Semantic Tagging with the Historical Thesaurus of English

Semantic Tagging with the Historical Thesaurus of English Marc Alexander
and Fraser Dallachy University of Glasgow – Historical Lexicography in a Digital Age Copenhagen, November 2022

For dealing historically with the phonological and grammatical systems of
English, we have inherited from our predecessors a legacy which can and should be used fruitfully [...] In the field of lexis – apart from alphabetical dictionaries – we are comparatively poorly equipped, and the way before us is a long one. Samuels ( 196 5 : 40 )

Historical Thesaurus of English ht.ac.uk

Put at its simplest, its purpose is to provide a
detailed record of the English vocabulary from the earliest times to the present, with sufficient accompanying information that, for any given period in the past, the user should be able to ascertain the exact state of the vocabulary (i.e. the ‘lexical system’) which existed at that time. Alexander and Kay ( 2022 ) ‘Why a Historical Thesaurus’ https://ht.ac.uk/why/

[…] the primacy of meaning, and the analysis of meaning,
as the essential tool and criterion for the study of any language [and] nothing less than classification, by meaning, of the whole if one is to begin to understand the parts. Alexander and Kay ( 2022 ) ‘Why a Historical Thesaurus’ https://ht.ac.uk/why/

[…] a magnificent achievement of quite extraordinary value. It is
perhaps the single most significant tool ever devised for investigating semantic, social and intellectual history. Randolph Quirk ( 2009 )

804,830 235,249 Entries (Words) Categories (Concepts) 3.4 Words for each
concept (on average)

Michael Samuels

Christian J. Kay

First edition OED Third Edition Modern Dictionaries Old English Dictionaries
OED Additions Series   ( 19 93 - 1 9 9 7 ) OED Supplements ( 19 33 , 1 98 6 ) Oxford English Dictionary ( 1884 - 19 28 ) Second supplement available after HT started Additional OED material before the (in-progress) third edition In progress since 200 0 (When the OED wasn’t being updated, the Concise Oxford and Chambers) Bosworth-Toller ( 1882 - 19 7 2 ) Clark Hall ( 1 96 0 ) Dictionary of Old English ( 19 8 6 –, in progress)

Semantic Tagging

6 2 % of English word forms   refer to
more than one meaning Of the 79 3 , 7 42 entries in the Historical Thesaurus   of English there are 3 7 0 , 0 1 1 non-Old-English   word forms, of which: 6 7 have more than 1 00 possible meanings 4 6 4 have more than 5 0 possible meanings 2 , 58 0 have more than 2 0 possible meanings 7 , 55 4 have more than 10 possible meanings 1 11 , 127 have more than 1 possible meaning 2 5 8 , 8 83 have just 1 possible meaning

strike   27 6 meanings including phrases, 181 meanings on
own

0 1 . 03 . 03 . 04 . 1
4 | 0 2 vt   Make healthy :: Practise physiotherapy :: rub/stroke with hands strike ( 1 400 + 161 1 + 1 886 dial.) 0 1 . 02 . 04 . 04 . 0 3 | 07 vt   Come by death :: Kill by specific method :: by poisoning strike ( 159 2 – 1 6 21 ) 0 1 . 06 . 10 . 08 | 01 vi   Plant :: Be a root :: grow (as root) strike ( 1682 –) 0 1 . 05 . 17 . 05 . 02 | 04 n   Animals :: Suborder Ophidia (snakes) :: act of darting at prey strike ( 1 879 –) 0 1 . 1 0 . 03 . 03 . 02 . 03 | 1 2 . 0 6 vt   Burn/consume by fire :: kindle/set alight :: produce (fire/spark) by striking strike (c 14 5 0 – also fig.) 0 1 . 1 0 . 09 . 03 . 03 | 01 vi   Dye :: sink in strike (c 1790 –) 0 1 . 1 3 . 06 . 0 1 | 04 vt   Time :: Clock :: strike strike ( 1 417 –) 0 3 . 1 1 . 04 . 03 | 0 5 vi   Carry on an occupation/work :: Participate in labour relations :: strike strike ( 17 68 –)

Semantic Annotation System VARD CLAWS HT sense tagger USAS NLP
lexicon resources USAS [HT-related resources] Historical Thesaurus; Higher-level HT categories; Linked HT categories; Highly polysemous words; Z-category words; Polyseme density list; Input raw text Annotated text HT sense disambiguator Spelling training model

•Pre-process text using VARD, CLAWS and USAS. •Currently: context-distance method
for disambiguation • Filter by POS. • For each candidate category, extract all possible parent categories and collect headings of them, including current heading. • Words in the headings form a feature set HWi = {h1 , h2 , …, hm }. • Collect up to five content words from each side of the key word/MWE. • Together with the target word/MWE wt , they form a context feature set CW={wt , w1 , w2 , …, wn }. • Measure Jaccard Distance between CW and each HWi , and select the candidate categories (up to three) that have close distances to the context. Current Methods

