Computational Historical Linguistics Research Articles

Grouping sounds into evolving units for the purpose of historical language comparison

Computer-assisted approaches to historical language comparison have made great progress during the past two decades. Scholars can now routinely use computational tools to annotate cognate sets, align words, and search for regularly recurring sound correspondences. However, computational approaches still suffer from a very rigid sequence model of the form part of the linguistic sign, in which words and morphemes are segmented into fixed sound units which cannot be modified. In order to bring the representation of sound sequences in computational historical linguistics closer to the research practice of scholars who apply the traditional comparative method, we introduce improved sound sequence representations in which individual sound segments can be grouped into evolving sound units in order to capture language-specific sound laws more efficiently. We illustrate the usefulness of this enhanced representation of sound sequences in concrete examples and complement it by providing a small software library that allows scholars to convert their data from forms segmented into sound units to forms segmented into evolving sound units and vice versa.

Open Problems in Computational Historical Linguistics.

Problems constitute the starting point of all scientific research. The essay reflects on the different kinds of problems that scientists address in their research and discusses a list of 10 problems for the field of computational historical linguistics, that was proposed throughout 2019 in a series of blog posts. In contrast to problems identified in different contexts, these problems were considered to be solvable, but no solution could be proposed back then. By discussing the problems in the light of developments that have been made in the field during the past five years, a modified list is proposed that takes new insights into account but also finds that the majority of the problems has not yet been solved.

Word prediction in computational historical linguistics

In this paper, we investigate how the prediction paradigm from machine learning and Natural Language Processing (NLP) can be put to use in computational historical linguistics. We propose word prediction as an intermediate task, where the forms of unseen words in some target language are predicted from the forms of the corresponding words in a source language. Word prediction allows us to develop algorithms for phylogenetic tree reconstruction, sound correspondence identification and cognate detection, in ways close to attested methods for linguistic reconstruction. We will discuss different factors, such as data representation and the choice of machine learning model, that have to be taken into account when applying prediction methods in historical linguistics. We present our own implementations and evaluate them on different tasks in historical linguistics.

Analyzing Gaussian distribution of semantic shifts in Lexical Semantic Change Models

In recent years, there has been a significant increase in interest in lexical semantic change detection. Many are the existing approaches, data used, and evaluation strategies to detect semantic shifts. The classification of change words against stable words requires thresholds to label the degree of semantic change. In this work, we compare state-of-the-art computational historical linguistics approaches to evaluate the efficacy of thresholds based on the Gaussian Distribution of semantic shifts. We present the results of an in-depth analysis conducted on both SemEval-2020 Task 1 Subtask 1 and DIACR-Ita tasks. Specifically, we compare Temporal Random Indexing, Temporal Referencing, Orthogonal Procrustes Alignment, Dynamic Word Embeddings and Temporal Word Embedding with a Compass. While results obtained with Gaussian thresholds achieve state-of-the-art performance in English, German, Swedish and Italian, they remain far from results obtained using the optimal threshold.

Model evaluation in computational historical linguistics

Abstract This is a reply to the comments by Hammarström et al. (This volume) and List (This volume) on the target article Computational Historical Linguistics (This volume). There I proposed several methodological principles for research in Computational Historical Linguistics pertaining to suitable techniques for model fitting and model evaluation. Hammarström et al. debate the usefulness of these principles, and List proposes a novel evaluation measure specifically aimed at the task of proto-form reconstruction. This reply will focus on the role of model evaluation in our field.

On computational historical linguistics in the 21st century

On computational historical linguistics in the 21st century

Computational historical linguistics

Abstract Computational approaches to historical linguistics have been proposed for half a century. Within the last decade, this line of research has received a major boost, owing both to the transfer of ideas and software from computational biology and to the release of several large electronic data resources suitable for systematic comparative work. In this article, some of the central research topics of this new wave of computational historical linguistics are introduced and discussed. These are automatic assessment of genetic relatedness, automatic cognate detection, phylogenetic inference and ancestral state reconstruction. They will be demonstrated by means of a case study of automatically reconstructing a Proto-Romance word list from lexical data of 50 modern Romance languages and dialects. The results illustrate both the strengths and the weaknesses of the current state of the art of automating the comparative method.

