scholarly journals Discovering Non-taxonomic Relations from the Web

Author(s):  
David Sánchez ◽  
Antonio Moreno
Keyword(s):  
2019 ◽  
Vol 9 (1) ◽  
pp. 252-267
Author(s):  
Alfredo Maldonado ◽  
Filip Klubička ◽  
John Kelleher

AbstractWord embeddings trained on natural corpora (e.g., newspaper collections, Wikipedia or the Web) excel in capturing thematic similarity (“topical relatedness”) on word pairs such as ‘coffee’ and ‘cup’ or ’bus’ and ‘road’. However, they are less successful on pairs showing taxonomic similarity, like ‘cup’ and ‘mug’ (near synonyms) or ‘bus’ and ‘train’ (types of public transport). Moreover, purely taxonomy-based embeddings (e.g. those trained on a random-walk of WordNet’s structure) outperform natural-corpus embeddings in taxonomic similarity but underperform them in thematic similarity. Previous work suggests that performance gains in both types of similarity can be achieved by enriching natural-corpus embeddings with taxonomic information from taxonomies like Word-Net. This taxonomic enrichment can be done by combining natural-corpus embeddings with taxonomic embeddings (e.g. those trained on a random-walk of WordNet’s structure). This paper conducts a deep analysis of this assumption and shows that both the size of the natural corpus and of the random-walk coverage of the WordNet structure play a crucial role in the performance of combined (enriched) vectors in both similarity tasks. Specifically, we show that embeddings trained on medium-sized natural corpora benefit the most from taxonomic enrichment whilst embeddings trained on large natural corpora only benefit from this enrichment when evaluated on taxonomic similarity tasks. The implication of this is that care has to be taken in controlling the size of the natural corpus and the size of the random-walk used to train vectors. In addition, we find that, whilst the WordNet structure is finite and it is possible to fully traverse it in a single pass, the repetition of well-connected WordNet concepts in extended random-walks effectively reinforces taxonomic relations in the learned embeddings.


2003 ◽  
pp. 301-319 ◽  
Author(s):  
Alexander Maedche ◽  
Viktor Pekar ◽  
Steffen Staab

2008 ◽  
Vol 11 (2) ◽  
pp. 83-85
Author(s):  
Howard Wilson
Keyword(s):  

2005 ◽  
Vol 8 (1) ◽  
pp. 16-18
Author(s):  
Howard F. Wilson
Keyword(s):  

1999 ◽  
Vol 3 (2) ◽  
pp. 6-6
Author(s):  
Barbara Shadden
Keyword(s):  

1999 ◽  
Vol 3 (1) ◽  
pp. 3-3
Author(s):  
Barbara B. Shadden
Keyword(s):  

2008 ◽  
Vol 18 (1) ◽  
pp. 9-20 ◽  
Author(s):  
Mark Kander ◽  
Steve White

Abstract This article explains the development and use of ICD-9-CM diagnosis codes, CPT procedure codes, and HCPCS supply/device codes. Examples of appropriate coding combinations, and Coding rules adopted by most third party payers are given. Additionally, references for complete code lists on the Web and a list of voice-related CPT code edits are included. The reader is given adequate information to report an evaluation or treatment session with accurate diagnosis, procedure, and supply/device codes. Speech-language pathologists can accurately code services when given adequate resources and rules and are encouraged to insert relevant codes in the medical record rather than depend on billing personnel to accurately provide this information. Consultation is available from the Division 3 Reimbursement Committee members and from [email protected] .


2001 ◽  
Vol 35 (2) ◽  
pp. 91-91
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document