Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change

William L. Hamilton, Jure Leskovec, Dan Jurafsky · ACL / arXiv · 2016 · digital-humanities · 10.18653/v1/P16-1141 · record hamilton2016-diachronic-embeddings
tag layer · index · concepts · authors · עברית

Where this record's text came from. faceted 2026-08 by reading the locally held text (pdftext); every evidence string verified as an exact substring of that text before merging. The PDF-to-text extraction for this paper stripped all inter-word spaces, so every verbatim quote is unspaced and retains the original line-break hyphens (e.g. 'method-ology'). Quotes were pulled programmatically from the file so they are exact substrings despite being unreadable. The queue records words=50 for this entry, which is an artefact of the same whitespace loss, not a short paper. Claim type is 'existence' rather than 'mechanism' because the paper explicitly declines to claim causation. FACETS WITHDRAWN: the text used was word spacing lost in extraction (mean token length 879); the quotes verified against that text but it is not this paper. Record left ungrounded rather than grounded in the wrong document. faceted 2026-08 by reading the l 2026-08-14 and 2026-08-28 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node. Update, 15 September 2026: EXCEPTION, measured with the merge gate's own predicate (Paper.locate): 5 quote(s) on this record are not found as one exact string in the current staged text - content_tags.statistics[2].evidence, content_tags.statistics[4].evidence, content_tags.statistics[5].evidence, content_tags.statistics[7].evidence, content_tags.variables[0].evidence. The sentence above does not hold for them as written. Where a row records why - the quote is grounded in another copy of the paper, joins two passages with an ellipsis, or differs from the staged text by extraction noise - that note stays on the row. Update, 16 September 2026: EXCEPTION TO THE DATED PASS ABOVE, on this record only: this record carries 1 composite quote field - a quote assembled from two or more passages joined by an ellipsis. A COMPOSITE IS NOT AN EXACT CONTIGUOUS SUBSTRING of the staged text and is deliberately not anchored: each of its parts is verified separately at the offsets in evidence composite spans, and a part occurring more than once carries span null rather than a guessed offset. So the 'every quote verified as an exact substring' clause of the dated pass above DOES NOT HOLD for those fields, and never did - the parts were verified, the whole was not. Nothing is deleted, re-grounded or withdrawn: this writes down an exception that was always true of composites and had not been recorded, so a reader was told more than the pass had checked. Update, 18 September 2026: the withdrawal above no longer holds - the staged text today is the ACL 2016 paper with ordinary spacing (mean token length 5.5), and this record is grounded in it: 130 of its 134 quotes are in the text, 123 anchored.

The quality of the text these quotes were cut from. diacritic-detached-from-its-letter (A NEW CLASS, AND NOT A LIGATURE FAULT): 1 words in a staged text of 36,685 characters carry a diacritic emitted as a SEPARATE SPACING CHARACTER AFTER the letter it belongs to, so 'Gaechter' is stored as 'Ga' + a spacing diaeresis + 'chter' and matches neither spelling. The em-dash ligature count on this record is ZERO and so is the '(cid:NNN)' count: this is a third kind of damage and is named rather than folded into either. THE QUOTES ON THIS RECORD ARE THE PAPER'S AND THE STAGED COPY IS THE DAMAGED ONE: 4 of its 133 live quotes are not exact substrings of this text, and NONE of them could be located in it even by aligning the quote's WORD SEQUENCE under this damage, so the defect recorded here is present on the record but does not by itself account for the miss. Not repaired in place: editing the staged text moves every offset after the edit and re-hashes every anchor on the record. Measured at 113aae60fefc3eb1, re-measured unchanged at 54b63482778ddf56.

3 quotes on this page break a word across a line. The PDF this text was extracted from hyphenated those words at the end of a printed line — adversar- ial, repre- sentations — and the extractor kept the hyphen and the space. The quotes keep them because a quote is reproduced exactly or it proves nothing: the break is the typesetter’s, not the author’s. A search of this page will not find the affected words.