Global-scale phylogenetic linguistic inference from lexical resources

Automatic phylogenetic inference plays an increasingly important role in computational historical linguistics. Most pertinent work is currently based on expert cognate judgments. This limits the scope of this approach to a small number of well-studied language families. We used machine learning techniques to compile data suitable for phylogenetic inference from the ASJP database, a collection of almost 7,000 phonetically transcribed word lists over 40 concepts, covering two thirds of the extant world-wide linguistic diversity. First, we estimated Pointwise Mutual Information scores between sound classes using weighted sequence alignment and general-purpose optimization. From this we computed a dissimilarity matrix over all ASJP word lists. This matrix is suitable for distance-based phylogenetic inference. Second, we applied cognate clustering to the ASJP data, using supervised training of an SVM classifier on expert cognacy judgments. Third, we defined two types of binary characters, based on automatically inferred cognate classes and on sound-class occurrences. Several tests are reported demonstrating the suitability of these characters for character-based phylogenetic inference.

Sequence comparison in computational historical linguistics

This research was supported by the European Research Council Starting Grant ‘Computer-Assisted Language Comparison’ (Grant CALC 715618, J.M.L., T.T.) and the Australian Research Council’s Centre of Excellence for the Dynamics of Language (Australian National University, Grant CE140100041, S.J.G.). As part of the GlottoBank project (http://glottobank.org), this work was further supported by the Department of Linguistic and Cultural Evolution of the Max Planck Institute for the Science of Human History (Jena) and the Royal Society of New Zealand (Marsden Fund, Grant 13-UOA-121).

Using ancestral state reconstruction methods for onomasiological reconstruction in multilingual word lists

AbstractCurrent efforts in computational historical linguistics are predominantly concerned with phylogenetic inference. Methods for ancestral state reconstruction have only been applied sporadically. In contrast to phylogenetic algorithms, automatic reconstruction methods presuppose phylogenetic information in order to explain what has evolved when and where. Here we report a pilot study exploring how well automatic methods for ancestral state reconstruction perform in the task of onomasiological reconstruction in multilingual word lists, where algorithms are used to infer how the words evolved along a given phylogeny, and reconstruct which cognate classes were used to express a given meaning in the ancestral languages. Comparing three different methods, Maximum Parsimony, Minimal Lateral Networks, and Maximum Likelihood on three different test sets (Indo-European, Austronesian, Chinese) using binary and multi-state coding of the data as well as single and sampled phylogenies, we find that Maximum Likelihood largely outperforms the other methods. At the same time, however, the general performance was disappointingly low, ranging between 0.66 (Chinese) and 0.79 (Austronesian) for the F-Scores. A closer linguistic evaluation of the reconstructions proposed by the best method and the reconstructions given in the gold standards revealed that the majority of the cases where the algorithms failed can be attributed to problems of independent semantic shift (homoplasy), to morphological processes in lexical change, and to wrong reconstructions in the independently created test sets that we employed.

Compiling the Uralic Dataset for NorthEuraLex, a Lexicostatistical Database of Northern Eurasia

This paper presents a large comparative lexical database which covers about a thousand concepts across twenty Uralic languages. The dataset will be releasedas the first part of NorthEuraLex, a lexicostatistical database of Northern Eurasia which is being compiled within the EVOLAEMP project.The chief purpose of the lexical database is to serve as a basis of benchmarks for different tasks within computational historical linguistics, but it might also be valuable to researchers who work on the application of computational methods to open research questions within the language family.The paper describes and motivates the decisions taken concerning data collection methodology, also discussing some of the problems involved in compiling and unifying data from lexical resources in six different gloss languages.The dataset is already publicly available in various PDF formats for inspection and review, and is scheduled for release in machine-readable form in early 2015.

A Pipeline for Computational Historical Linguistics

AbstractThere are many parallels between historical linguistics and molecular phylogenetics. In this paper we describe an algorithmic pipeline that mimics, as closely as possible, the traditional workflow of language reconstruction known as the comparative method. The pipeline consists of suitably modified algorithms based on recent research in bioinformatics, which are adapted to the specifics of linguistic data. This approach can alleviate much of the laborious research needed to establish proof of historical relationships between languages. Equally important to our proposal is that each step in the workflow of the comparative method is implemented independently, so language specialists have the possibility to scrutinize intermediate results. We have used our pipeline to investigate two groups of languages, the Tsezic languages of the Caucasus and the Mataco-Guaicuruan languages of South America, based on the lexical data from the Intercontinental Dictionary Series (IDS). The results of these tests show that the current approach is a viable and useful extension to historical linguistic research.