Tools & Resources
Python Libraries
LingPy (lingpy.org) Primary library for computational historical linguistics in Python. Provides IPA tokenization, phoneme feature extraction, sequence alignment (SCA algorithm), cognate detection (LexStat), and distance matrix computation.
pip install lingpyGensim (radimrehurek.com/gensim) Industry-standard library for Word2Vec, FastText, and GloVe embeddings. Handles large corpora efficiently.
conda install -c conda-forge gensimNetworkX (networkx.org) Graph data structures and algorithms for Python. Used throughout Chapter 11 for building and querying etymology graphs.
conda install -c conda-forge networkxscikit-learn (scikit-learn.org) Standard Python machine learning library. Used for cognate detection (Chapter 5), borrowing detection (Chapter 9), and all classification tasks.
conda install -c conda-forge scikit-learnHugging Face Transformers (huggingface.co/transformers) Library for pre-trained transformer models including FLAN-T5 for fine-tuning (Chapter 10).
pip install transformersNLTK (nltk.org) General-purpose NLP library with useful tokenizers and corpus readers.
conda install -c conda-forge nltkSciPy (scipy.org) Scientific computing library. Used for hierarchical clustering (UPGMA) and distance matrix operations.
conda install -c conda-forge scipyLinguistics Software
EDICTOR (digling.org/edictor) Web-based tool for creating, editing, and annotating etymological wordlists in CLDF format. The best tool for building gold-standard alignment datasets.
SplitsTree (splitstree.org) Desktop software for phylogenetic network visualization, including NeighborNet for reticulate evolution. Free for academic use.
BEAST2 (beast2.org) Bayesian phylogenetic inference software with time-calibrated tree reconstruction. Used in the major computational historical linguistics papers on Indo-European dating.
PRAAT (fon.hum.uva.nl/praat) Standard tool for acoustic phonetics: recording, spectrograms, formant analysis. Required for working with actual speech data rather than transcribed text.
Data Sources
CLLD — Cross-Linguistic Linked Data (clld.org) Hub for CLDF-format linguistic databases. Key datasets: - WALS (World Atlas of Language Structures): typological features of 2,600 languages - Glottolog: genealogical classification of all documented languages - Concepticon: standardized concept list linking Swadesh lists across studies
Etymonline (etymonline.com) The Online Etymology Dictionary. Free, well-curated, with entries for 50,000+ English words. The best free source for English etymology.
Wiktionary (wiktionary.org) Crowdsourced multilingual dictionary with etymological sections. Quality varies but coverage is unmatched. Parseable via the Wiktionary API or dump files.
COHA — Corpus of Historical American English (corpus.byu.edu/coha) 400 million words of American English from 1810–2009, balanced by decade. Primary resource for diachronic embedding studies. Free access with registration.
Google Ngrams (books.google.com/ngrams) Frequency data for words and phrases across Google Books (1500–2019). Useful for spotting when words gained or lost usage, not a substitute for a full corpus.
ASJP (asjp.clld.org) Automated Similarity Judgments Program. 40-item wordlists for 6,000+ languages in a consistent orthographic format. Useful for broad-coverage studies.
IELex (ielex.mpi.nl) Indo-European Lexical Cognacy Database. 208-item Swadesh lists for ~50 Indo-European languages with expert cognate judgments.
Reference Books
Ladefoged, P., & Johnson, K. (2014). A Course in Phonetics (7th ed.). Cengage. The standard phonetics textbook. Clear, well-illustrated, and available in most university libraries.
Campbell, L. (2013). Historical Linguistics: An Introduction (3rd ed.). MIT Press. Comprehensive, authoritative, and readable. The reference for the comparative method.
Fortson, B. W. (2010). Indo-European Language and Culture: An Introduction (2nd ed.). Wiley-Blackwell. Best single-volume reference for Indo-European specifically.
Haspelmath, M., & Tadmor, U. (2009). Loanwords in the World’s Languages. De Gruyter Mouton. Systematic cross-linguistic study of borrowing patterns.
Jurafsky, D., & Martin, J. H. (2023). Speech and Language Processing (3rd ed. draft). Available free at web.stanford.edu/~jurafsky/slp3/. The standard NLP textbook. Covers word embeddings, sequence models, and language processing at graduate level.
Key Papers by Chapter
Chapter 4 (Sequence Alignment) - Needleman & Wunsch (1970) — the original alignment algorithm - Kondrak (2000) — phonetic alignment specifically
Chapter 5 (Cognate Detection) - List (2012) — LexStat - Jäger, List & Sofroniev (2017) — SVM approach
Chapter 6 (Phylogenetics) - Saitou & Nei (1987) — Neighbor-Joining - Gray & Atkinson (2003) — Nature paper on Indo-European dating
Chapter 7 (Proto-reconstruction) - Ciobanu & Dinu (2018) — Ab Initio - Meloni et al. (2021) — Ab Antiquo (transformer approach)
Chapter 8 (Semantic Drift) - Hamilton, Leskovec & Jurafsky (2016) — diachronic embeddings
Chapter 9 (Borrowing) - Haspelmath & Tadmor (2009) — systematic borrowing survey
Chapter 10 (LLMs) - Brown et al. (2020) — GPT-3 few-shot learning - Chung et al. (2022) — FLAN-T5
Chapter 11 (Graphs) - Navigli & Ponzetto (2012) — BabelNet