test-post...

متن کامل

WordSleuth: Deducing Social Connotations from Syntactic Clues

0. Abstract The realm of social and emotional connotation is often thought to be the purview of humans rather than machines. Namely, humans are generally capable of recognizing social connotations including emotions (such as embarrassment), intentions (deception and persuading), attitudes (confidence and disbelief), and tone (formality, politeness, rudeness), and recent work has suggested that ...

متن کامل

Managing the Supply Chain with Intelligent Software Agents Using an Asymmetric Cost Function

Using an exact replication of the MIT Beer Game, a supply chain simulation was developed in which Intelligent Software Agents manage the supply chain subject to all of the constraints placed on the original human players. The agents’ information processing capabilities are founded on Support Vector Machines (SVM) with an asymmetric cost function, which permits internal modeling of appropriate s...

متن کامل

A Web-Based Agent Challenges Human Experts on Crosswords

with “the smallest initial structures” (Minsky 1968), thus making their study important for both theoretical and practical issues. Since the birth of artificial intelligence (AI), games and puzzles have received much attention. The game that has captured most of the attention of computer scientists is chess. The founding fathers of AI such as McCarthy, Simon (Simon and Schaeffer 1992), Samuel, ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:
  • Entropy

دوره 19  شماره 

صفحات  -

تاریخ انتشار 2017