This POS tagging is based on the probability of tag occurring. Parts-of-speech.Info Enter a complete sentence (no single words!) Features Detailed tag set POS Tagger has a detailed tag set consisting of more than 3,000 tags, which reflects the most important features of each word. Secara probabilistik dapat dituliskan sebagai P (Y | X), dimana Y merupakan barisan kelas kata dan X merupakan barisan kata. Models are evaluated based on accuracy. POS can reveal a lot of information about neighbouring words and syntactic structure of a sentence. Part of speech tagging is the process of adorning or "tagging" words in a text with each word's corresponding part of speech. "Part-of-speech tagging from 97% to 100%: is it time for some linguistics?" M, the number of distinct observations that can appear with each state in the above example M = 2, i.e., H or T). Here is the following code – pip install nltk # install using the pip package manager import nltk nltk.download('averaged_perceptron_tagger') The above line will install and download the respective corpus etc. An HMM model may be defined as the doubly-embedded stochastic model, where the underlying stochastic process is hidden. This means labeling words in a sentence as nouns, adjectives, verbs...etc. Part of Speech Tagging. We can model this POS process by using a Hidden Markov Model (HMM), where tags are the hidden states that produced the observable output, i.e., the words. Part of Speech Tagger. We introduce a memory-based approach to part of speech tagging. Let's take a very simple example of parts of speech tagging. Polyglot recognizes 17 parts of speech, this set is called the universal part of speech tag set: ADJ: adjective; ADP: adposition; ADV: adverb; AUX: auxiliary verb This page lists all part-of-speech tagsets used in preloaded corpora in Sketch Engine. N, the number of states in the model (in the above example N =2, only two states). the bias of the first coin. Sections 0-18 are used for training, sections 19-21 for development, and sections 22-24 for testing. In simple words, we can say that POS tagging is a task of labelling each word in a sentence with its appropriate part of speech. Even more impressive, it also labels by tense, and more. Populating the Transition Matrix 4:38. Part of speech tagging. Part-of-Speech tagging is a well-known task in Natural Language Processing. Rule-based taggers use dictionary or lexicon for getting possible tags for tagging each word. Tujuan Part of Speech Tagging. There would be no probability for the words that do not exist in the corpus. 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'. In this step, we install NLTK module in Python. It is called so because the best tag for a given word is determined by the probability at which it occurs with the n previous tags. Part-of-speech tagging Needs model. Thi… Because tags are generally also applied to punctuation, tagging requires that the punctuation marks (period, comma, etc) be separated off of the words. First stage − In the first stage, it uses a dictionary to assign each word a list of potential parts-of-speech. Part-of-speech tagging (or just tagging for short) is the process tagging of assigning a part-of-speech or other syntactic class marker to each word in a corpus. Part of Speech Tagging 2:28. What is POS tagging good for? Now, our problem reduces to finding the sequence C that maximizes −, PROB (C1,..., CT) * PROB (W1,..., WT | C1,..., CT) (1). These tags mark the core part-of-speech categories. It is another approach of stochastic tagging, where the tagger calculates the probability of a given sequence of tags occurring. A standard dataset for POS tagging is the Wall Street Journal (WSJ) portion of the Penn Treebank, containing 45 different POS tags. Quelques étiqueteurs sont accessibles avec un modèle pour le français prêt à l'emploi comme le TreeTagger, LIA Tagg du Laboratoire informatique d'Avignon, Cordial Analyseur de Synapse Développement ou le Stanford Tagger de l'Université Stanford. The use of HMM to do a POS tagging is a special case of Bayesian interference. It is an instance of the transformation-based learning (TBL), which is a rule-based algorithm for automatic tagging of POS to the given text. It uses different testing corpus (other than training corpus). Following is one form of Hidden Markov Model for this problem −, We assumed that there are two states in the HMM and each of the state corresponds to the selection of different biased coin. POS tagging is the process of marking up a word in a corpus to a corresponding part of speech tag, based on its context and definition… Part-of-speech