0 1 . 02 . 02 . 0 3 .
05 . 02 . 0 7 | 0 4 n Health and disease Medicinal potion/draught :: medicated wine wine 165 2 – 0 1 . 02 . 05 . 13 . 09 . 0 2 . 0 2 | 0 6 . 14 n Plants Tree/plant producing edible berries :: grape-vine wine 13 40 / 7 0 – 16 3 2 0 1 . 02 . 09 . 0 2 . 02 . 02 n Food and drink Wine wine oe– 0 1 . 02 . 09 . 0 2 . 02 . 02 . 12 n Food and drink Non-grape and home-made wines wine 13 98 – 0 1 . 02 . 09 . 0 2 . 14 . 01 | 0 8 vt Make wine store wine/stock cellar wine c 1 6 4 5 0 1 . 02 . 09 . 0 2 . 19 | 05 vt Provide/serve (with) drink supply with specific drink wine 1862 – 0 1 . 02 . 09 . 0 2 . 2 0 . 01 | 18 n Food and drink Drinking vessel :: glass wine 1848 – 0 1 . 02 . 09 . 0 2 . 2 1 | 10 . 09 vi Drink drink intoxicating liquor :: drink wine wine (and dine) 1829 – 0 1 . 04 . 09 . 07 . 03 | 0 2 . 02 n Colour Red/redness :: shades of red :: deep red /crimson wine 1895 – 0 1 . 04 . 09 . 07 . 03 | 0 7 aj Pertaining to colour Red :: deep red/crimson wine 1950 – 0 1 . 05 . 05 . 12 . 01 . 0 3 . 02 | 02 . 03 n Action/operation Patronage :: patron :: as lord/protector wine oe 0 1 . 05 . 05 . 15 . 01 . 05 | 1 7 . 0 6 . 03 n Action/operation Care/protection :: protector :: one who looks after a lord wine oe 0 2 . 02 . 22 . 1 2 | 01 n Love One who loves/a lover :: male lover wine oe 0 2 . 02 . 22 . 1 5 | 1 4 n Love Friendliness :: friend wine oe– 1 481 0 2 . 02 . 22 . 1 5 | 1 4 . 19 n Love Friendliness :: friend :: friendly/gracious lord wine oe 0 3 . 0 4 . 0 9 . 02 . 01 . 02 . 0 2 | 09 n Being subject to authority Attendant :: confidential servant/companion wine oe 0 3 . 0 7 . 0 5 . 15 . 07 . 02 n Artefacts Wine wine oe– 0 3 . 11 . 02 . 0 5 . 01 | 1 1 n Social event Party :: drinking-party wine 185 7 – Disambiguation

Disambiguation Semantic Context Distance 0 1 . 02 . 02
. 0 3 . 05 . 02 . 0 7 | 0 4 n Health and disease Medicinal potion/draught :: medicated wine wine 165 2 – 0 1 . 02 . 05 . 13 . 09 . 0 2 . 0 2 | 0 6 . 14 n Plants Tree/plant producing edible berries :: grape-vine wine 13 40 / 7 0 – 16 3 2 0 1 . 02 . 09 . 0 2 . 02 . 02 n Food and drink Wine wine oe– 0 1 . 02 . 09 . 0 2 . 02 . 02 . 12 n Food and drink Non-grape and home-made wines wine 13 98 – 0 1 . 02 . 09 . 0 2 . 14 . 01 | 0 8 vt Make wine store wine/stock cellar wine c 1 6 4 5 0 1 . 02 . 09 . 0 2 . 19 | 05 vt Provide/serve (with) drink supply with specific drink wine 1862 – 0 1 . 02 . 09 . 0 2 . 2 0 . 01 | 18 n Food and drink Drinking vessel :: glass wine 1848 – 0 1 . 02 . 09 . 0 2 . 2 1 | 10 . 09 vi Drink drink intoxicating liquor :: drink wine wine (and dine) 1829 – 0 1 . 04 . 09 . 07 . 03 | 0 2 . 02 n Colour Red/redness :: shades of red :: deep red /crimson wine 1895 – 0 1 . 04 . 09 . 07 . 03 | 0 7 aj Pertaining to colour Red :: deep red/crimson wine 1950 – 0 1 . 05 . 05 . 12 . 01 . 0 3 . 02 | 02 . 03 n Action/operation Patronage :: patron :: as lord/protector wine oe 0 1 . 05 . 05 . 15 . 01 . 05 | 1 7 . 0 6 . 03 n Action/operation Care/protection :: protector :: one who looks after a lord wine oe 0 2 . 02 . 22 . 1 2 | 01 n Love One who loves/a lover :: male lover wine oe 0 2 . 02 . 22 . 1 5 | 1 4 n Love Friendliness :: friend wine oe– 1 481 0 2 . 02 . 22 . 1 5 | 1 4 . 19 n Love Friendliness :: friend :: friendly/gracious lord wine oe 0 3 . 0 4 . 0 9 . 02 . 01 . 02 . 0 2 | 09 n Being subject to authority Attendant :: confidential servant/companion wine oe 0 3 . 0 7 . 0 5 . 15 . 07 . 02 n Artefacts Wine wine oe– 0 3 . 11 . 02 . 0 5 . 01 | 1 1 n Social event Party :: drinking-party wine 185 7 –

