Learning to identify animate references

نویسندگان

  • Constantin Orasan
  • Richard Evans
چکیده

Information about the animacy of nouns is important for a wide range of tasks in NLP. In this paper, we present a method for determining the animacy of English nouns using WordNet and machine learning techniques. Our method firstly categorises the senses from WordNet using an annotated corpus and then uses this information in order to classify nouns for which the sense is not known. Our evaluation results show that the accuracy of the classification of a noun is around 97% and that animate entities are more difficult to identify than inanimate ones.

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

Adaptive memory: animacy effects persist in paired-associate learning.

Recent evidence suggests that animate stimuli are remembered better than matched inanimate stimuli. Two experiments tested whether this animacy effect persists in paired-associate learning of foreign words. Experiment 1 randomly paired Swahili words with matched animate and inanimate English words. Participants were told simply to learn the English "translations" for a later test. Replicating e...

متن کامل

First Principles Organize Attention to and Learning About Relevant Data: Number and the Animate-Inanimate Distinction as Examples

Early cognitive development benefits from nonilnguistic representations of skeietai sets of domain-specific principles and complementary domain-relevant doto obstroction processes. The principles outline the domain, identify relevant inputs, and structure coherently what is learned. Knowledge acquisition within the domoin is a faint function of such domain-specific principles and domain-general...

متن کامل

First Principles Organize Attention to and Learning About Relevant Data : Number and the Animate - lnanimate Distinction as Examples ROCHEL

Early cognitive development benefits from nonilnguistic representations of skeietai sets of domain-specific principles and complementary domain-relevant doto obstroction processes. The principles outline the domain, identify relevant inputs, and structure coherently what is learned. Knowledge acquisition within the domoin is a faint function of such domain-specific principles and domain-general...

متن کامل

When a Stone Tries to Climb up a Slope: The Interplay between Lexical and Perceptual Animacy in Referential Choices

Several studies suggest that referential choices are influenced by animacy. On the one hand, animate referents are more likely to be mentioned as subjects than inanimate referents. On the other hand, animate referents are more frequently pronominalized than inanimate referents. These effects have been analyzed as effects of conceptual accessibility. In this paper, we raise the question whether ...

متن کامل

Eugene Garfield and Algorithmic Historiography: Co-Words, Co-Authors, and Journal Names

Algorithmic historiography was proposed by Eugene Garfield in collaboration with Irving Sher in the 1960s, but further developed only recently into HistCiteTM with Alexander Pudovkin. As in history writing, HistCiteTM reconstructs by drawing intellectual lineages. In addition to cited references, however, documents can be attributed a multitude of other variables such as title words, keywords, ...

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 2001