4 quotes on this page were cut from a different copy of this article. This project holds two extractions of this paper: the plain text every other quote here is anchored in, and the publisher’s own HTML edition, which we are not licensed to republish. They are verbatim in the second and cannot be found in the first — not because the tagging is wrong, but because the extraction damaged the passage: a page number dropped into the middle of a number, a formula moved out of its sentence, a ligature where two letters belong. The record names the copy for each one. The quote is the paper’s; the extraction is not.

How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.

Other fields define these differently the same word, defined another way in another discipline
learning 7 fields · sample-size 5 fields · statistical-significance 2 fields · frequency 2 fields · linear regression 2 fields · semantic 2 fields · and 1 more →

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 47 concept tags on this paper, 44 are grounded in a quoted sentence. 38 carry the tagger's gloss of what the term means in this paper, which is not something the article can license.

word embedding semantic change diachronic analysis distributional semantics law of innovation law of conformity polysemy word frequency PPMI distributional methods co-occurrence relationships distributional hypothesis semantic similarity/distance cosine similarity/distance SVD embeddings low-dimensional approximations of the PPMI embeddings dimensionality reduction regularization SGNS ‘neural’ embeddings skip-gram with negative sampling incremental initialization Google N-Gram datasets corpus artifacts COHA corpus orthogonal Procrustes rotational alignment Pair-wise similarity time-series pairwise similarity shifts Spearman correlation semantic displacement cos-dist synchronic accuracy diachronic validity detecting known shifts discovering shifts from data linear mixed model random intercepts per word fixed effects per decade contextual diversity polysemousness empirical co-occurrence network clustering coefficient discourse function words controlling for frequency null model learning sociocultural conformity bias statistical laws of semantic change: the rate of change scales as an inverse power-law of word frequency (law of conformity) and rises with polysemy (law of innovation) semantic change word embeddings frequency polysemous diachronic historical corpora rate of semantic change Bayesian correlation Pearson hypothesis-testing test hypotheses statistical-significance regression linear regression sample-size sample sizes statistically significant variance corpus-analysis

Method, as described: computational-corpus-analysis

Legend

relation to other work	`claim_relations`	how this paper stands to another: agrees, contradicts, extends, qualifies
claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
control	`controls`	an experiment run to eliminate a rival explanation
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
phenomenon	`phenomenon`	the effect or regularity under study
sense	`senses`	a distinct use of a term, quoted where the paper fixes it
transfer	`transfers`	a method or concept carried in from another field
unrecordable relation	`unhoused_relations`	a relation the paper asserts that this vocabulary cannot express, with the reason

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://doi.org/10.18653/v1/P16-1141. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 4 · claim_type 1 · concept_edges 8 · concepts 44 · content_tags 11 · controls 1 · limitations 8 · mechanisms 1 · method 1 · phenomenon 1 · senses 18 · transfers 1 · unhoused_relations 7

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; 6 of 8 relations here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