Disambiguation Semantic Context Distance 0 1 . 02 . 02
. 0 3 . 05 . 02 . 0 7 | 0 4 n Health and disease Medicinal potion/draught :: medicated wine wine 165 2 – 0 1 . 02 . 05 . 13 . 09 . 0 2 . 0 2 | 0 6 . 14 n Plants Tree/plant producing edible berries :: grape-vine wine 13 40 / 7 0 – 16 3 2 0 1 . 02 . 09 . 0 2 . 02 . 02 n Food and drink Wine wine oe– 0 1 . 02 . 09 . 0 2 . 02 . 02 . 12 n Food and drink Non-grape and home-made wines wine 13 98 – 0 1 . 02 . 09 . 0 2 . 14 . 01 | 0 8 vt Make wine store wine/stock cellar wine c 1 6 4 5 0 1 . 02 . 09 . 0 2 . 19 | 05 vt Provide/serve (with) drink supply with specific drink wine 1862 – 0 1 . 02 . 09 . 0 2 . 2 0 . 01 | 18 n Food and drink Drinking vessel :: glass wine 1848 – 0 1 . 02 . 09 . 0 2 . 2 1 | 10 . 09 vi Drink drink intoxicating liquor :: drink wine wine (and dine) 1829 – 0 1 . 04 . 09 . 07 . 03 | 0 2 . 02 n Colour Red/redness :: shades of red :: deep red /crimson wine 1895 – 0 1 . 04 . 09 . 07 . 03 | 0 7 aj Pertaining to colour Red :: deep red/crimson wine 1950 – 0 1 . 05 . 05 . 12 . 01 . 0 3 . 02 | 02 . 03 n Action/operation Patronage :: patron :: as lord/protector wine oe 0 1 . 05 . 05 . 15 . 01 . 05 | 1 7 . 0 6 . 03 n Action/operation Care/protection :: protector :: one who looks after a lord wine oe 0 2 . 02 . 22 . 1 2 | 01 n Love One who loves/a lover :: male lover wine oe 0 2 . 02 . 22 . 1 5 | 1 4 n Love Friendliness :: friend wine oe– 1 481 0 2 . 02 . 22 . 1 5 | 1 4 . 19 n Love Friendliness :: friend :: friendly/gracious lord wine oe 0 3 . 0 4 . 0 9 . 02 . 01 . 02 . 0 2 | 09 n Being subject to authority Attendant :: confidential servant/companion wine oe 0 3 . 0 7 . 0 5 . 15 . 07 . 02 n Artefacts Wine wine oe– 0 3 . 11 . 02 . 0 5 . 01 | 1 1 n Social event Party :: drinking-party wine 185 7 – 01 . 02 . 09 . 0 2 . 02 . 02 01 . 04 . 09 . 0 7 . 0 3 | 02 . 02 02 . 02 . 2 2 . 1 5 | 14 03 . 11 . 02 . 0 5 . 01 | 1 1

Disambiguation Time Filtering 0 1 . 02 . 02 .
0 3 . 05 . 02 . 0 7 | 0 4 n Health and disease Medicinal potion/draught :: medicated wine wine 165 2 – 0 1 . 02 . 05 . 13 . 09 . 0 2 . 0 2 | 0 6 . 14 n Plants Tree/plant producing edible berries :: grape-vine wine 13 40 / 7 0 – 16 3 2 0 1 . 02 . 09 . 0 2 . 02 . 02 n Food and drink Wine wine oe– 0 1 . 02 . 09 . 0 2 . 02 . 02 . 12 n Food and drink Non-grape and home-made wines wine 13 98 – 0 1 . 02 . 09 . 0 2 . 14 . 01 | 0 8 vt Make wine store wine/stock cellar wine c 1 6 4 5 0 1 . 02 . 09 . 0 2 . 19 | 05 vt Provide/serve (with) drink supply with specific drink wine 1862 – 0 1 . 02 . 09 . 0 2 . 2 0 . 01 | 18 n Food and drink Drinking vessel :: glass wine 1848 – 0 1 . 02 . 09 . 0 2 . 2 1 | 10 . 09 vi Drink drink intoxicating liquor :: drink wine wine (and dine) 1829 – 0 1 . 04 . 09 . 07 . 03 | 0 2 . 02 n Colour Red/redness :: shades of red :: deep red /crimson wine 1895 – 0 1 . 04 . 09 . 07 . 03 | 0 7 aj Pertaining to colour Red :: deep red/crimson wine 1950 – 0 1 . 05 . 05 . 12 . 01 . 0 3 . 02 | 02 . 03 n Action/operation Patronage :: patron :: as lord/protector wine oe 0 1 . 05 . 05 . 15 . 01 . 05 | 1 7 . 0 6 . 03 n Action/operation Care/protection :: protector :: one who looks after a lord wine oe 0 2 . 02 . 22 . 1 2 | 01 n Love One who loves/a lover :: male lover wine oe 0 2 . 02 . 22 . 1 5 | 1 4 n Love Friendliness :: friend wine oe– 1 481 0 2 . 02 . 22 . 1 5 | 1 4 . 19 n Love Friendliness :: friend :: friendly/gracious lord wine oe 0 3 . 0 4 . 0 9 . 02 . 01 . 02 . 0 2 | 09 n Being subject to authority Attendant :: confidential servant/companion wine oe 0 3 . 0 7 . 0 5 . 15 . 07 . 02 n Artefacts Wine wine oe– 0 3 . 11 . 02 . 0 5 . 01 | 1 1 n Social event Party :: drinking-party wine 185 7 –

