ACL RD-TEC 1.0 Summarization of W06-1107
Paper Title:
EVALUATION OF SEVERAL PHONETIC SIMILARITY ALGORITHMS ON THE TASK OF COGNATE IDENTIFICATION
EVALUATION OF SEVERAL PHONETIC SIMILARITY ALGORITHMS ON THE TASK OF COGNATE IDENTIFICATION
Authors: Grzegorz Kondrak and Tarek Sherif
Primarily assigned technology terms:
- algorithm
- baum-welch algorithm
- binary classi cation
- classi cation
- cognate identification
- cognate matching
- computational linguistics
- computing
- cross-language information retrieval
- database
- decomposition
- dynamic bayesian nets
- dynamic programming
- dynamic programming algorithm
- dynamic time warping
- edit distance algorithm
- expectation maximization
- hidden markov
- hidden markov model
- hmms
- identification
- information retrieval
- learning
- learning algorithms
- learning approaches
- learning methods
- learning process
- learning techniques
- levenshtein
- linking
- machine learning
- machine learning algorithms
- machine learning techniques
- machine transliteration
- markov model
- matching
- measuring
- modeling
- multidimensional scaling
- normalization
- orthographic representation
- parameter estimation
- phonetic similarity algorithms
- processing
- programming algorithm
- ranking
- recognition
- scoring
- speech processing
- speech production
- spelling
- spelling correction
- time warping
- training process
- transducer
- transliteration
- viterbi
Other assigned terms:
- acyclic graph
- alphabet
- approach
- association for computational linguistics
- bias
- bitext
- case
- characters
- chunk
- computational linguistics evaluation
- conditional probability
- context model
- contextual information
- data corpus
- data sets
- development set
- distance metric
- distribution
- edit distance
- estimation
- euclidean distance
- fact
- feature
- feature set
- frame
- french
- generation
- grounding
- hmm model
- hypotheses
- indoeuropean data corpus
- knowledge
- language pairs
- large training
- levenshtein distance
- lexicon
- likelihood
- linguistic
- linguistic intuition
- linguistics
- maximum similarity
- meaning
- meanings
- measure
- measures
- method
- noise
- pairs of words
- phoneme
- phonemes
- phonetic similarity
- positive and negative examples
- precision
- probabilities
- probability
- probability distribution
- process
- pronunciation
- recognition precision
- roman alphabet
- segments
- similarity between words
- similarity matrix
- similarity score
- similarity scores
- symbol
- target word
- technique
- terms
- test data
- test set
- testing data
- toolkit
- training
- training data
- training set
- translation model
- vowel
- word
- word lists
- word pair
- word similarity
- words
