Are Automatic Methods for Cognate Detection Good Enough for Phylogenetic Reconstruction in Historical Linguistics?

Rama, Taraka; List, Johann‐Mattis; Wahle, Johannes; Jäger, Gerhard

doi:10.48550/arxiv.1804.05416

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An alternative to LexStat is the OnlinePMI method published by Rama et al (2017). OnlinePMI performed better than LexStat in identifying cognate classes (Rama et al, 2017), but it gave worse results when reconstructing trees using Bayesian phylogenetics on the bases of these classes (Rama et al, 2018).1 Compared to LexStat, the OnlinePMI method is better able to handle data with lower numbers of shared concepts. This comes at the cost of a significant random component, making it harder to optimize OnlinePMI for a particular application.…”

Section: 2mentioning

confidence: 99%

“…On the methodological side, recent years have seen a significant improvement of computational tools, practices, models, and algorithms for inferring language histories from word lists. For example, there are now new methods for automatic cognate detection using state-of-the-art pairwise phonetic alignment algorithms (Jäger et al, 2017;List, 2012a;List et al, 2017;List, 2012b;List et al, 2018b) that reach nearly 90% accuracy (B-cubed F-score) in determining the cognate sets to be used in phylogenetic analyses (Rama et al, 2018). Bayesian phylogenetic inference research has empirically shown which models are useful for lexical data Language Dynamics and Change (2022) 1-53 | 10.1163/22105832-bja10019 (Chang et al, 2015;Kolipakam et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The dialect chain of the Timor-Alor-Pantar language family

Kaiping

Klamer

2022

Lang. Dyn. Change

View full text Add to dashboard Cite

This paper refines the subgroupings of the Timor-Alor-Pantar (TAP) family of Papuan languages, using a systematic Bayesian phylogenetics study. While recent work indicates that the TAP family comprises a Timor (T) branch and an Alor-Pantar (AP) branch (Holton et al., 2012; Schapper et al., 2017), the internal structure of the AP branch has proven to be a challenging issue, and earlier studies leave large gaps in our understanding. Our Bayesian inference study is based on an extensive set of TAP lexical data from the online LexiRumah database (Kaiping et al., 2019b; Kaiping and Klamer, 2018). Systematically comparing different analytical models and tying them back to the evidence in terms of historical linguistics, we arrive at a subgrouping structure of the TAP family that is based on features of the phylogenies shared across the different analyses. Our TAP tree differs from all earlier proposals by inferring the East Alor subgroup as an early split-off from all other AP languages, instead of the most deeply embedded subgroup inside that branch. The evidences suggests that dialect cluster effects played a major role in the formation of today’s Timor-Alor-Pantar languages.

show abstract

Section: 2mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

The dialect chain of the Timor-Alor-Pantar language family

Kaiping

Klamer

2022

Lang. Dyn. Change

View full text Add to dashboard Cite

show abstract

“…Indian language pairs borrow a large number of cognates and false friends due to this shared ancestry. Knowing and utilising these cognates/false friends can help improve the performance of computational phylogenetics (Rama et al, 2018) as well as cross-lingual 2 Released Data: Github Link information retrieval (Meng et al, 2001) in the Indian setting, thus encouraging us to investigate this problem for this linguistic area 3 . Some other applications of cognate detection in NLP have been sentence alignment (Simard et al, 1993;Melamed, 1999), inducing translation lexicons (Mann and Yarowsky, 2001;Tufis, 2002), improving statistical machine translation models (Al-Onaizan et al, 1999), and identification of confusable drug names (Kondrak and Dorr, 2004).…”

Section: Introductionmentioning

confidence: 99%

Challenge Dataset of Cognates and False Friend Pairs from Indian Languages

Kanojia¹,

Bhattacharyya²,

Kulkarni³

et al. 2021

Preprint

View full text Add to dashboard Cite

Cognates are present in multiple variants of the same text across different languages (e.g., "hund" in German and "hound" in English language mean "dog"). They pose a challenge to various Natural Language Processing (NLP) applications such as Machine Translation, Cross-lingual Sense Disambiguation, Computational Phylogenetics, and Information Retrieval. A possible solution to address this challenge is to identify cognates across language pairs. In this paper, we describe the creation of two cognate datasets for twelve Indian languages, namely Sanskrit, Hindi, Assamese, Oriya, Kannada, Gujarati, Tamil, Telugu, Punjabi, Bengali, Marathi, and Malayalam. We digitize the cognate data from an Indian language cognate dictionary and utilize linked Indian language Wordnets to generate cognate sets. Additionally, we use the Wordnet data to create a False Friends' dataset for eleven language pairs. We also evaluate the efficacy of our dataset using previously available baseline cognate detection approaches. We also perform a manual evaluation with the help of lexicographers and release the curated gold-standard dataset with this paper.

show abstract

“…In numerous cases, these words also are morphologically altered as per the Indian language morphological rules to generate new variants of existing words. Detection of such variants or 'Cognates' across languages helps Cross-lingual Information Retrieval (CLIR) (Makin et al, 2008;Meng et al, 2001), Machine Translation (MT) (Kondrak, 2005;Kondrak et al, 2003;Al-Onaizan et al, 1999), and Computational Phylogenetics (Rama et al, 2018). Cognates are etymologically related words across two languages (Crystal, 2011).…”

Section: Introductionmentioning

confidence: 99%

Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages

Kanojia

Dabre

Dewangan

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

View full text Add to dashboard Cite

Cognates are variants of the same lexical form across different languages; for example "fonema" in Spanish and "phoneme" in English are cognates, both of which mean "a unit of sound". The task of automatic detection of cognates among any two languages can help downstream NLP tasks such as Cross-lingual Information Retrieval, Computational Phylogenetics, and Machine Translation. In this paper, we demonstrate the use of cross-lingual word embeddings for detecting cognates among fourteen Indian Languages. Our approach introduces the use of context from a knowledge graph to generate improved feature representations for cognate detection. We then evaluate the impact of our cognate detection mechanism on neural machine translation (NMT), as a downstream task. We evaluate our methods to detect cognates on a challenging dataset of twelve Indian languages, namely, Sanskrit, Hindi, Assamese, Oriya, Kannada, Gujarati, Tamil, Telugu, Punjabi, Bengali, Marathi, and Malayalam. Additionally, we create evaluation datasets for two more Indian languages, Konkani and Nepali 1 . We observe an improvement of up to 18% points, in terms of F-score, for cognate detection. Furthermore, we observe that cognates extracted using our method help improve NMT quality by up to 2.76 BLEU. We also release 2 our code, newly constructed datasets and cross-lingual models publicly.

show abstract

Are Automatic Methods for Cognate Detection Good Enough for Phylogenetic Reconstruction in Historical Linguistics?

Cited by 3 publications

References 0 publications

The dialect chain of the Timor-Alor-Pantar language family

The dialect chain of the Timor-Alor-Pantar language family

Challenge Dataset of Cognates and False Friend Pairs from Indian Languages

Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages

Contact Info

Product

Resources

About