Disambiguation Time Filtering (Present Day) 0 1 . 02 .
02 . 0 3 . 05 . 02 . 0 7 | 0 4 n Health and disease Medicinal potion/draught :: medicated wine wine 165 2 – 0 1 . 02 . 05 . 13 . 09 . 0 2 . 0 2 | 0 6 . 14 n Plants Tree/plant producing edible berries :: grape-vine wine 13 40 / 7 0 – 16 3 2 0 1 . 02 . 09 . 0 2 . 02 . 02 n Food and drink Wine wine oe– 0 1 . 02 . 09 . 0 2 . 02 . 02 . 12 n Food and drink Non-grape and home-made wines wine 13 98 – 0 1 . 02 . 09 . 0 2 . 14 . 01 | 0 8 vt Make wine store wine/stock cellar wine c 1 6 4 5 0 1 . 02 . 09 . 0 2 . 19 | 05 vt Provide/serve (with) drink supply with specific drink wine 1862 – 0 1 . 02 . 09 . 0 2 . 2 0 . 01 | 18 n Food and drink Drinking vessel :: glass wine 1848 – 0 1 . 02 . 09 . 0 2 . 2 1 | 10 . 09 vi Drink drink intoxicating liquor :: drink wine wine (and dine) 1829 – 0 1 . 04 . 09 . 07 . 03 | 0 2 . 02 n Colour Red/redness :: shades of red :: deep red /crimson wine 1895 – 0 1 . 04 . 09 . 07 . 03 | 0 7 aj Pertaining to colour Red :: deep red/crimson wine 1950 – 0 1 . 05 . 05 . 12 . 01 . 0 3 . 02 | 02 . 03 n Action/operation Patronage :: patron :: as lord/protector wine oe 0 1 . 05 . 05 . 15 . 01 . 05 | 1 7 . 0 6 . 03 n Action/operation Care/protection :: protector :: one who looks after a lord wine oe 0 2 . 02 . 22 . 1 2 | 01 n Love One who loves/a lover :: male lover wine oe 0 2 . 02 . 22 . 1 5 | 1 4 n Love Friendliness :: friend wine oe– 1 481 0 2 . 02 . 22 . 1 5 | 1 4 . 19 n Love Friendliness :: friend :: friendly/gracious lord wine oe 0 3 . 0 4 . 0 9 . 02 . 01 . 02 . 0 2 | 09 n Being subject to authority Attendant :: confidential servant/companion wine oe 0 3 . 0 7 . 0 5 . 15 . 07 . 02 n Artefacts Wine wine oe– 0 3 . 11 . 02 . 0 5 . 01 | 1 1 n Social event Party :: drinking-party wine 185 7 –

Disambiguation Time Filtering ( 14 00 ) 0 1 .
02 . 02 . 0 3 . 05 . 02 . 0 7 | 0 4 n Health and disease Medicinal potion/draught :: medicated wine wine 165 2 – 0 1 . 02 . 05 . 13 . 09 . 0 2 . 0 2 | 0 6 . 14 n Plants Tree/plant producing edible berries :: grape-vine wine 13 40 / 7 0 – 16 3 2 0 1 . 02 . 09 . 0 2 . 02 . 02 n Food and drink Wine wine oe– 0 1 . 02 . 09 . 0 2 . 02 . 02 . 12 n Food and drink Non-grape and home-made wines wine 13 98 – 0 1 . 02 . 09 . 0 2 . 14 . 01 | 0 8 vt Make wine store wine/stock cellar wine c 1 6 4 5 0 1 . 02 . 09 . 0 2 . 19 | 05 vt Provide/serve (with) drink supply with specific drink wine 1862 – 0 1 . 02 . 09 . 0 2 . 2 0 . 01 | 18 n Food and drink Drinking vessel :: glass wine 1848 – 0 1 . 02 . 09 . 0 2 . 2 1 | 10 . 09 vi Drink drink intoxicating liquor :: drink wine wine (and dine) 1829 – 0 1 . 04 . 09 . 07 . 03 | 0 2 . 02 n Colour Red/redness :: shades of red :: deep red /crimson wine 1895 – 0 1 . 04 . 09 . 07 . 03 | 0 7 aj Pertaining to colour Red :: deep red/crimson wine 1950 – 0 1 . 05 . 05 . 12 . 01 . 0 3 . 02 | 02 . 03 n Action/operation Patronage :: patron :: as lord/protector wine oe 0 1 . 05 . 05 . 15 . 01 . 05 | 1 7 . 0 6 . 03 n Action/operation Care/protection :: protector :: one who looks after a lord wine oe 0 2 . 02 . 22 . 1 2 | 01 n Love One who loves/a lover :: male lover wine oe 0 2 . 02 . 22 . 1 5 | 1 4 n Love Friendliness :: friend wine oe– 1 481 0 2 . 02 . 22 . 1 5 | 1 4 . 19 n Love Friendliness :: friend :: friendly/gracious lord wine oe 0 3 . 0 4 . 0 9 . 02 . 01 . 02 . 0 2 | 09 n Being subject to authority Attendant :: confidential servant/companion wine oe 0 3 . 0 7 . 0 5 . 15 . 07 . 02 n Artefacts Wine wine oe– 0 3 . 11 . 02 . 0 5 . 01 | 1 1 n Social event Party :: drinking-party wine 185 7 –

