We probe the layers in multilingual BERT (mBERT) for phylogenetic and geographic language signals across 100 languages and compute language distances based on the mBERT representations.We 1) employ the language distances to infer and evaluate language trees, finding that they are close to the reference family tree in terms of quartet tree distance, 2) perform distance matrix regression analysis, finding that the language distances can be best explained by phylogenetic and worst by structural factors and 3) present a novel measure for measuring diachronic meaning stability (based on cross-lingual representation variability) which correlates significantly with published ranked lists based on linguistic approaches.Our results contribute to the nascent field of typological interpretability of cross-lingual text representations.

This paper seeks to uncover patterns of sound change across Indo-Aryan languages using an LSTM encoder-decoder architecture.We augment our models with embeddings representing language ID, part of speech, and other features such as word embeddings.We find that a highly augmented model shows highest accuracy in predicting held-out forms, and investigate other properties of interest learned by our models' representations.We outline extensions to this architecture that can better capture variation in Indo-Aryan sound change.

We present a fully automated workflow for phylogenetic reconstruction on large datasets, consisting of two novel methods, one for fast detection of cognates and one for fast Bayesian phylogenetic inference.Our results show that the methods take less than a few minutes to process language families that have so far required large amounts of time and computational power.Moreover, the cognates and the trees inferred from the method are quite close, both to gold standard cognate judgments and to expert language family trees.Given its speed and ease of application, our framework is specifically useful for the exploration of very large datasets in historical linguistics.

Bayesian linguistic phylogenies are standardly based on cognate matrices for words referring to a fix set of meanings—typically around 100-200. To this day there has not been any empirical investigation into which datasize is optimal. Here we determine, across a set of language families, the optimal number of meanings required for the best performance in Bayesian phylogenetic inference. We rank meanings by stability, infer phylogenetic trees using first the most stable meaning, then the two most stable meanings, and so on, computing the quartet distance of the resulting tree to the tree proposed by language family experts at each step of datasize increase. When a gold standard tree is not available we propose to instead compute the quartet distance between the tree based on the n-most stable meaning and the one based on the n + 1-most stable meanings, increasing n from 1 to N − 1, where N is the total number of meanings. The assumption here is that the value of n for which the quartet distance begins to stabilize is also the value at which the quality of the tree ceases to improve. We show that this assumption is borne out. The results of the two methods vary across families, and the optimal number of meanings appears to correlate with the number of languages under consideration.

We present and evaluate two similarity dependent Chinese Restaurant Process (sd-CRP) algorithms at the task of automated cognate detection.The sd-CRP clustering algorithms do not require any predefined threshold for detecting cognate sets in a multilingual word list.We evaluate the performance of the algorithms on six language families (more than 750 languages) and find that both the sd-CRP variants performs as well as InfoMap and better than UPGMA at the task of inferring cognate clusters.The algorithms presented in this paper are family agnostic and can be applied to any linguistically under-studied language family.

In this paper, we present phoneme level Siamese convolutional networks for the task of pair-wise cognate identification. We represent a word as a two-dimensional matrix and employ a siamese convolutional network for learning deep representations. We present siamese architectures that jointly learn phoneme level feature representations and language relatedness from raw words for cognate identification. Compared to previous works, we train and test on larger and realistic datasets; and, show that siamese architectures consistently perform better than traditional linear classifier approach.

In this paper, we describe the problem of cognate identification in NLP.We introduce the idea of gap-weighted subsequences for discriminating cognates from non-cognates.We also propose a scheme to integrate phonetic features into the feature vectors for cognate identification.We show that subsequence based features perform better than state-ofthe-art classifier for the purpose of cognate identification.The contribution of this paper is the use of subsequence features for cognate identification.