facet	tag	field	conf.	whose words
claim_type	existence Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	semantic change Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	corpus-analysis Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: corpus-analysis	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: statistical laws of semantic change: the rate of change scales as an inverse power-law of word frequency (law of conformity) and rises with polysemy (law of innovation)	`mechanisms[0]`		the tagger's words
limitations	The paper's results are correlational; it explicitly declines to claim the causal mechanisms it speculates about. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the mechanistic story: WHILE OUR RESULTS CANNOT CONFIRM SUCH CAUSAL LINKS, THEY NONETHELESS HIGHLIGHT A NEW ROLE FOR FREQUENCY AND POLYSEMY - correlational by the authors' own statement	`limitations[0]`		the tagger's words
limitations	The polysemy proxy (local clustering coefficient in a PPMI co-occurrence network) is biased towards rating contextually diverse function words as highly polysemous. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: every polysemy score: the measure IS SLIGHTLY BIASED TOWARDS RATING CONTEXTUALLY DIVERSE DISCOURSE FUNCTION WORDS (E.G., ALSO) AS HIGHLY POLYSEMOUS	`limitations[1]`		the tagger's words
limitations	Polysemy has no agreed ground truth to validate the measure against. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any validation of a polysemy measure at all: MEASURING WORD POLYSEMY IS A DIFFICULT AND FRAUGHT TASK, AS EVEN 'GROUND TRUTH' DICTIONARIES DIFFER IN THE NUMBER OF SENSES THEY ASSIGN TO WORDS	`limitations[2]`		the tagger's words
limitations	The main corpora contain artifacts from shifting sampling biases over time. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: every result computed on that corpus: THE GOOGLE N-GRAM DATASETS ... CONTAIN MANY CORPUS ARTIFACTS DUE, E.G., TO SHIFTING SAMPLING BIASES OVER TIME	`limitations[3]`		the tagger's words
limitations	Part of the polysemy result (the negative curvature at high polysemy) is not robust across datasets or methods. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the polysemy curvature result specifically: IT VARIES ACROSS DATASETS AND WAS NOT PRESENT WITH SGNS, SO IT IS NOT AS ROBUST AS THE CLEAR LINEAR TREND	`limitations[4]`		the tagger's words
limitations	The paper's second law is stated in two logically different forms, two pages apart. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any citation of the law of innovation: the abstract states it as holding independent of frequency, while the introduction states it as holding after controlling for frequency and adds 'significantly', and the two are not the same claim	`limitations[5]`	1.0	the tagger's words
limitations	One of the three methods is stated to be prone to false discoveries. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any result computed with PPMI embeddings: the authors state	`limitations[6]`	1.0	the tagger's words
limitations	The choice between the two remaining methods is left unsettled by the paper's own benchmarks. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: any rate of semantic change quoted from this work: between SVD and SGNS the results are described as somewhat equivocal, with each performing best on two of the four tasks	`limitations[7]`	1.0	the tagger's words
transfers	word embeddings (word2vec) applied across time to quantify historical semantic change Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[0]`		the tagger's words
controls	word frequency, in the law of innovation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: the reading that polysemous words change faster only because they are rarer · outcome (stated by the tagger, no quotation): held	`controls[0]`	1.0	the tagger's words
concepts	semantic change Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: semantic change	`concepts[1]`		the paper's words
concepts	law of innovation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: law of innovation	`concepts[4]`		the paper's words
concepts	law of conformity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: law of conformity	`concepts[5]`		the paper's words
concepts	polysemy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: polysemy	`concepts[6]`		the paper's words
concepts	word frequency Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: word frequency	`concepts[7]`		the paper's words
concepts	PPMI Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: PPMI	`concepts[8]`		the paper's words
concepts	distributional methods Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: distributional methods	`concepts[9]`	0.95	the paper's words
concepts	co-occurrence relationships Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: co-occurrence relationships	`concepts[10]`	0.95	the paper's words
concepts	distributional hypothesis Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: distributional hypothesis	`concepts[11]`	0.95	the paper's words
concepts	semantic similarity/distance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: semantic similarity/distance	`concepts[12]`	0.95	the paper's words
concepts	cosine similarity/distance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: cosine similarity/distance	`concepts[13]`	0.95	the paper's words
concepts	SVD embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: SVD embeddings	`concepts[14]`	0.95	the paper's words
concepts	low-dimensional approximations of the PPMI embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: low-dimensional approximations of the PPMI embeddings	`concepts[15]`	0.95	the paper's words
concepts	dimensionality reduction Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: dimensionality reduction	`concepts[16]`	0.95	the paper's words
concepts	regularization Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: regularization	`concepts[17]`	0.95	the paper's words
concepts	SGNS ‘neural’ embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: SGNS ‘neural’ embeddings	`concepts[18]`	0.95	the paper's words
concepts	skip-gram with negative sampling Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: skip-gram with negative sampling	`concepts[19]`	0.95	the paper's words
concepts	incremental initialization Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: incremental initialization	`concepts[20]`	0.95	the paper's words
concepts	Google N-Gram datasets Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Google N-Gram datasets	`concepts[21]`	0.95	the paper's words
concepts	corpus artifacts Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: corpus artifacts	`concepts[22]`	0.95	the paper's words
concepts	COHA corpus Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: COHA corpus	`concepts[23]`	0.95	the paper's words
concepts	orthogonal Procrustes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: orthogonal Procrustes	`concepts[24]`	0.95	the paper's words
concepts	rotational alignment Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: rotational alignment	`concepts[25]`	0.95	the paper's words