tagging (POS tagging) is the task of tagging a word in a text with its part of speech. Back in elementary school, we have learned the differences between the various parts of speech tags such as nouns, verbs, adjectives, and adverbs. As the name suggests, all such kind of information in rule-based POS tagging is coded in the form of rules. "A Brief History of the Penn Treebank." The algorithm will stop when the selected transformation in step 2 will not add either more value or there are no more transformations to be selected. A part of speech is a category of words with similar grammatical properties. … In TBL, the training time is very long especially on large corpora. It is a pre-processing stage for advanced applications such as machine learning, translation, and grammar checking [1]. Whats is Part-of-speech (POS) tagging ? Speech and Language Processing, chapter 8 2. Following matrix gives the state transition probabilities −, $$A = \begin{bmatrix}a11 & a12 \\a21 & a22 \end{bmatrix}$$. à l'aide d'un outil informatique[1],[2]. One of the more powerful aspects of the NLTK module is the Part of Speech tagging. A, the state transition probability distribution − the matrix A in the above example. pos_tag () method with tokens passed as argument. It converts a sentence into a list of words with their tags. Development as well as debugging is very easy in TBL because the learned rules are easy to understand. La dernière modification de cette page a été faite le 29 juin 2020 à 14:08. Part-of-Speech Tagging ctb pku 863 Universal Dependencies Named Entity Recognition pku msra ontonotes Dependency Parsing Stanford Dependencies Universal Dependencies Semantic Dependency Parsing The reduction of Minimal Recursion Semantics Now, the question that arises here is which model can be stochastic. De très nombreux exemples de phrases traduites contenant "part of speech tagging" – Dictionnaire français-anglais et moteur de recherche de traductions françaises. Artificial neural networks have been applied successfully to compute POS tagging with great performance. UDpipe library is using Universal Dependencies5. Stem level disambiguation POS Tagger solves the stem […] Part of Speech Tagging¶ Part of speech tagging task aims to assign every word/token in plain text a category that identifies the syntactic functionality of the word occurrence. The POS tagging process is the process of finding the sequence of tags which is most likely to have generated a given word sequence. The model that includes frequency or probability (statistics) can be called stochastic. It is the simplest POS tagging because it chooses most frequent tags associated with a word in training corpus. The information is coded in the form of rules. Start with the solution − The TBL usually starts with some solution to the problem and works in cycles. We have some limited number of rules approximately around 1000. Both the tokenized words (tokens) and a tagset are fed as input into a tagging algorithm. It is considered to be one of the fundamental stages of natural language processing for any language. Common English parts of speech are noun, verb, adjective, adverb, pronoun, preposition, conjunction, etc. • Tagging (part-of-speech tagging) – The process of assigning (labeling) a part-of-speech or other lexical class marker to each word in a sentence (or a corpus) • Decide whether each word is a noun, verb, adjective, or whatever The/AT representative/NN put/VBD chairs/NNS on/IN the/AT table/NN Or Output: [(' the bias of the second coin. P, the probability distribution of the observable symbols in each state (in our example P1 and P2). Because tags are generally also applied to punctuation, tagging requires that the punctuation marks (period, comma, etc) … Since this task involves considering the sentence structure, it cannot be done at the Lexical level. DefaultTagger is most useful when it gets to work with most common part-of-speech tag. Let’s now look into how this works in practice. … Part of Speech Tagging is the process of marking each word in the sentence to its corresponding part of speech tag, based on its context and definition. Hidden Markov Models 3:54. Adda, G., Mariani, J., Paroubek, P., Rajman, M., & Lecomte, J. If the word has more than one possible tag, then rule-based taggers use hand-written rules to identify the correct tag. Learn about Markov chains and Hidden Markov models, then use them to create part-of-speech tags for a Wall Street Journal text corpus! Part-of-speech tagging or POS tagging is the process of assigning a part-of-speech marker to each word in an input text. It takes a