CLAWS (linguistics) The Constituent Likelihood Automatic Word-tagging System or CLAWS is a program that performs part-of-speech tagging. It was developed in the 1980s at Lancaster University by the University Centre for Computer Corpus Research on Language. ^[1] It has an overall accuracy rate of 96-97% with the latest version (CLAWS4) tagging around 100 million words of the British National Corpus. ^[1]

A Part-Of-Speech Tagger (POS Tagger) is a piece of software that reads text in some language and assigns parts of speech to each word (and other token), such as noun, verb, adjective, etc., although generally computational applications use more fine-grained POS tags like 'noun-plural'. ^[2] Developed in the early 1980s ^[1], CLAWS was built to fill the ever-growing gap created by always changing POS necessities. Since its inception, CLAWS has been hailed for its functionality and adaptability. Still it is not without flaws, and though it boasts an error-rate of only 1.5% when judged in major categories, CLAWS still remains with c.3.3% ambiguities unresolved. ^[1] Ambiguity arises in cases such as with the word flies, and whether it should be classified as a noun or a verb. ^[3] It's these ambiguities that will require the various upgrades and tagsets that CLAWS will endure.

CLAWS uses a Hidden Markov model to determine the likelihood of sequences of words / parts of speech. ^[4]

This excerpt from Bram Stoker's Dracula (1897) has been tagged using both the CLAWS C5 and C7 tagsets. This is what a CLAWS output will generally look like, with the most likely part-of-speech tag following each word.

The first tagset developed in CLAWS, CLAWS1 tagset, has 132 word tags. In terms of form and application, C1 tagset is similar to Brown Corpus tags ^[5]. See Table of tags in C1 tagset here ^[6].

CLAWS2 tasget with 166 word tags was developed at Lancaster in 1983-1986 ^[7]. See Table of tags in C2 tagset here ^[8].

CLAWS4 is a general-purpose grammatical tagger. It was used for 100-million-word British National Corpus (BNC). It is a successor of CLAWS1 tagger ^[9]. The latest version of CLAWS4 is offered by UCREL, a research center of Lancaster University ^{[10] [11]}.

CLAWS5 tagset, which was used for BNC, has over 60 tags ^[12]. See Table of tags in C5 tagset here ^[13].

CLAWS6 tagset, which was used for BNC sampler corpus, has over 160 tags ^[14]. See Table of tags in C6 tagset here ^[15].

The standard CLAWS7 tagset is used currently. It is only different in the punctuation tags when compared to the CLAWS6 tagset ^[16]. See Table of tags in C7 tagset here ^[17].

CLAWS8 tagset was extended from C7 tagset with further distinctions in the determiner and pronoun categories, as well as auxiliary verbs ^[18]. See Table of tags in C8 tagset here.

.tagsets used in Sketch Engine

about Sketch Engine

what it was created for

what it is used for now "The latest version of the tagger, CLAWS4, was used to POS tag c.100 million words of the British National Corpus" ^[19]

who uses it now

CLAWS Tag Sets - what in each one, what it means: present in table/chart form

http://ucrel.lancs.ac.uk/claws/ ^[1]

https://www.researchgate.net/publication/2618590_The_CLAWS_Web_Tagger ^[20]

https://www.sketchengine.eu/english-claws7-part-of-speech-tagset/: claws 7 Tag sets ^[21]

https://books.google.com/books?id=67OSqA_3hykC&pg=PA164&lpg=PA164&dq=CLAWS+(linguistics)&source=bl&ots=bfXmJDElEe&sig=ACfU3U17rX6G14e_ulF3sGIkTwesNCfGHw&hl=en&sa=X&ved=2ahUKEwiRlZbQs-vnAhUJR6wKHeomC9sQ6AEwBnoECAsQAQ#v=onepage&q=CLAWS%20(linguistics)&f=false ^[22]

http://www.natcorp.ox.ac.uk/docs/claws7.html ^[23]

other taggers: http://martinweisser.org/corpora_site/taggers.html ^[24]

benefits of POS taggers: http://www.inf.ed.ac.uk/teaching/courses/inf2a/slides/2007_inf2a_L13_slides.pdf

in depth explanation of taggers: http://www.cs.uccs.edu/~jkalita/work/cs589/2010/5POSTags.pdf

https://e-space.mmu.ac.uk/619647/1/Tagging_the_Bard_Evaluating_the_accuracy_of_a_mode.pdf how it can be used/works

http://ucrel-api.lancaster.ac.uk/claws/free.html ^[25] Link to actual free tagger

current system: http://ucrel.lancs.ac.uk/papers/coling.html ^[26]

• Brill tagger
• Part-of-speech tagging
• Sliding window based part-of-speech tagging
• British National Corpus
• Brown Corpus
• Lancaster University