concepts	Pair-wise similarity time-series Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Pair-wise similarity time-series	`concepts[26]`	0.95	the paper's words
concepts	pairwise similarity shifts Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: pairwise similarity shifts	`concepts[27]`	0.95	the paper's words
concepts	Spearman correlation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Spearman correlation	`concepts[28]`	0.95	the paper's words
concepts	semantic displacement Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: semantic displacement	`concepts[29]`	0.95	the paper's words
concepts	cos-dist Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: cos-dist	`concepts[30]`	0.95	the paper's words
concepts	synchronic accuracy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: synchronic accuracy	`concepts[31]`	0.95	the paper's words
concepts	diachronic validity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: diachronic validity	`concepts[32]`	0.95	the paper's words
concepts	detecting known shifts Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: detecting known shifts	`concepts[33]`	0.95	the paper's words
concepts	discovering shifts from data Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: discovering shifts from data	`concepts[34]`	0.95	the paper's words
concepts	linear mixed model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: linear mixed model	`concepts[35]`	0.95	the paper's words
concepts	random intercepts per word Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: random intercepts per word	`concepts[36]`	0.95	the paper's words
concepts	fixed effects per decade Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: fixed effects per decade	`concepts[37]`	0.95	the paper's words
concepts	contextual diversity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: contextual diversity	`concepts[38]`	0.95	the paper's words
concepts	polysemousness Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: polysemousness	`concepts[39]`	0.95	the paper's words
concepts	empirical co-occurrence network Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: empirical co-occurrence network	`concepts[40]`	0.95	the paper's words
concepts	clustering coefficient Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: clustering coefficient	`concepts[41]`	0.95	the paper's words
concepts	discourse function words Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: discourse function words	`concepts[42]`	0.95	the paper's words
concepts	controlling for frequency Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: controlling for frequency	`concepts[43]`	0.95	the paper's words
concepts	null model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: null model	`concepts[44]`	0.95	the paper's words
concepts	learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: learning	`concepts[45]`	0.9	the paper's words
concepts	sociocultural conformity bias Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: sociocultural conformity bias	`concepts[46]`	0.9	the paper's words
unhoused_relations	SGNS → skip-gram with negative sampling Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. SGNS abbreviates skip-gram with negative sampling; acronym-expansion is absent from the edge registry.	`unhoused_relations[0]`	0.95	the tagger's words
unhoused_relations	SVD → singular value decomposition Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. SVD abbreviates singular value decomposition; acronym-expansion is absent from the edge registry.	`unhoused_relations[1]`	0.95	the tagger's words
unhoused_relations	clustering coefficient → polysemousness Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. A lower clustering coefficient indicates higher polysemousness; inverse-association is absent from the edge registry.	`unhoused_relations[2]`	0.95	the tagger's words
unhoused_relations	learning → law of conformity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Learning errors are offered as a possible mechanism for the conformity law; hypothesized-mechanism-for is absent from the edge registry.	`unhoused_relations[3]`	0.9	the tagger's words
unhoused_relations	sociocultural conformity bias → law of conformity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Sociocultural conformity bias is offered as another possible mechanism; hypothesized-mechanism-for is absent from the edge registry.	`unhoused_relations[4]`	0.9	the tagger's words
unhoused_relations	rotational alignment → orthogonal Procrustes Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Orthogonal Procrustes is used to obtain rotational alignment; implemented-by is absent from the edge registry.	`unhoused_relations[5]`	0.95	the tagger's words
unhoused_relations	polysemy → contextual diversity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. Contextual diversity is used as a proxy for polysemy; proxy-for is absent from the edge registry.	`unhoused_relations[6]`	0.95	the tagger's words
senses	the law of innovation - TWO STATEMENTS, ONE NAME: the abstract has it holding 'independent of frequency' and the introduction 'after controlling for frequency', with 'significantly' added in the second; independence and a residual surviving adjustment are different claims, and the name that travels does not say which one is meant Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	1.0	the tagger's words
senses	a rate of semantic change - A NUMBER PRODUCED BY A CHOICE OF EMBEDDING: PPMI, SVD and SGNS are ranked against each other by the paper itself, PPMI is called clearly worse and prone to false discoveries from genre shifts, and between the other two the result is equivocal - so the construct's value depends on an instrument the paper declines to settle Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	1.0	the tagger's words
senses	a law - PROPOSED, NOT DERIVED: the authors say they PROPOSE two statistical laws relating frequency and polysemy to semantic change, fitted over six corpora, and the record's existing limitation already records that the analysis is correlational and the causal mechanisms are declined Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	1.0	the tagger's words
senses	Distributional hypothesis - word meaning represented implicitly by co-occurrence relationships Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[3]`	0.95	the tagger's words
senses	SVD embedding - low-dimensional regularized approximation to a PPMI representation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[4]`	0.95	the tagger's words
senses	SGNS embedding - word/context vectors trained with skip-gram negative sampling Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[5]`	0.95	the tagger's words
senses	Google N-Grams / COHA - very large artifact-prone sample versus smaller genre-balanced corpus Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[6]`	0.95	the tagger's words
senses	Orthogonal Procrustes - cosine-preserving rotational alignment of embeddings across periods Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[7]`	0.95	the tagger's words
senses	Pair-wise similarity series - changing cosine similarity summarized against time by Spearman correlation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[8]`	0.95	the tagger's words