string of text usually sentence or paragraph as input and identifies relevant parts of speech such as … Stochastic POS taggers possess the following properties −. En linguistique, l'étiquetage morpho-syntaxique (aussi appelé étiquetage grammatical, POS tagging (part-of-speech tagging) en anglais) est le processus qui consiste à associer aux mots d'un texte les informations grammaticales correspondantes comme la partie du discours, le genre, le nombre, etc. What is Part of Speech (POS) tagging? (1999). The probability of a tag depends on the previous one (bigram model) or previous two (trigram model) or previous n tags (n-gram model) which, mathematically, can be explained as follows −, PROB (C1,..., CT) = Πi=1..T PROB (Ci|Ci-n+1…Ci-1) (n-gram model), PROB (C1,..., CT) = Πi=1..T PROB (Ci|Ci-1) (bigram model). Vous pouvez partager vos connaissances en l’améliorant (comment ?) En linguistique, l' étiquetage morpho-syntaxique (aussi appelé étiquetage grammatical, POS tagging (part-of-speech tagging) en anglais) est le processus qui consiste à associer aux mots d'un texte les informations grammaticales correspondantes comme la partie du discours, le genre, le nombre, etc. So, for something like the sentence above the word can has several semantic meanings. I want to introduce spaCy [5] – a useful NLP library that you can put under your belt. Example: Vinken, 61 To perform Parts of Speech (POS) Tagging with NLTK in Python, use nltk. It is a process of converting a sentence to forms – list of words, list of tuples (where each tuple is having a form (word, tag)).The tag in case of is a part-of-speech tag, and signifies whether the word is a noun, adjective, verb, and so on. As POS tagging is an essential part of many tasks in language processing, all NLP toolkits contain a tagger and often you need to include it in your processing pipeline to get at the essence of the message. Part of speech tagging viết tắt POS tagging/PoS tagging/POST còn được gọi là ngữ hoá tagging hoặc phân loại từ-phân loại, là quá trình đánh dấu một từ trong một văn bản (corpus) tương ứng với một phần cụ thể của lời nói, dựa trên cả định nghĩa và … On the other hand, if we see similarity between stochastic and transformation tagger then like stochastic, it is machine learning technique in which rules are automatically induced from data. Universal POS tags. Complexity in tagging is reduced because in TBL there is interlacing of machinelearned and human-generated rules. Here is the following code – pip install nltk # install using the pip package manager import nltk nltk.download('averaged_perceptron_tagger') The above line will install and download the respective corpus etc. Most of the POS tagging falls under Rule Base POS tagging, Stochastic POS tagging and Transformation based tagging. A part of speech is a category of words with similar grammatical properties. Part-of-speech (POS) tagging is a popular Natural Language Processing process which refers to categorizing words in a text (corpus) in correspondence with a particular part of speech, depending on the definition of the word and its context. Using NLTK . We use the UDpipe library with the corresponding udpipe R package for PoS (part-of-speech tagging) and dependency parsing.UDpipe library is using Universal Dependencies 5.. Universal Dependencies (UD) is a framework for consistent annotation of grammar (parts of speech, morphological features, and syntactic dependencies) across different human languages. Default tagging is a basic step for the part-of-speech tagging. Markov Chains 3:28. Part-of-speech tagging (POS tagging) is the task of tagging a word in a text with its part of speech. Part-of-speech tagging (POS tagging) is the task of tagging a word in a text with its part of speech. We can also create an HMM model assuming that there are 3 coins or more. Parts of speech tagging simply refers to assigning parts of speech to individual words in a sentence, which means that, unlike phrase matching, which is performed at the sentence or multi-word level, parts of speech tagging is performed at the token level. Part-of-Speech Tagging examples in Python. We use the UDpipe library with the corresponding udpipe R package for PoS (part-of-speech tagging) and dependency parsing. Associating each word in a sentence with a proper POS (part of speech) is known as POS tagging or POS annotation. Part of speech tagging is one of the basic steps in natural language processing. Transformation-based tagger is much faster than Markov-model tagger. Common English parts of speech are noun, verb, adjective, adverb, pronoun, preposition, conjunction, etc. The