Natat in Cerebro: Intelligent Information Retrieval for "The Guillotin" Language Game

نویسندگان

  • Pierpaolo Basile
  • Marco Degemmis
  • Pasquale Lops
  • Giovanni Semeraro
چکیده

This paper describes OTTHO (On the Tip of my THOught), a system designed for solving a language game, called Guillotine. The rule of the game is simple: the player observes five words, generally unrelated to each other, and in one minute she has to provide a sixth word, semantically connected to the others. The system performs retrieval from several knowledge sources, such as a dictionary, a set of proverbs, and Wikipedia to realize a knowledge infusion process. The main motivation for designing an artificial player for Guillotine is the challenge of providing the machine with the cultural and linguistic background knowledge which makes it similar to a human being, with the ability of interpreting natural language documents and reasoning on their content. Our feeling is that the approach presented in this work has a great potential for other more practical applications besides solving a language game. 1. BACKGROUND AND MOTIVATION Words are popular features of many games, and they play a central role in many language games. A language game is defined as a game involving natural language in which word meanings play an important role. Language games draw their challenge and excitement from the richness and ambiguity of natural language. In this paper we present a system that tries to play the Guillotine game. The Guillotine is a language game played in a show on RAI, the Italian National Broadcasting Service, in which a player is given a set of five words (clues), each linked in some way to a specific word that represents the unique solution of the game. ∗The full version appears in [3] Appears in the Proceedings of the 1st Italian Information Retrieval Workshop (IIR’10), January 27–28, 2010, Padova, Italy. http://ims.dei.unipd.it/websites/iir10/index.html Copyright owned by the authors. She receives one word at a time, and must choose between two different proposed words: one is correct, the other one is wrong. Each time she chooses the wrong word, the prize money is divided by half (the reason for the name Guillotine). The five words are generally unrelated to each other, but each of them is strongly related to the word representing the solution. Once the five clues are given, the player has one minute to provide the solution. An example of the game follows: Given the five words Capital, Pope, City, Colosseum, YellowAndRed, the solution is Rome, because Rome is Capital of Italy, the Pope lives in Rome, Rome is a City, the Colosseum is in Rome and YellowAndRed is an alternative name for one of the Rome football teams. Often the solution is not so intuitive and the player needs different knowledge sources to reason and find the correct word. OTTHO (On the Tip of my THOught) tries to solve the final stage of the Guillotine game. We assume that the five words are provided at the same time, neglecting the initial phase of choosing the words, that only concerns the reduction of the initial prize.

برای دانلود 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

Improved Skips for Faster Postings List Intersection

Information retrieval can be achieved through computerized processes by generating a list of relevant responses to a query. The document processor, matching function and query analyzer are the main components of an information retrieval system. Document retrieval system is fundamentally based on: Boolean, vector-space, probabilistic, and language models. In this paper, a new methodology for mat...

متن کامل

Improved Skips for Faster Postings List Intersection

Information retrieval can be achieved through computerized processes by generating a list of relevant responses to a query. The document processor, matching function and query analyzer are the main components of an information retrieval system. Document retrieval system is fundamentally based on: Boolean, vector-space, probabilistic, and language models. In this paper, a new methodology for mat...

متن کامل

JaBot: A Multilingual Java-Based Intelligent Agent for Web Sites

Abstrac t This paper presents a novel type of intelligent agent with a multilingual natural language interface, which retrieves information from within a Web site. This agent, named JaBot after the fact that it is a bot which has been programmed in Java, has been designed and developed by the authors in an attempt to solve common Web site problems related to information retrieval. JaBot runs qu...

متن کامل

بررسی تأثیرات ریشه‌یابی در بازیابی اطلاعات در زبان فارسی

Using the language-specific behavior in information retrieval systems can improve the quality of the retrieved results significantly. Part of the word that remains after removing its affixes is called stem. Stemming process can be used for improving the relevancy of the results in information retrieval system. Different morphological variants of words (plural, past tense…) will be mapped into t...

متن کامل

Impact of Controlled and Free Language Use in Retrieving Articles from the ProQuest and Science Direct Databases

Abstract Introduction: The growth and expansion of the Internet has changed the way information is accessed and many facilities have been created on the Web to facilitate and expedite information locating. Objective: To identify the impact of keyword documentation using the medical thesaurus on the retrieval of articles from Proquest and Science Direct databases. Materials and Methods:The pr...

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

برای دانلود 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

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2010