senses	Semantic displacement - cosine distance between one word’s aligned representations at different times Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[9]`	0.95	the tagger's words
senses	Synchronic accuracy / diachronic validity - within-period similarity versus across-time change performance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[10]`	0.95	the tagger's words
senses	Detection / discovery benchmarks - recovery of known shifts versus expert judgment of inferred shifts Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[11]`	0.95	the tagger's words
senses	SVD / SGNS trade-off - sensitivity to subtle shifts versus robustness to corpus artifacts Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[12]`	0.95	the tagger's words
senses	Linear mixed model - word random intercepts and decade fixed effects for displacement regression Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[13]`	0.95	the tagger's words
senses	Contextual diversity - network-neighborhood proxy for polysemousness Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[14]`	0.95	the tagger's words
senses	Local clustering coefficient - inverse polysemy score from co-occurrence-neighbor connectivity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[15]`	0.95	the tagger's words
senses	Frequency control - necessary because polysemy proxy and word frequency are intrinsically correlated Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[16]`	0.95	the tagger's words
senses	Law of conformity null model - frequency-driven baseline for other semantic-change interactions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[17]`	0.95	the tagger's words
claim_relations	builds-on → prior distributional work on semantic change (Sagi et al., 2011; Wijaya and Yeniterzi, 2011; Gulordava and Baroni, 2011; Jatowt and Duh, 2014; Kulkarni et al., 2014; Xu and Kemp, 2015) and novel-sense detection (Lau et al., 2012; Mitra et al., 2014; Cook et al., 2014; Mitra et al., 2015; Frermann and Lapata, 2016) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[0]`		the tagger's words
claim_relations	extends → the same lines of quantitative / distributional work on semantic change Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[1]`		the tagger's words
claim_relations	contradicts → Wilkins (1993); Hopper and Traugott (2003), who argued that semantic change leads to polysemy Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[2]`		the tagger's words
claim_relations	replicates → Levy et al. (2015) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[3]`		the tagger's words
concept_edges	word frequency —causes→ semantic change Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. direction on the measure: reduces · strength of the relation: 0.8 also in: word frequency · semantic change	`concept_edges[0]`		the tagger's words
concept_edges	polysemy —causes→ semantic change Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. holds when: after controlling for word frequency · direction on the measure: increases · strength of the relation: 0.8 also in: polysemy · semantic change	`concept_edges[1]`		the tagger's words
concept_edges	distributional hypothesis —operationalised-as→ co-occurrence relationships Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The paper explicitly says the methods operationalize the hypothesis through co-occurrence. also in: distributional hypothesis · co-occurrence relationships	`concept_edges[2]`	0.95	the tagger's words
concept_edges	semantic similarity/distance —operationalised-as→ cosine similarity/distance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: Semantic similarity/distance is approximated by cosine similarity/distance. also in: semantic similarity/distance · cosine similarity/distance	`concept_edges[3]`	0.95	the tagger's words
concept_edges	SVD embeddings —is-a→ low-dimensional approximations of the PPMI embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The paper states SVD embeddings correspond to low-dimensional PPMI approximations. also in: SVD embeddings · low-dimensional approximations of the PPMI embeddings	`concept_edges[4]`	0.95	the tagger's words
concept_edges	pairwise similarity shifts —operationalised-as→ Spearman correlation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: Pairwise shifts are assessed with Spearman correlation against time. also in: pairwise similarity shifts · Spearman correlation	`concept_edges[5]`	0.95	the tagger's words
concept_edges	semantic change —operationalised-as→ cos-dist Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: Cosine distance between aligned representations is explicitly used as a semantic-change measure. also in: semantic change · cos-dist	`concept_edges[6]`	0.95	the tagger's words
concept_edges	SVD embeddings —contrasted-with→ SGNS ‘neural’ embeddings Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. the relation itself is separately evidenced · strength of the relation: 1 · note: The paper contrasts SVD sensitivity with SGNS robustness and their task strengths. Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span compares the methods 'SVD' and 'SGNS', not 'SVD embeddings' / 'SGNS ‘neural’ embeddings'. also in: SVD embeddings · SGNS ‘neural’ embeddings	`concept_edges[7]`	0.95	the tagger's words
content_tags	6 corpora / 4 languages / 2 centuries — empirical scope of the study Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[0]`		the tagger's words
content_tags	inverse power-law — how semantic-change rate scales with word frequency (law of conformity) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[1]`		the tagger's words
content_tags	Two quantitative laws of semantic change: conformity (change rate falls as an inverse power of word frequency) and innovation (more polysemous words change faster, independent of frequency). Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted.	`content_tags.findings[0]`		the tagger's words
content_tags	rate of semantic change Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: rate of semantic change	`content_tags.variables[1]`		the tagger's words
content_tags	law of conformity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: law of conformity	`content_tags.definitions[0]`		the tagger's words
content_tags	law of innovation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: law of innovation	`content_tags.definitions[1]`		the tagger's words
content_tags	Bayesian Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. also in: Bayesian	`content_tags.statistics[0]`		the tagger's words
content_tags	correlation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. also in: correlation	`content_tags.statistics[1]`		the tagger's words
content_tags	hypothesis-testing Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: hypothesis-testing	`content_tags.statistics[2]`		the tagger's words
content_tags	statistical-significance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: statistical-significance	`content_tags.statistics[3]`		the tagger's words
content_tags	statistical-significance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: statistical-significance	`content_tags.statistics[6]`		the tagger's words