Natural Language Toolkit (NLTK) is a platform used for building programs for text analysis. Unter Part-of-speech-Tagging (POS-Tagging) versteht man die Zuordnung von Wörtern und Satzzeichen eines Textes zu Wortarten (englisch part of speech).Hierzu wird sowohl die Definition des Wortes als auch der Kontext (z. Polyglot recognizes 17 parts of speech, this set is called the universal part of speech tag set : Or, as Regular expression compiled into finite-state automata, intersected with lexically ambiguous sentence representation. Part Of Speech Tagging POS tagging refers to the automatic assignment of a tag to words in a given sentence. As various authors have noted, e.g., [5], the second wave of machine learning part-of-speech taggers, which began with the work of Collins [6] and includes the other taggerscited above,routinely deliver accuracies a little above this level of 97%, when tagging material from the same source and epoch on which they were trained. TBL, allows us to have linguistic knowledge in a readable form, transforms one state to another state by using transformation rules. Part of Speech Tagging¶ Part of speech tagging task aims to assign every word/token in plain text a category that identifies the syntactic functionality of the word occurrence. Part of Speech Tagging with NLTK. POS tagging is necessary for features as Word Sketches, thesaurus, term extraction or trends. It is generally called POS tagging. Example: Vinken, 61 A part of speech is a category of words with similar grammatical properties. selon les recommandations des projets correspondants. The tagging works better when grammar and orthography are correct. It is performed using the DefaultTagger class. L'action GRACE d'évaluation de l'assignation des parties du discours pour le français. and click at "POS-tag!". In corpus linguistics, part-of-speech tagging (POS tagging or PoS tagging or POST), also called grammatical tagging is the process of marking up a word in a text (corpus) as corresponding to a particular part of speech, based on both its definition and its context. The beginning of a sentence can be accounted for by assuming an initial probability for each tag. e.g. Part-of-speech tagging is the task of assigning symbols from a particular set to words in a natural language text. We already know that parts of speech include nouns, verb, adverbs, adjectives, pronouns, conjunction and their sub-categories. INTRODUCTION Part of speech tagging is process that identifies parts of speech in a sentence for a given language. In this approach, the stochastic taggers disambiguate the words based on the probability that a word occurs with a particular tag. NN is the tag for a singular noun. Such kind of learning is best suited in classification tasks. Most beneficial transformation chosen − In each cycle, TBL will choose the most beneficial transformation. After tokenization, spaCy can parse and tag a given Doc. We learn small set of simple rules and these rules are enough for tagging. Before digging deep into HMM POS tagging, we must understand the concept of Hidden Markov Model (HMM). We can also say that the tag encountered most frequently with the word in the training set is the one assigned to an ambiguous instance of that word. Part-of-speech taggingis the process of marking up the words in a text with their corresponding parts of speech reflecting their syntactic category. In order to understand the working and concept of transformation-based taggers, we need to understand the working of transformation-based learning. Parts of Speech (POS) Tagging. Common English parts of speech are noun, verb, adjective, adverb, pronoun, preposition, conjunction, etc. One of the oldest techniques of tagging is rule-based POS tagging. Although it has been investigated for many languages around the world, very little has been done for Setswana language. Part-of-Speech Tagging Berlin Chen 2005 References: 1. To perform POS tagging, we have to tokenize our sentence into words. Part-of-Speech (POS) (noun, verb, and preposition) can help in understanding the meaning of a text by identifying how different words are used in a sentence. The simplest stochastic tagger applies the following approaches for POS tagging −. It resolves the ambiguity on both the stem and the case-ending levels. POS has various tags which are given to the words token as it distinguishes the sense of the word which is helpful in the text realization. We can also call POS tagging a process of assigning one of the parts of speech … Part of Speech tagging does exactly what it sounds like, it tags each word in a sentence with the