论文信息 - Syntax is from Mars while Semantics from Venus! Insights from Spectral Analysis of Distributional Similarity Networks

Syntax is from Mars while Semantics from Venus! Insights from Spectral Analysis of Distributional Similarity Networks

We study the global topology of the syntactic and semantic distributional similarity networks for English through the technique of spectral analysis. We observe that while the syntactic network has a hierarchical structure with strong communities and their mixtures, the semantic network has several tightly knit communities along with a large core without any such well-defined community structure.

[1] Dekang Lin,et al. Automatic Retrieval and Clustering of Similar Words , 1998, ACL.

[2] Shlomo Moran,et al. The stochastic approach for link-structure analysis (SALSA) and the TKC effect , 2000, Comput. Networks.

[3] Ted Dunning,et al. Accurate Methods for the Statistics of Surprise and Coincidence , 1993, CL.

[4] Christian Biemann,et al. Unsupervised Part-of-Speech Tagging Employing Efficient Graph Clustering , 2006, ACL.

[5] Animesh Mukherjee,et al. Discovering Global Patterns in Linguistic Networks through Spectral Analysis: A Case Study of the Consonant Inventories , 2009, EACL.

[6] Mikhail Belkin,et al. Using eigenvectors of the bigram graph to infer morpheme identity , 2002, SIGMORPHON.

[7] Mark Johnson,et al. Parsing the Wall Street Journal using a Lexical-Functional Grammar and Discriminative Estimation Techniques , 2002, ACL.

[8] Zellig S. Harris,et al. Mathematical structures of language , 1968, Interscience tracts in pure and applied mathematics.

[9] Joy Deep Nath,et al. Unsupervised Parts-of-Speech Induction for Bengali , 2008, LREC.