Thematic Category Set

v. 1 Print htoed v. 2 First online version v.
3 Small-scale moves, tidying up v. 4 Large-scale renumbering v. 4 . 2 Thematic category set v. 5 oed 3 updates/sync; over 16 0 , 000 entries from v 1 re-dated, 1 1 , 097 new words added

‣ HT Thematic Dataset ‣ ‘Human scale’ categories ‣ for
example: aq 03 b Ghost/phantom ‣ 4 , 034 categories (as opposed to 235 , 0 0 0+ ) ‣ Useful for: ‣ an aggregation level for data ‣ larger categories for analysis ‣ browsing and visualisation ‣ users finding search terms Thematic Categories

‣ Thematic top tier corresponds to high level HT categories
‣ From aa (The world) to bk (Leisure) ‣ And za (Proper nouns) to zf (Pronouns) for the ht “04” categories of grammatical items and other words with no semantic content ‣ Four further possible tiers below this Thematic Categories

‣ bf 2 4 e 02 b Christmas: ‣ bf
Faith ‣ bf 2 4 Worship ‣ bf 2 4 e Liturgical year ‣ bf 2 4 e 0 2 Feast, festival ‣ Cf ht 03 . 0 8 . 0 4 . 05 . 02 . 01 . 0 5 n Christmas: ‣ Society :: Faith :: Worship :: Liturgical year (chronological order) :: Feast, festival :: Specific Christian festivals Thematic Categories

110 0 1125 1150 1175 120 0 1225 1250 1275
13 00 13 25 13 50 13 75 140 0 1425 145 0 1475 150 0 15 2 5 1550 157 5 160 0 1625 1650 16 75 17 00 17 25 175 0 1775 1800 1825 185 0 1875 190 0 19 25 1950 1975 20 00 aj 01 Alchemy 110 0 1125 1150 1175 120 0 1225 1250 1275 13 00 13 25 13 50 13 75 140 0 1425 145 0 1475 150 0 15 2 5 1550 157 5 160 0 1625 1650 16 75 17 00 17 25 175 0 1775 1800 1825 185 0 1875 190 0 19 25 1950 1975 20 00 AJ02 Chemistry

1100 1125 1150 1175 1200 1225 1250 1275 1300 1325
1350 1375 1400 1425 1450 1475 1500 1525 1550 1575 1600 1625 1650 1675 1700 1725 1750 1775 1800 1825 1850 1875 1900 1925 1950 1975 2000 A U 07 Meekness 1100 1125 1150 1175 1200 1225 1250 1275 1300 1325 1350 1375 1400 1425 1450 1475 1500 1525 1550 1575 1600 1625 1650 1675 1700 1725 1750 1775 1800 1825 1850 1875 1900 1925 1950 1975 2000 A U 37 a Arrogance 1100 1125 1150 1175 1200 1225 1250 1275 1300 1325 1350 1375 1400 1425 1450 1475 1500 1525 1550 1575 1600 1625 1650 1675 1700 1725 1750 1775 1800 1825 1850 1875 1900 1925 1950 1975 2000 AI 12 a Insipidity

•Ten texts were selected from different genres and time periods
( 1820 t o 2014 ) a nd m a n ua ll y ta g g ed by o u r t e a m •E a ch t ex t con ta ins a bo ut 1 , 000 words •Evaluated for both H T senses and thematic senses •Evaluation criterion: If top three of the candidate tags suggested by the system contain the correct tag(s), this is considered to have been correctly annotated –In our evaluation, 8 1 . 18% and 12 . 7 4% of the correct tags were the first and second candidate tags respectively. Tagging Accuracy

Document Text type Year of publication HT full cat. precision
(%) HT main cat. precision (%) Thematic cat precision (%) B iography Written biography   (Life of Theodore Roosevelt) 190 4 70 . 50 72 . 93 73 . 41 C onvers Spoken conversation   (SCOTS Corpus) 201 4 69 . 31 71 . 72 73 . 77 E mail Email messages (Enron Corpus) 200 1 67 . 60 69 . 79 70 . 89 F iction 1 Dickens, Bleak House 185 2 70 . 27 73 . 82 75 . 32 F iction 2 Wodehouse, Something Fresh 191 5 73 . 31 75 . 10 75 . 60 H ans 1 8 2 0 Hansard Speech (William Scott) 182 0 76 . 73 79 . 45 80 . 33 H ans 20 01 Hansard Speech (Tony Blair) 200 1 74 . 61 77 . 32 77 . 42 H istory Gibbon’s Decline and Fall (II.ii) 184 5 73 . 83 77 . 73 77 . 98 J ournalism Longform Journalism   (The Radioactive Boy Scout) 199 8 66 . 67 70 . 45 71 . 74 N ews C ol Newspaper opinion column (Drinking Is Like A Minibreak) 201 0 70 . 69 73 . 43 74 . 91 Total 71 . 56 74 . 44 75 . 36

