Corpus linguistics is the study of a language as that language is expressed in its text corpus (plural corpora), its body of "real world" text. Corpus linguistics proposes that a reliable analysis of a language is more feasible with a corpora collected in the field--the natural context ("realia") of that language--with minimal experimental interference.
The text-corpus method uses the body of texts written in any natural language to derive the set of abstract rules which govern that language. Those results can be used to explore the relationships between that subject language and other languages which have undergone a similar analysis. The first such corpora were manually derived from source texts, but now that work is automated.
Corpora have not only been used for linguistics research, they have also been used to compile dictionaries (starting with The American Heritage Dictionary of the English Language in 1969) and grammar guides, such as A Comprehensive Grammar of the English Language, published in 1985.
Experts in the field have differing views about the annotation of a corpus. These views range from John McHardy Sinclair, who advocates minimal annotation so texts speak for themselves, to the Survey of English Usage team (University College, London), who advocate annotation as allowing greater linguistic understanding through rigorous recording.
Some of the earliest efforts at grammatical description were based at least in part on corpora of particular religious or cultural significance. For example, Pr?tikhya literature described the sound patterns of Sanskrit as found in the Vedas, and Pini's grammar of classical Sanskrit was based at least in part on analysis of that same corpus. Similarly, the early Arabic grammarians paid particular attention to the language of the Quran. In the Western European tradition, scholars prepared concordances to allow detailed study of the language of the Bible and other canonical texts.
A landmark in modern corpus linguistics was the publication of Computational Analysis of Present-Day American English in 1967. Written by Henry Ku?era and W. Nelson Francis, the work was based on an analysis of the Brown Corpus, which was a contemporary compilation of about a million American English words, carefully selected from a wide variety of sources. Ku?era and Francis subjected the Brown Corpus to a variety of computational analyses and then combined elements of linguistics, language teaching, psychology, statistics, and sociology to create a rich and variegated opus. A further key publication was Randolph Quirk's "Towards a description of English Usage" in 1960 in which he introduced the Survey of English Usage.
Shortly thereafter, Boston publisher Houghton-Mifflin approached Ku?era to supply a million-word, three-line citation base for its new American Heritage Dictionary, the first dictionary compiled using corpus linguistics. The AHD took the innovative step of combining prescriptive elements (how language should be used) with descriptive information (how it actually is used).
Other publishers followed suit. The British publisher Collins' COBUILD monolingual learner's dictionary, designed for users learning English as a foreign language, was compiled using the Bank of English. The Survey of English Usage Corpus was used in the development of one of the most important Corpus-based Grammars, which was written by Quirk et al. and published in 1985 as A Comprehensive Grammar of the English Language.
The Brown Corpus has also spawned a number of similarly structured corpora: the LOB Corpus (1960s British English), Kolhapur (Indian English), Wellington (New Zealand English), Australian Corpus of English (Australian English), the Frown Corpus (early 1990s American English), and the FLOB Corpus (1990s British English). Other corpora represent many languages, varieties and modes, and include the International Corpus of English, and the British National Corpus, a 100 million word collection of a range of spoken and written texts, created in the 1990s by a consortium of publishers, universities (Oxford and Lancaster) and the British Library. For contemporary American English, work has stalled on the American National Corpus, but the 400+ million word Corpus of Contemporary American English (1990-present) is now available through a web interface.
The first computerized corpus of transcribed spoken language was constructed in 1971 by the Montreal French Project, containing one million words, which inspired Shana Poplack's much larger corpus of spoken French in the Ottawa-Hull area.
In the 1990s, many of the notable early successes on statistical methods in natural-language programming (NLP) occurred in the field of machine translation, due especially to work at IBM Research. These systems were able to take advantage of existing multilingual textual corpora that had been produced by the Parliament of Canada and the European Union as a result of laws calling for the translation of all governmental proceedings into all official languages of the corresponding systems of government.
There are corpora in non-European languages as well. For example, the National Institute for Japanese Language and Linguistics in Japan has built a number of corpora of spoken and written Japanese.
Besides these corpora of living languages, computerized corpora have also been made of collections of texts in ancient languages. An example is the Andersen-Forbes database of the Hebrew Bible, developed since the 1970s, in which every clause is parsed using graphs representing up to seven levels of syntax, and every segment tagged with seven fields of information. The Quranic Arabic Corpus is an annotated corpus for the Classical Arabic language of the Quran. This is a recent project with multiple layers of annotation including morphological segmentation, part-of-speech tagging, and syntactic analysis using dependency grammar.
Besides pure linguistic inquiry, researchers had begun to apply corpus linguistics to other academic and professional fields, such as the emerging sub-discipline of law and corpus linguistics, which seeks to understand legal texts using corpus data and tools.
Corpus linguistics has generated a number of research methods, which attempt to trace a path from data to theory. Wallis and Nelson (2001) first introduced what they called the 3A perspective: Annotation, Abstraction and Analysis.
Most lexical corpora today are part-of-speech-tagged (POS-tagged). However even corpus linguists who work with 'unannotated plain text' inevitably apply some method to isolate salient terms. In such situations annotation and abstraction are combined in a lexical search.
The advantage of publishing an annotated corpus is that other users can then perform experiments on the corpus (through corpus managers). Linguists with other interests and differing perspectives than the originators' can exploit this work. By sharing data, corpus linguists are able to treat the corpus as a locus of linguistic debate and further study.
Book series in this field include:
There are several international peer-reviewed journals dedicated to corpus linguistics, for example: