SegStereo: Exploiting Semantic Information for Disparity Estimation

For many decades there has been a consensus among linguists of various schools that derivational suffixes function not only to determine the word-class of the complex expressions they form, but also convey semantic information. The aspect of suffix-inherent meaning is ignored by representatives of a relatively new theoretical direction – Neo-Construction Grammar – who consider derivational suffixes to be either purely functional elements of the grammar or meaningless phonological realizations of abstract grammatical morphemes. The latter view is maintained by adherents of Distributed Morphology, who at the same time emphasize the importance of conceptual knowledge for derivational processes without attempting to define this aspect. The purpose of this study is first of all to provide support for the long-standing assumption that suffixes are inherently meaningful. The focus of interest is on the suffixes -ship, -dom and -hood. Data from Old English and Modern English (including neologisms) will show that these suffixes have developed rich arrays of meaning which cannot be structurally derived. Moreover, since conceptual knowledge is indeed an important factor for word-formation processes, a concrete, theory-independent model for the representation of the synchronically observable meaning components associated with -ship, -dom and -hood will be proposed.

Download Full-text

The research of semantic information retrieval for Mongolian data structure

Advanced Materials and Information Technology Processing ◽

10.2495/amitp130781 ◽

2014 ◽

Author(s):

Yila Su ◽

Chuan Fan ◽

Hongbo Chen ◽

Xiulan Xie ◽

Haitao Liu

Keyword(s):

Information Retrieval ◽

Data Structure ◽

Semantic Information ◽

Semantic Information Retrieval

Download Full-text

Natural language interfaces using limited semantic information

10.3115/991813.991827 ◽

1982 ◽

Cited By ~ 3

Author(s):

Ralph Grishman ◽

Lynette Hirschman ◽

Carol Friedman

Keyword(s):

Natural Language ◽

Semantic Information ◽

Natural Language Interfaces

Download Full-text

An Investigation on Ontology Based Fuzzy Semantic Information Retrieval

International Journal of Psychosocial Rehabilitation ◽

10.37200/ijpr/v23i1/pr190248 ◽

2019 ◽

Vol 23 (1) ◽

pp. 377-384

Author(s):

Naren J ◽

Raja Rajeswari D ◽

Nikhith Sannidhi ◽

Vithya G

Keyword(s):

Information Retrieval ◽

Semantic Information ◽

Semantic Information Retrieval

Download Full-text

Fast disparity estimation algorithm based on features of disparity vector

Journal of Computer Applications ◽

10.3724/sp.j.1087.2012.01856 ◽

2013 ◽

Vol 32 (6) ◽

pp. 1856-1859

Author(s):

Xiao-wei SONG ◽

Lei YANG ◽

Zhong LIU ◽

Liang LIAO

Keyword(s):

Estimation Algorithm ◽

Disparity Estimation ◽

Disparity Vector

Download Full-text

Key phrase Extraction by Improving TextRank with an Integration of Word Embedding and Syntactic Information

Recent Advances in Computer Science and Communications ◽

10.2174/2666255813999200820155846 ◽

2020 ◽

Vol 13 ◽

Author(s):

Sheng Zhang ◽

Qi Luo ◽

Yukun Feng ◽

Ke Ding ◽

Daniela Gifu ◽

...

Keyword(s):

Semantic Information ◽

Performance Enhancement ◽

Word Embedding ◽

The Other ◽

Test Set ◽

Pagerank Algorithm ◽

Phrase Extraction ◽

Extraction Algorithm ◽

Syntactic Information ◽

Key Phrase Extraction

Background: As a known key phrase extraction algorithm, TextRank is an analogue of PageRank algorithm, which relied heavily on the statistics of term frequency in the manner of co-occurrence analysis. Objective: The frequency-based characteristic made it a neck-bottle for performance enhancement, and various improved TextRank algorithms were proposed in the recent years. Most of improvements incorporated semantic information into key phrase extraction algorithm and achieved improvement. Method: In this research, taking both syntactic and semantic information into consideration, we integrated syntactic tree algorithm and word embedding and put forward an algorithm of Word Embedding and Syntactic Information Algorithm (WESIA), which improved the accuracy of the TextRank algorithm. Results: By applying our method on a self-made test set and a public test set, the result implied that the proposed unsupervised key phrase extraction algorithm outperformed the other algorithms to some extent.

Download Full-text