Disambiguation (Future) Polyseme Density 0 1 . 02 . 02
. 0 3 . 05 . 02 . 0 7 | 0 4 n Health and disease Medicinal potion/draught :: medicated wine wine 165 2 – 0 1 . 02 . 05 . 13 . 09 . 0 2 . 0 2 | 0 6 . 14 n Plants Tree/plant producing edible berries :: grape-vine wine 13 40 / 7 0 – 16 3 2 0 1 . 02 . 09 . 0 2 . 02 . 02 n Food and drink Wine wine oe– 0 1 . 02 . 09 . 0 2 . 02 . 02 . 12 n Food and drink Non-grape and home-made wines wine 13 98 – 0 1 . 02 . 09 . 0 2 . 14 . 01 | 0 8 vt Make wine store wine/stock cellar wine c 1 6 4 5 0 1 . 02 . 09 . 0 2 . 19 | 05 vt Provide/serve (with) drink supply with specific drink wine 1862 – 0 1 . 02 . 09 . 0 2 . 2 0 . 01 | 18 n Food and drink Drinking vessel :: glass wine 1848 – 0 1 . 02 . 09 . 0 2 . 2 1 | 10 . 09 vi Drink drink intoxicating liquor :: drink wine wine (and dine) 1829 – 0 1 . 04 . 09 . 07 . 03 | 0 2 . 02 n Colour Red/redness :: shades of red :: deep red /crimson wine 1895 – 0 1 . 04 . 09 . 07 . 03 | 0 7 aj Pertaining to colour Red :: deep red/crimson wine 1950 – 0 1 . 05 . 05 . 12 . 01 . 0 3 . 02 | 02 . 03 n Action/operation Patronage :: patron :: as lord/protector wine oe 0 1 . 05 . 05 . 15 . 01 . 05 | 1 7 . 0 6 . 03 n Action/operation Care/protection :: protector :: one who looks after a lord wine oe 0 2 . 02 . 22 . 1 2 | 01 n Love One who loves/a lover :: male lover wine oe 0 2 . 02 . 22 . 1 5 | 1 4 n Love Friendliness :: friend wine oe– 1 481 0 2 . 02 . 22 . 1 5 | 1 4 . 19 n Love Friendliness :: friend :: friendly/gracious lord wine oe 0 3 . 0 4 . 0 9 . 02 . 01 . 02 . 0 2 | 09 n Being subject to authority Attendant :: confidential servant/companion wine oe 0 3 . 0 7 . 0 5 . 15 . 07 . 02 n Artefacts Wine wine oe– 0 3 . 11 . 02 . 0 5 . 01 | 1 1 n Social event Party :: drinking-party wine 185 7 –

Disambiguation (Future) HS D (Human-Scale Distance) 0 1 . 02
. 02 . 0 3 . 05 . 02 . 0 7 | 0 4 n Health and disease Medicinal potion/draught :: medicated wine wine 165 2 – 0 1 . 02 . 05 . 13 . 09 . 0 2 . 0 2 | 0 6 . 14 n Plants Tree/plant producing edible berries :: grape-vine wine 13 40 / 7 0 – 16 3 2 0 1 . 02 . 09 . 0 2 . 02 . 02 n Food and drink Wine wine oe– 0 1 . 02 . 09 . 0 2 . 02 . 02 . 12 n Food and drink Non-grape and home-made wines wine 13 98 – 0 1 . 02 . 09 . 0 2 . 14 . 01 | 0 8 vt Make wine store wine/stock cellar wine c 1 6 4 5 0 1 . 02 . 09 . 0 2 . 19 | 05 vt Provide/serve (with) drink supply with specific drink wine 1862 – 0 1 . 02 . 09 . 0 2 . 2 0 . 01 | 18 n Food and drink Drinking vessel :: glass wine 1848 – 0 1 . 02 . 09 . 0 2 . 2 1 | 10 . 09 vi Drink drink intoxicating liquor :: drink wine wine (and dine) 1829 – 0 1 . 04 . 09 . 07 . 03 | 0 2 . 02 n Colour Red/redness :: shades of red :: deep red /crimson wine 1895 – 0 1 . 04 . 09 . 07 . 03 | 0 7 aj Pertaining to colour Red :: deep red/crimson wine 1950 – 0 1 . 05 . 05 . 12 . 01 . 0 3 . 02 | 02 . 03 n Action/operation Patronage :: patron :: as lord/protector wine oe 0 1 . 05 . 05 . 15 . 01 . 05 | 1 7 . 0 6 . 03 n Action/operation Care/protection :: protector :: one who looks after a lord wine oe 0 2 . 02 . 22 . 1 2 | 01 n Love One who loves/a lover :: male lover wine oe 0 2 . 02 . 22 . 1 5 | 1 4 n Love Friendliness :: friend wine oe– 1 481 0 2 . 02 . 22 . 1 5 | 1 4 . 19 n Love Friendliness :: friend :: friendly/gracious lord wine oe 0 3 . 0 4 . 0 9 . 02 . 01 . 02 . 0 2 | 09 n Being subject to authority Attendant :: confidential servant/companion wine oe 0 3 . 0 7 . 0 5 . 15 . 07 . 02 n Artefacts Wine wine oe– 0 3 . 11 . 02 . 0 5 . 01 | 1 1 n Social event Party :: drinking-party wine 185 7 – 2.5 1 0 1 0.5 0.5 0.5 1 1 0.5 2 1.5 0.5 0.5 1 2.5 0 0.5

