Editing Lemmatization (section)

{{Short description|Natural language processing canonicalisation}}
'''Lemmatization''' (or less commonly '''lemmatisation''') in [[linguistics]] is the process of grouping together the [[Inflection|inflected form]]s of a word so they can be analysed as a single item, identified by the word's [[Lemma (morphology)|lemma]], or dictionary form.<ref>''Collins English Dictionary'', entry for "lemmatize"</ref>

In [[computational linguistics]], lemmatization is the algorithmic process of determining the [[Lemma (morphology)|lemma]] of a word based on its intended meaning. Unlike [[stemming]], lemmatization depends on correctly identifying the intended [[part of speech]] and meaning of a word in a sentence, as well as within the larger [[context (language use)|context]] surrounding that sentence, such as neighbouring sentences or even an entire document. As a result, developing efficient lemmatization algorithms is an open area of research.<ref name="Semantic Annotation Research">{{cite web |url=https://scholar.archive.org/work/wes6yl773jb7jb3w5jvdydiuei|title=WebBANC: Building Semantically-Rich Annotated Corpora from Web User Annotations of Minority Languages}}</ref><ref name="Muller, University of Munich">{{cite conference  |url=http://www.cis.lmu.de/~muellets/pdf/emnlp_2015.pdf|title=Joint Lemmatization and Morphological Tagging with LEMMING|first1=Thomas|last1=Müller|first2=Ryan|last2=Cotterell|first3=Alexander|last3=Fraser|first4=Hinrich|last4=Schütze|date=2015|doi=10.18653/v1/D15-1272|doi-access=free|publisher=Association for Computational Linguistics|conference=2015 Conference on Empirical Methods in Natural Language Processing|pages=2268–2274|location=Lisbon}}</ref><ref>{{Cite web|url=http://homepages.inf.ed.ac.uk/s1044253/papers/Context_Sensitive_Neural_Lemmatization_with_Lematus.pdf|title=Context Sensitive Neural Lemmatization with Lematus|last1=Bergmanis|first1=Toms|last2=Goldwater|first2=Sharon|author2-link=Sharon Goldwater}}</ref>