Interpretive choices

Tags that could not be placed in the text:

content_tags.variables[0] — quotation withheld — the page has already reproduced as much of this paper as the rights budget allows
this quote's status: quote-not-in-current-staged-text · about this quote: marked quote-not-in-current-staged-text - today's merge gate would REFUSE this quote: Paper.locate() does not find it in the current staged text. · NOT MACHINE-VOUCHED: not-in-our-copy - The quote is in NEITHER copy we hold - not in the text we tag against and not in the page we fetched ('fulltext.html') - checked with ligatures, hyphens, spacing and punctuation set aside. This body carries 5 detached diacritics. We do not know what it was taken from, and no class is claimed for it.
content_tags.statistics[4] — quotation withheld — the page has already reproduced as much of this paper as the rights budget allows
NOT MACHINE-VOUCHED: not-in-our-copy - The quote is in the original web page we fetched for this paper, but not in the text we tag against, which was extracted differently. Checked with ligatures, hyphens, spacing and punctuation set aside.
content_tags.statistics[5] — quotation withheld — the page has already reproduced as much of this paper as the rights budget allows
NOT MACHINE-VOUCHED: not-in-our-copy - The quote is in the original web page we fetched for this paper, but not in the text we tag against, which was extracted differently. Checked with ligatures, hyphens, spacing and punctuation set aside.
content_tags.statistics[7] — quotation withheld — the page has already reproduced as much of this paper as the rights budget allows
NOT MACHINE-VOUCHED: not-in-our-copy - The quote is in the original web page we fetched for this paper, but not in the text we tag against, which was extracted differently. Checked with ligatures, hyphens, spacing and punctuation set aside.

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.