Disambiguation (Future) Other Methods Highly polysemous words? set ( 3
4 5 meanings), run ( 30 2 ), strike ( 25 6 ), fall ( 2 0 6 ), cast ( 18 7 ), round ( 179 ), turn ( 1 7 4 ), point ( 169 ), slip ( 165 ), pass ( 16 0 ), shoot ( 1 5 9 ), take ( 15 8 )... eg, take ( 199 results) – likely to be 0 2 . 07 . 1 3 (‘move a thing from an initial place into one’s possession’) Template rules? eg, sneeze usually 0 1 . 02 . 02 . 01 . 04 . 18 . 14 | 0 2 vi ‘have respiratory spasm’…but if in a structure sneeze NP PP (eg ‘sneeze the napkin off the table’) then tag as 01 . 02 . 02 . 0 1 . 0 4 . 18 . 14 | 03 vt ‘ Text topic identification? Collocation/machine learning (using OED example sentences)?

Hansard Corpus 18 0 3 – 2 003 7 .
6 m speeches; 1 . 6 bn words; POS and 2 x semantically tagged   www.english-corpora.org/hansard

2 0 46 references to the uncivil in Hansard from
1803 – 200 3 Coded for: Target, Category, Theme, Animacy, Foreign/Domestic, (Relative) Present/Past, Country, Region, Nation, People, Sense-Family

Ireland 5 5 Northern Ireland 45 India 34 Russia 32
Scotland 31 Africa 30 China 25 New Zealand 18 South Africa 16 Turkey 16 Iraq 14 Europe 13 Abyssinia 11 Japan 11 England 10 Greece 10 Spain 10 Afghanistan 9 US 9 Egypt 8

1 80 0 1 810 1 820 1 830 1
840 1 85 0 1 860 1 87 0 1 88 0 1 890 1 90 0 1 910 1 9 2 0 1 930 1 94 0 1 95 0 1 960 1 97 0 1 980 1 990 2 000 Past Present

1 80 0 1 810 1 820 1 830 1
840 1 85 0 1 860 1 87 0 1 88 0 1 890 1 90 0 1 910 1 9 2 0 1 930 1 94 0 1 95 0 1 960 1 97 0 1 980 1 990 2 000 Animate Inanimate

1 80 0 1 810 1 820 1 830 1
840 1 85 0 1 860 1 87 0 1 88 0 1 890 1 90 0 1 910 1 9 2 0 1 930 1 94 0 1 95 0 1 960 1 97 0 1 980 1 990 2 000 Domestic Foreign Ireland Northern Ireland

Shift from foreign to domestic Shift from place to practice
Shift from animate to inanimate Outlook, attitude, increased oppositionality

AP Relative properties AK Existence and causation AO Action/operation AR
The mind AM Time BB Authority AW Possession/ownership AS Attention, judgment, curiosity AX Language AL Space BJ Trade and fi nance AV Will BG Communication AU Emotion BK Leisure AY Society AA The world AN Movement BI Occupation and work BD Morality BC Law AI Physical sensation AB Life AC Health and disease AJ Matter AZ Inhabiting and dwelling AG Food and drink AD People BA Armed hostility BE Education AE Animals BF Faith AT Goodness and badness BH Travel and travelling AF Plants AH Textiles and clothing AQ The supernatural 0 25 , 00 0 , 000 50 , 0 0 0 , 00 0 75 , 0 00 , 000 100 , 000 , 0 00 Hansard   (Commons)

AZ Inhabiting and dwelling AG Food and drink AD People
BA Armed hostility BE Education AE Animals BF Faith AT Goodness and badness BH Travel and travelling AF Plants AH Textiles and clothing AQ The supernatural 0 Hansard   (Commons)

The mind AM Time BB Authority AW Possession/ownership AS Attention, judgment, curiosity AX Language AL Space BJ Trade and fi nance AV Will BG Communication AU Emotion BK Leisure AY Society AA The world AN Movement BI Occupation and work BD Morality BC Law AI Physical sensation AB Life AC Health and disease AJ Matter AZ Inhabiting and dwelling AG Food and drink AD People BA Armed hostility BE Education AE Animals BF Faith AT Goodness and badness BH Travel and travelling AF Plants AH Textiles and clothing AQ The supernatural 0 25 , 00 0 , 000 50 , 0 0 0 , 00 0 75 , 0 00 , 000 100 , 000 , 0 00 Hansard   (Commons)