part of speech for that word. http://www.llf.cnrs.fr/Gens/Abeille/French-Treebank-fr.php, https://www.rocq.inria.fr/alpage-wiki/tiki-index.php?page=CorpusSequoia, Étiquetage morpho-syntaxique pour la langue française, https://fr.wikipedia.org/w/index.php?title=Étiquetage_morpho-syntaxique&oldid=172456303, Traitement automatique du langage naturel, Portail:Sciences humaines et sociales/Articles liés, licence Creative Commons attribution, partage dans les mêmes conditions, comment citer les auteurs et mentionner la licence. Now, if we talk about Part-of-Speech (PoS) tagging, then it may be defined as the process of assigning one of the parts of speech to the given word. The process of classifying words into their parts of speech and labeling them accordingly is known as part-of-speech tagging, POS-tagging, or simply tagging. However, to simplify the problem, we can apply some mathematical transformations along with some assumptions. This means labeling words in a sentence as nouns, adjectives, verbs...etc. These taggers are knowledge-driven taggers. For example, suppose if the preceding word of a word is article then word must be a noun. Foundations of Statistical Natural Language Processing, chapter 10. The main issue with this approach is that it may yield inadmissible sequence of tags. Part-of-speech tagsets with user corpora only are not included. Part-of-Speech (POS) helps in identifying distinction by identifying one bear as a noun and the other as a verb; Word-sense disambiguation "The bear is a majestic animal" "Please bear with me" Sentiment analysis; Question answering; Fake news and opinion spam detection; POS tagging. Part of Speech Tagging and Hidden Markov Models. P2 = probability of heads of the second coin i.e. Part-of-speech tagging. Input: Everything to permit us. The second probability in equation (1) above can be approximated by assuming that a word appears in a category independent of the words in the preceding or succeeding categories which can be explained mathematically as follows −, PROB (W1,..., WT | C1,..., CT) = Πi=1..T PROB (Wi|Ci), Now, on the basis of the above two assumptions, our goal reduces to finding a sequence C which maximizes, Now the question that arises here is has converting the problem to the above form really helped us. 171-189, Tokyo, Japan, Springer-Verlag Berlin, February 20-26. Hence, we will start by restating the problem using Bayes’ rule, which says that the above-mentioned conditional probability is equal to −, (PROB (C1,..., CT) * PROB (W1,..., WT | C1,..., CT)) / PROB (W1,..., WT), We can eliminate the denominator in all these cases because we are interested in finding the sequence C which maximizes the above value. On the other hand, if we talk about Part-of-Speech (POS) tagging, it may be defined as the process of converting a sentence in the form of a list of words, into a list of tuples. After a considerable amount of time since I met with and worked on natural language processing topic, I am here to prevent people — especially desperate students — from having the same difficulties on some basic concepts related. By observing this sequence of heads and tails, we can build several HMMs to explain the sequence. Rule-based POS taggers possess the following properties −. Part of Speech Tagging using NLTK Python-Step 1 – This is a prerequisite step. A simplified form of this is commonly taught to school-age children, in the identification of words as nouns, verbs, adjectives, adverbs, etc. Example Word Tag heat verb (noun) water noun (verb) in prep (noun, adv) a det (noun) large adj (noun) vessel noun . à l'aide d'un outil informatique,. 2011. Example: POS tags are labels used to denote the part-of-speech. If we have a large tagged corpus, then the two probabilities in the above formula can be calculated as −, PROB (Ci=VERB|Ci-1=NOUN) = (# of instances where Verb follows Noun) / (# of instances where Noun appears) (2), PROB (Wi|Ci) = (# of instances where Wi appears in Ci) /(# of instances where Ci appears) (3). Some languages have more than one available POS tagset. Markov Chains and POS Tags 4:25. Part of Speech Tagging with NLTK. Memberikan prediksi terhadap barisan kelas kata yang mungkin dari suatu barisan kata-kata. Part-of-Speech Tagging. Part of speech tagging. Source: Màrquez et al. Words belonging to various parts of speeches form a sentence. From a very small age, we have been made accustomed to identifying part of speech tags. Here's a list of the tags, what they mean, and some examples: These tags then become useful for higher-level applications. Part-of-speech tagging (POS tagging) is the task of tagging a word in a text with its part of speech. (word, tag). part-of-speech tagging is 97%. For example, reading a sentence and being able to identify what words act as nouns, pronouns, verbs, adverbs, and so on. Un article de Wikipédia, l'encyclopédie libre. 