Slide 1
Slide 1 text
Using Sequence Similarity Networks
to Identify Partial Cognates in
Multilingual Wordlists
Johann-Mattis List, Philippe Lopez, and Eric Bapteste
Slide 2
Slide 2 text
Introduction
Slide 3
Slide 3 text
Keys to the Past
by comparing the languages of the world, we gain invaluable
insights
● into the past of the languages spoken in the world
● into the history of ancestral populations
● into human prehistory in general
Slide 4
Slide 4 text
Keys to the Past
in order to compare the languages in the world
● we need to prove that two or more languages are
genetically related by
● identifying elements they have inherited from their
common ancestors
Slide 5
Slide 5 text
Keys to the Past
having identified these cognate elements (usually words and
morphemes)
● we can calculate phylogenetic trees and networks,
● we can reconstruct the words in the unattested ancestral
languages, and
● we can try to learn more about these language families
(when they existed, how they developed, etc.)
Slide 6
Slide 6 text
Finding Cognate Words
increasing amounts of digital data of the languages in the
world necessitate the use of automatic methods for language
comparison, but unfortunately
● available methods work well on small language families
with moderate time depths,
● but they completely fail when it comes to the detection of
words which are only partially cognate
Slide 7
Slide 7 text
Finding Cognate Words
“moon” in Germanic languages
English moon
German Mond
Dutch maan
Swedish måne
Slide 8
Slide 8 text
Finding Cognate Words
“moon” in Germanic languages “moon” in Chinese dialects
English moon Fúzhōu ŋuoʔ⁵
German Mond Měixiàn ŋiat⁵ kuoŋ⁴⁴
Dutch maan Wēnzhōu ȵy²¹ kuɔ³⁵ vai¹³
Swedish måne Běijīng yɛ⁵¹ liɑŋ¹
Slide 9
Slide 9 text
Finding Cognate Words
“moon” in Germanic languages “moon” in Chinese dialects
English moon Fúzhōu ŋuoʔ⁵
German Mond Měixiàn ŋiat⁵ kuoŋ⁴⁴
Dutch maan Wēnzhōu ȵy²¹ kuɔ³⁵ vai¹³
Swedish måne Běijīng yɛ⁵¹ liɑŋ¹
Slide 10
Slide 10 text
Finding Cognate Words
“moon” in Germanic languages “moon” in Chinese dialects
English moon Fúzhōu ŋuoʔ⁵
German Mond Měixiàn ŋiat⁵ kuoŋ⁴⁴
Dutch maan Wēnzhōu ȵy²¹ kuɔ³⁵ vai¹³
Swedish måne Běijīng yɛ⁵¹ liɑŋ¹
Slide 11
Slide 11 text
Finding Cognate Words
“moon” in Germanic languages “moon” in Chinese dialects
English moon Fúzhōu moon
German Mond Měixiàn moon shine
Dutch maan Wēnzhōu moon shine suff.
Swedish måne Běijīng moon gloss
Slide 12
Slide 12 text
Finding Cognate Words
“moon” in Germanic languages “moon” in Chinese dialects
English moon Fúzhōu moon
German Mond Měixiàn moon shine
Dutch maan Wēnzhōu moon shine suff.
Swedish måne Běijīng moon gloss
So far, no algorithm can detect these shared similarities across
words in language families like Sino-Tibetan, Austro-Asiatic,
Tai-Kadai, etc.
Slide 13
Slide 13 text
Finding Cognate Words
“moon” in Germanic languages “moon” in Chinese dialects
English moon ? Fúzhōu moon ?
German Mond ? Měixiàn moon shine ?
Dutch maan ? Wēnzhōu moon shine suff. ?
Swedish måne ? Běijīng moon gloss ?
But not only are our algorithms not capable of detecting the
structures: We also have huge problems to actually use this
information in phylogenetic tree reconstruction and related
tasks.
Slide 14
Slide 14 text
Finding Cognate Words
“moon” in Germanic languages “moon” in Chinese dialects
English moon 1 Fúzhōu moon ?
German Mond 1 Měixiàn moon shine ?
Dutch maan 1 Wēnzhōu moon shine suff. ?
Swedish måne 1 Běijīng moon gloss ?
But not only are our algorithms not capable of detecting the
structures: We also have huge problems to actually use this
information in phylogenetic tree reconstruction and related
tasks.