AP Relative properties AK Existence and causation AR The mind
AW Possession/ownership AO Action/operation AM Time BB Authority AS Attention, judgment, curiosity BF Faith AX Language AL Space AU Emotion AB Life AN Movement AQ The supernatural AI Physical sensation BG Communication BK Leisure AV Will AA The world AJ Matter BD Morality AD People AY Society AG Food and drink AT Goodness and badness AE Animals BJ Trade and fi nance AC Health and disease BH Travel and travelling BC Law BA Armed hostility BI Occupation and work AF Plants AZ Inhabiting and dwelling BE Education AH Textiles and clothing 0 17 , 50 0 , 000 3 5 , 0 00 , 0 00 5 2 , 5 0 0 , 000 7 0 , 00 0 , 000 SEEBO

The mind AM Time BB Authority AW Possession/ownership AS Attention, judgment, curiosity AX Language AL Space BJ Trade and fi nance AV Will BG Communication AU Emotion BK Leisure AY Society AA The world AN Movement BI Occupation and work BD Morality BC Law AI Physical sensation AB Life AC Health and disease AJ Matter AZ Inhabiting and dwelling AG Food and drink AD People BA Armed hostility BE Education AE Animals BF Faith AT Goodness and badness BH Travel and travelling AF Plants AH Textiles and clothing AQ The supernatural 0 2 5 , 000 , 00 0 5 0 , 0 0 0 , 000 7 5 , 0 0 0 , 00 0 1 00 , 000 , 0 00 AP Relative properties AK Existence and causation AR The mind AW Possession/ownership AO Action/operation AM Time BB Authority AS Attention, judgment, curiosity BF Faith AX Language AL Space AU Emotion AB Life AN Movement AQ The supernatural AI Physical sensation BG Communication BK Leisure AV Will AA The world AJ Matter BD Morality AD People AY Society AG Food and drink AT Goodness and badness AE Animals BJ Trade and fi nance AC Health and disease BH Travel and travelling BC Law BA Armed hostility BI Occupation and work AF Plants AZ Inhabiting and dwelling BE Education AH Textiles and clothing 0 1 7 , 500 , 0 0 0 35 , 0 00 , 000 5 2 , 500 , 00 0 7 0 , 000 , 00 0 SEEBO Hansard   (Commons)

Type I Semantic Scaffolds

Type I Semantic Scaffolds Type II Semantic Content

Type I Semantic Scaffolds Type II Semantic Content Type 0
Grammatical Operators

Type II Frequencies Type 0 Type I Keyness

Content Function Type I Type II Type 0

Type I Type II ↓↓ content role ↑↑ grammatical role
↑ discourse-pragmatic scaffolding ↓↓ range of lexical realisations ↑ content role ↓ grammatical role ↑↑ discourse-pragmatic scaffolding ↓ range of lexical realisations ↑↑ content role ↓↓ grammatical role ↓↓ discourse-pragmatic scaffolding ↑↑ range of lexical realisations Type 0

Thank you! ht.ac.uk www.glasgow.ac.uk/samuels

Kay, C., Alexander, M. , Dallachy, F. , Roberts, J.,
Samuels, M. and Wotherspoon, I. ( 2 0 20 ) The Historical Thesaurus of English, second edition. https://ht.ac.uk Alexander, M. and Dallachy, F. ( 2 0 2 0 ) Lexis. In: Adolphs, S. and Knight, D. (eds.) The Routledge Handbook of English Language and Digital Humanities. Routledge. 16 4 – 18 4 . Alexander, M. , Davies, M. and Dallachy, F. ( 20 15 ) The Hansard Corpus 1803 - 2005 . https://www.english-corpora.org/hansard/ Alexander, M. , Davies, M. and Dallachy, F. ( 20 17 ) Semantic EEBO. https://www.english-corpora.org/eebo/ Alexander, M. , Baron, A., Dallachy, F. , Piao, S., Rayson, P. and Wattam, S. ( 2015 ) The Historical Thesaurus Semantic Tagger. https://www.glasgow.ac.uk/samuels Alexander, M. , Dallachy, F. , Piao, S., Baron, A. and Rayson, P. ( 20 1 5 ) Metaphor, popular science, and semantic tagging: Distant reading with the Historical Thesaurus of English. Digital Scholarship in the Humanities 30 i. i 1 6 –i 2 7 . Piao, S., Dallachy, F. , Baron, A., Demmen, J., Wattam, S., Durkin, P., McCracken, J., Rayson, P. and Alexander, M. ( 2017 ) A time- sensitive historical thesaurus-based semantic tagger for deep semantic annotation. Computer Speech and Language 4 6 . 113 – 135 . Wattam, S., Rayson, P., Alexander, M. and Anderson, J. ( 2015 ) Experiences with parallelisation of an existing NLP pipeline: tagging Hansard. Language Resources and Evaluation ( LREC ' 14 ), European Language Resources Association ( EL R A ). 4093 – 4 0 9 6 . Kay, C. and Alexander, M. ( 2 015 ) Diachronic and synchronic thesauruses. In: Durkin, P. (ed.) The Oxford Handbook of Lexicography. Oxford University Press.

Semantic Tagging with the Historical Thesaurus ...

Semantic Tagging with the Historical Thesaurus of English

More Decks by Marc Alexander

Featured

Transcript