1 |
Semi-Supervised and Unsupervised Sense Annotation via Translations ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
WiC = TSV = WSD: On the Equivalence of Three Semantic Tasks ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Using Translations to Distinguish Between Homonymy and Polysemy
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Leveraging Translations for Word Sense Disambiguation
|
|
Luan, Yixing. - : University of Alberta. Department of Computing Science., 2020
|
|
BASE
|
|
Show details
|
|
7 |
Assessing the importance of several acoustic properties to the perception of spontaneous speech
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Relation Extraction and its Application to Question Answering
|
|
Xu, Ying. - : University of Alberta. Department of Computing Science., 2017
|
|
BASE
|
|
Show details
|
|
9 |
Identifying Cognate Sets Across Dictionaries of Related Languages
|
|
|
|
Abstract:
Degree: Master of Science ; Abstract: Cognates are words in related languages that have originated from the same word in an ancestor language, such as the English/German word pair father/Vater. Cognate information is critical in the field of historical linguistics, where it is used to determine the relationships between languages and to construct the ancestor languages they originated from. Most recent work in cognate identification focuses on the task of clustering cognates within lists of words each having an identical definition. In that task, only orthographic or phonetic information about a word is utilized when making cognate judgments. We present a system for the more challenging task of identifying cognate sets across dictionaries of related languages. The likelihood of a cognate relationship is calculated on the basis of a rich set of features that capture both phonetic and semantic similarity, as well as the presence of regular sound correspondences. The pairwise similarity scores are combined with an average-score clustering algorithm to create sets of words from different languages that may originate from a common proto-word. When tested on the Algonquian language family, our system detects 63% of cognate sets while maintaining cluster purity of 70%.
|
|
Keyword:
Cognates; Computational diachronic linguistics; Computational linguistics; Machine learning; Natural language processing
|
|
URL: http://hdl.handle.net/10402/era.43889 https://era.library.ualberta.ca/items/1daa2479-8131-48a7-ab5e-5b07f821c0d9 https://doi.org/10.7939/R3NV99Q98
|
|
BASE
|
|
Hide details
|
|
10 |
Modelling phonetic reduction in a corpus of spoken English using Random Forests and Mixed-Effects Regression
|
|
Dilts, Philip C. - : University of Alberta. Department of Linguistics., 2013
|
|
BASE
|
|
Show details
|
|
11 |
Modelling phonetic reduction in a corpus of spoken English using Random Forests and Mixed-Effects Regression
|
|
Dilts, Philip C. - : University of Alberta. Department of Linguistics., 2013
|
|
BASE
|
|
Show details
|
|
17 |
The Application of Chordal Graphs to Inferring Phylogenetic Trees of Languages
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Leveraging supplementary transcriptions and transliterations via re-ranking
|
|
Bhargava, Aditya. - : University of Alberta. Department of Computing Science., 2011
|
|
BASE
|
|
Show details
|
|
19 |
Leveraging supplementary transcriptions and transliterations via re-ranking
|
|
Bhargava, Aditya. - : University of Alberta. Department of Computing Science., 2011
|
|
BASE
|
|
Show details
|
|
|
|