Slide 15
Slide 15 text
Finding Cognate Words
“moon” in Germanic languages “moon” in Chinese dialects
English moon 1 Fúzhōu moon 1
German Mond 1 Měixiàn moon shine 1
Dutch maan 1 Wēnzhōu moon shine suff. 1
Swedish måne 1 Běijīng moon gloss 1
Most algorithms require binary (yes/no) cognate decisions as input.
But given the data for Chinese dialects, should we
1. label them all as cognate words, as they share one element?
2. label them all as different, as their strings all differ?
loose coding
of partial
cognates
Slide 16
Slide 16 text
Finding Cognate Words
“moon” in Germanic languages “moon” in Chinese dialects
English moon 1 Fúzhōu moon 1
German Mond 1 Měixiàn moon shine 2
Dutch maan 1 Wēnzhōu moon shine suff. 3
Swedish måne 1 Běijīng moon gloss 4
Most algorithms require binary (yes/no) cognate decisions as input.
But given the data for Chinese dialects, should we
1. label them all as cognate words, as they share one element?
2. label them all as different, as their strings all differ?
strict coding
of partial
cognates
Slide 17
Slide 17 text
Finding Cognate Words
“moon” in Germanic languages “moon” in Chinese dialects
English moon 1 Fúzhōu moon 1
German Mond 1 Měixiàn moon shine 1 2
Dutch maan 1 Wēnzhōu moon shine suff. 1 2 3
Swedish måne 1 Běijīng moon gloss 1 4
Ideally, we label them exactly as they are, as the exact coding
enables us to switch to strict or loose coding automatically.
exact coding
of partial
cognates
Slide 18
Slide 18 text
Materials
Slide 19
Slide 19 text
New Gold Standards
Dataset Bai Chinese Tujia
Languages 9 18 5
Words 1028 3653 513
Concepts 110 180 109
Strict Cognates 285 1231 247
Partial Cognates 309 1408 348
Sounds 94 122 57
Source Wang 2006 Běijīng Dàxué 1964 Starostin 2013
Slide 20
Slide 20 text
New Gold Standards
Dataset Bai Chinese Tujia
Languages 9 18 5
Words 1028 3653 513
Concepts 110 180 109
Strict Cognates 285 1231 247
Partial Cognates 309 1408 348
Sounds 94 122 57
Source Wang 2006 Běijīng Dàxué 1964 Starostin 2013
This is the first time that a valid gold
standard was created for the task of
partial cognate detection!
Slide 21
Slide 21 text
New Gold Standards
Text file of the data (originally CSV format), visualized with help of
the EDICTOR tool (http://edictor.digling.org)
Slide 22
Slide 22 text
New Gold Standards
Text file of the data (originally CSV format), visualized with help of
the EDICTOR tool (http://edictor.digling.org)
Language
Identifier
Slide 23
Slide 23 text
New Gold Standards
Text file of the data (originally CSV format), visualized with help of
the EDICTOR tool (http://edictor.digling.org)
Concept
Identifier
Slide 24
Slide 24 text
New Gold Standards
Text file of the data (originally CSV format), visualized with help of
the EDICTOR tool (http://edictor.digling.org)
Phonetic
Transcription
Segmented
Transcription
Slide 25
Slide 25 text
New Gold Standards
Text file of the data (originally CSV format), visualized with help of
the EDICTOR tool (http://edictor.digling.org)
Cognate
Identifier
Slide 26
Slide 26 text
New Gold Standards
Text file of the data (originally CSV format), visualized with help of
the EDICTOR tool (http://edictor.digling.org)
Cognate
Identifier
Slide 27
Slide 27 text
New Gold Standards
Text file of the data (originally CSV format), visualized with help of
the EDICTOR tool (http://edictor.digling.org)
Partial
Cognate ID
Slide 28
Slide 28 text
New Gold Standards
Text file of the data (originally CSV format), visualized with help of
the EDICTOR tool (http://edictor.digling.org)
Partial
Cognate ID
Slide 29
Slide 29 text
New Gold Standards
Text file of the data (originally CSV format), visualized with help of
the EDICTOR tool (http://edictor.digling.org)
Partial
Cognate ID
Slide 30
Slide 30 text
Methods
Slide 31
Slide 31 text
Workflow
1. compute pairwise sequence similarities between all
morphemes of all words in the same meaning slot in a
wordlist
2. create a similarity network in which nodes represent
morphemes and edges represent similarities between the
morphemes
3. use an algorithm for network partitioning to cluster the
nodes of the network into groups of cognate morphemes
Slide 32
Slide 32 text
Sequence Similarity (Step 1)
1. language-independent measures
a. scores depend on the strings that are compared only
b. any further information, like recurring similarities of
sounds (sound correspondences) are ignored
2. language-specific measures
a. previously identified regularities between languages
are used to create a scoring function
b. alignment algorithms use the scoring function to
evaluate word similarity
Slide 33
Slide 33 text
Sequence Similarity (Step 1)
1. language-independent measures
● SCA algorithm (List 2012a & 2014)
2. Language-specific measures
● LexStat algorithm (List 2012b & 2014)
All algorithms are implemented as part of the LingPy
software package (http://lingpy.org, List and Forkel 2016,
version 2.5).
