Dealing with written language semantics by a connectionist model of cognitive reading

Although machines perform much better than human beings in most of the tasks, it is not the case of natural language processing. Computational linguistic systems usually rely on mathematical and statistical formalisms, which are efficient and useful but far from human procedures and therefore not so skilled. This paper proposes a computational model of natural language reading, called Cognitive Reading Indexing Model (CRIM), inspired by some aspects of human cognition, that tries to become as more psychologically plausible as possible. The model relies on a semantic neural network and it produces not vectors but nets of activated concepts as text representations. Based on these representations, measures of semantic similarity are also defined. Human comparison results show that the system is suitable to model human reading. Additional results also point out that the system could be used in real applications concerning natural language processing tasks.

[1]  Arthur C. Graesser,et al.  Similarity Between Semantic Spaces , 2005 .

[2]  Mark S. Seidenberg.  Connectionist Models of Word Reading , 2005 .

[3]  Richard M. Shiffrin,et al.  Incorporating Connotation of Meaning into Models of Semantic Representation: An Application in Text Corpus Analysis , 2007 .

[4]  Anders Holst,et al.  Random indexing of text samples for latent semantic analysis , 2000 .

[5]  Padraic Monaghan,et al.  Proceedings of the 23rd annual conference of the cognitive science society , 2001 .

[6]  W. Kintsch.  The role of knowledge in discourse comprehension: a construction-integration model. , 1988, Psychological review.

[7]  R. Azevedo,et al.  Testing and refining the direct and inferential mediation model of reading comprehension , 2007 .

[8]  Stefan L. Frank,et al.  Learn more by training less: systematicity in sentence processing by recurrent networks , 2006, Connect. Sci..

[9]  M. F. Porter,et al.  An algorithm for suffix stripping , 1997 .

[10]  Peter W. Foltz,et al.  An introduction to latent semantic analysis , 1998 .

[11]  Brian Riordan,et al.  Comparing semantic space models using child -directed speech , 2007 .

[12]  Melanie Mitchell,et al.  Analogy-making as perception - a computer model , 1993, Neural network modeling and connectionism.

[13]  Trent E. Lange,et al.  Dynamic Memories: Analysis of an Integrated Comprehension and Episodic Memory Retrieval Model , 1993, IJCAI.

[14]  Curt Burgess,et al.  From simple associations to the building blocks of language: Modeling meaning in memory with the HAL model , 1998 .

[15]  Cyrus Shaoul,et al.  Word frequency effects in high-dimensional co-occurrence models: A new approach , 2006, Behavior research methods.

[16]  Colin M. Brown,et al.  The neurocognition of language , 2000 .

[17]  Benoît Lemaire,et al.  Incremental Construction of an Associative Network from a Corpus , 2004 .

[18]  Kenneth D. Forbus,et al.  Proceedings of the 26th annual meeting of the Cognitive Science Society , 2004 .

[19]  Graeme Hirst,et al.  Semantic distance in WordNet: An experimental, application-oriented evaluation of five measures , 2004 .

[20]  Peter D. Turney.  Mining the Web for Synonyms: PMI-IR versus LSA on TOEFL , 2001, ECML.

[21]  Ashwin Ram,et al.  Understanding language understanding: computational models of reading , 1999 .

[22]  Richard M. Shiffrin,et al.  Word Association Spaces for Predicting Semantic Similarity Effects in Episodic Memory. , 2005 .

[23]  B. J. Casey,et al.  Semantic impairment with and without surface dyslexia: Implications for models of reading , 2005, Cognitive neuropsychology.

[24]  M. Sigman,et al.  The neural code for written words: a proposal , 2005, Trends in Cognitive Sciences.

[25]  Johanna D. Moore,et al.  Proceedings of the 28th Annual Conference of the Cognitive Science Society , 2005 .

[26]  Thorsten Joachims,et al.  A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Categorization , 1997, ICML.

[27]  Ming S. Hung,et al.  A computational study of efficient shortest path algorithms , 1988, Comput. Oper. Res..

[28]  Naohiro Ishii,et al.  Text Classification by Combining Grouping, LSA and kNN , 2006, 5th IEEE/ACIS International Conference on Computer and Information Science and 1st IEEE/ACIS International Workshop on Component-Based Software Engineering,Software Architecture and Reuse (ICIS-COMSAR'06).

[29]  Bonnie J. F. Meyer,et al.  Effects of Structure Strategy Training and Signaling on Recall of Text. , 2001 .

[30]  Neslihan Serap Sengör,et al.  Modelling the Stroop effect: A connectionist approach , 2007, Neurocomputing.

[31]  J. Bullinaria,et al.  Extracting semantic representations from word co-occurrence statistics: A computational study , 2007, Behavior research methods.

[32]  Fabrizio Sebastiani,et al.  Machine learning in automated text categorization , 2001, CSUR.

[33]  Marco Zorzi,et al.  Nested incremental modeling in the development of computational theories: the CDP+ model of reading aloud. , 2007, Psychological review.

[34]  Luc De Raedt,et al.  Proceedings of the 12th European Conference on Machine Learning , 2001 .