Inferring Psycholinguistic Properties of Words

Proceedings of NAACL-HLT 2016, pages 435–440, San Diego, California, June 12-17, 2016. c⃝2016 Association for Computational Linguistics Inferring Psycholinguistic Properties of Words Gustavo Henrique Paetzold and Lucia Specia Department of Computer Science University of Sheffield, UK {ghpaetzold1,l.specia}@sheffield.ac.uk Abstract We introduce a bootstrapping algorithm for re- gression that exploits word embedding mod- els. We use it to infer four psycholinguis- tic properties of words: Familiarity, Age of Acquisition, Concreteness and Imagery and further populate the MRC Psycholinguistic Database with these properties. The ap- proach achieves 0.88 correlation with human- produced values and the inferred psycholin- guistic features lead to state-of-the-art results when used in a Lexical Simplification task. 1 Introduction Throughout the last three decades, much has been found on how the psycholinguistic properties of words influence cognitive processes in the human brain when a subject is presented with either writ- ten or spoken forms. A word’s Age of Acquisition is an example. The findings in (Carroll and White, 1973) reveal that objects whose names are learned earlier in life can be named faster in later stages of life. Zevin and Seidenberg (2002) show that words learned in early ages are orthographically or phono- logically very distinct from those learned in adult life. Other examples of psycholinguistic properties, such as Familiarity and Concreteness, influence one’s proficiency in word recognition and text com- prehension. The experiments in (Connine et al., 1990; Morrel-Samuels and Krauss, 1992) show that words with high Familiarity yield lower reaction times in both visual and auditory lexical decision, and require less hand gesticulation in order to be de- scribed. Begg and Paivio (1969) found that humans are less sensitive to changes in wording made to sen- tences with high Concreteness words. When quantified, these aspects can be used as features for various Natural Language Processing (NLP) tasks. The Lexical Simplification approach in (Jauhar and Specia, 2012) is an example. By combining various collocational features and psy- cholinguistic measures extracted from the MRC Psycholinguistic Database (Coltheart, 1981), they trained a ranker (Joachims, 2002) that reached first place in the English Lexical Simplification task at SemEval 2012. Semantic Classification tasks have also benefited from the use of such features: by combining Concreteness with other features, (Hill and Korhonen, 2014) reached the state-of-the- art performance in Semantic Composition (denota- tive/connotative) and Semantic Modification (inter- sective/subsective) prediction. Despite the evident usefulness of psycholinguis- tic properties of words, resources describing such properties are rare. The most extensively developed resource for English is the MRC Psycholinguistic Database (Section 2). However, it is far from com- plete, most likely due to the inherent cost of manu- ally entering such properties. In this paper we pro- pose a method to automatically infer these missing properties. We train regressors by performing boot- strapping (Yarowsky, 1995) over the existing fea- tures in the MRC database, exploiting word em- bedding models and other linguistic resources for that (Section 3). This approach outperform various strong baselines (Section 4) and the resulting prop- erties lead to significant improvements when used in …

Content truncated to 500 words