Slide 34
Slide 34 text
Sequence Similarity Networks (Step 2)
● sequence similarity networks are tools for
exploratory data analysis (Méheust et al. 2016,
Corel et al. 2016)
● sequences (gene sequences in biology, words in
linguistics) represent nodes in a network
● weighted edges represent similarities between
the nodes
Slide 35
Slide 35 text
Sequence Similarity Networks (Step 2)
filtering edges drawn between sequences:
a. draw no edges between morphemes in the
same word
b. in each word pair, link each morpheme only to
one other morpheme (choose the most similar
pair)
c. only draw edges whose similarity exceeds a
certain threshold
Slide 36
Slide 36 text
Network Partitioning (Step 3)
1. flat version of UGPMA (Sokal and Michener 1958) which
terminates when a user-defined threshold is reached
2. Markov Clustering (van Dongen 2000) uses techniques
for matrix multiplication to inflate and expand the edge
weights in a given network
3. Infomap (Rosvall and Bergstrom 2008) was designed for
community detection in complex networks and uses
random walks to partition a network into communities
Slide 37
Slide 37 text
Workflow Example
Slide 38
Slide 38 text
Workflow Example
Slide 39
Slide 39 text
Workflow Example
Slide 40
Slide 40 text
Workflow Example
Slide 41
Slide 41 text
Results
Slide 42
Slide 42 text
Analyses and Evaluation
● all analyses require user-defined thresholds
● since our gold-standard data is too small to split it into test
and training set, we carried out an exhaustive evaluation
with a large range of thresholds varying between 0.05 and
0.95 in steps of 0.05
● B-Cubed scores (Bagga and Baldwin 1998) were used as
evaluation measure, since they have been shown to yield
sensible results (Hauer and Kondrak 2011)
Slide 43
Slide 43 text
Analyses and Evaluation
● we tested two classical methods for cognate detection
(SCA and LexStat) against their refined variants sensitive
for partial cognates (SCA-Partial, LexStat-Partial)
● since SCA and LexStat yield full cognate judgments, we
need to convert the partial (exact) cognate judgments to
full cognate accounts, using the criterion of full identity
(strict encoding as shown before)
● we tested also the accuracy of SCA-Partial and
LexStat-Partial on partial cognacy, but cannot compare
these scores with other algorithms
Slide 44
Slide 44 text
Implementation
The code was implemented in Python, as part of the
LingPy library (Version 2.5, List and Forkel (2016),
http://lingpy.org). The igraph software package
(Csárdi and Nepusz 2006) is needed to apply the
Infomap algorithm.
Slide 45
Slide 45 text
Results: General
Slide 46
Slide 46 text
Results: General
Slide 47
Slide 47 text
Results: SCA vs. LexStat
Slide 48
Slide 48 text
Results: Datasets
Slide 49
Slide 49 text
Discussion
Slide 50
Slide 50 text
Discussion
● our method is a pilot approach for the detection of
partial cognates in multilingual word lists
● further improvements are needed
● we should test on additional datasets (new language
families) and increase our data (testing and training)
● our approach can be easily adjusted to employ different
string similarity measures or partitioning algorithms: let’s
try and see whether alternative measures can improve
upon our current version
Slide 51
Slide 51 text
Code and data at:
https://github.com/lingpy/partial-cognate-detection
or
https://zenodo.org/record/51328?ln=en
Slide 52
Slide 52 text
Thanks for your attention!
Code and data at:
https://github.com/lingpy/partial-cognate-detection
or
https://zenodo.org/record/51328?ln=en