Statistical Estimation of Word Acquisition with Application to Readability Prediction

Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing, pages 900–909, Singapore, 6-7 August 2009. c⃝2009 ACL and AFNLP Statistical Estimation of Word Acquisition with Application to Readability Prediction Paul Kidwell Department of Statistics Purdue University West Lafayette, IN kidwellpaul@gmail.com Guy Lebanon College of Computing Georgia Institute of Technology Atlanta, GA lebanon@cc.gatech.edu Kevyn Collins-Thompson Microsoft Research Redmond, WA kevynct@microsoft.com Abstract Models of language learning play a cen- tral role in a wide range of applica- tions: from psycholinguistic theories of how people acquire new word knowledge, to information systems that can automati- cally match content to users’ reading abil- ity. We present a novel statistical ap- proach that can infer the distribution of a word’s likely acquisition age automati- cally from authentic texts collected from the Web. We then show that combining these acquisition age distributions for all words in a document provides an effective semantic component for predicting read- ing difficulty of new texts. We also com- pare our automatically inferred acquisition ages with norms from existing oral stud- ies, revealing interesting historical trends as well as differences between oral and written word acquisition processes. 1 Introduction Word acquisition refers to the temporal process by which children learn the meaning and understand- ing of new words. Some words are acquired at a very early age, some are acquired at early pri- mary school grades, and some are acquired at high school or even later in life as the individual under- goes experiences related to that word. A related concept to acquisition age is document grade level readability which refers to the school grade level of the document’s intended audience. It applies in situations where documents are written with the expressed intent of being understood by children in a certain school grade. For example, textbooks authored specifically for fourth graders are said to have readability grade level four. We develop and evaluate a novel statistical model that draws a connection between document grade level readability and age acquisition distri- butions. Based on previous work in the area, we define a model for document readability using a logistic Rasch model and the quantiles of the ac- quisition age distributions. We then proceed to in- fer the age acquisition distributions for different words from document readability data collected by crawling the web. We examine the inferred acquisition distribu- tions from two perspectives. First, we analyze and contrast them with previous studies on oral word acquisition, revealing interesting historical trends as well as differences between oral and written word acquisition processes. Second, the inferred acquisition distributions serve as parameters for the readability model, which enables us to predict the readability level of novel documents. To our knowledge, this is the first published study of a method to ‘reverse-engineer’ individ- ual word acquisition statistics from graded texts. By obtaining such a fine-grained model of how language evolves over time, we obtain a new, rich source of semantic features for a document. The increasing amounts of content available from the Web and …

Content truncated to 500 words