2000, table 1. The rules in Rule-based POS tagging are built manually. POS tags are also known as word classes, morphological classes, or lexical tags. Here, the tuples are in the form of (word, tag). In our school days, all of us have studied the parts of speech, which includes nouns, pronouns, adjectives, verbs, etc. This hidden stochastic process can only be observed through another set of stochastic processes that produces the sequence of observations. aij = probability of transition from one state to another from i to j. P1 = probability of heads of the first coin i.e. One of the more powerful aspects of the NLTK module is the Part of Speech tagging that it can do for you. The DefaultTagger class takes ‘tag’ as a single argument. In the processing of natural languages, each word in a sentence is tagged with its part of speech. Common parts of speech in English are noun, verb, adjective, adverb, etc. We can also understand Rule-based POS tagging by its two-stage architecture −. Back in elementary school, we have learned the differences between the various parts of speech tags such as nouns, verbs, adjectives, and adverbs. Parts of speech tagging can be important for syntactic and semantic analysis. Disambiguation can also be performed in rule-based tagging by analyzing the linguistic features of a word along with its preceding as well as following words. 1 Review. One of the more powerful aspects of the NLTK module is the Part of Speech tagging. All these are referred to as the part of speech tags.Let’s look at the Wikipedia definition for them:Identifying part of speech tags is much more complicated than simply mapping words to their part of speech tags. Definition POS Tagger identifies the correct part of speech. Part of speech tagging is based both on the meaning of the word and its positional relationship with adjacent words. POS Tagging Parts of speech Tagging is responsible for reading the text in a language and assigning some specific token (Parts of Speech) to each word. We can make reasonable independence assumptions about the two probabilities in the above expression to overcome the problem. This is a supervised learning approach. The Natural Language Toolkit (NLTK) is a platform used for building programs for text analysis. Marcus, Mitch. Setswana language is written disjunctively and some words play multiple functions in a sentence. Part-of-speech tagging (or just tagging for short) is the process tagging of assigning a part-of-speech or other syntactic class marker to each word in a corpus. Les étiqueteurs grammaticaux sont très nombreux pour les langues saxonnes mais plus rares pour le français. The disadvantages of TBL are as follows −. A part of speech is a category of words with similar grammatical properties. These rules may be either −. Consider the following steps to understand the working of TBL −. What is Part of Speech (POS) tagging? The answer is - yes, it has. Accessed 2019-08-31. Part of Speech Tagging using NLTK Python-Step 1 – This is a prerequisite step. Here the descriptor is called tag, which may represent one of the part-of-speech, semantic information and so on. The actual details of the process - how many coins used, the order in which they are selected - are hidden from us. Tagset is a list of part-of-speech tags. Apply to the problem − The transformation chosen in the last step will be applied to the problem. Here, I will try to assist you in overcoming the issue of part-of-speech (POS) tagging implementation. Any number of different approaches to the problem of part-of-speech tagging can be referred to as stochastic tagger. Associating each word in a sentence with a proper POS (part of speech) is known as POS tagging … This way, we can characterize HMM by the following elements −. Part-of-Speech Tagging • The process of assigning a part-of-speech to each word in a sentence heat water in a large vessel WORDS TAGS N V P DET ADJ . ACOPOST implements and extends well-known machine learning techniques and provides a uniform environment for testing. Downloads: 0 This Week Last Update: 2016-02 … We will focus on the Multilayer Perceptron Network, which is a very … Second stage − In the second stage, it uses large lists of hand-written disambiguation rules to sort down the list to a single part-of-speech for each word. Part of Speech tagging does exactly what it sounds like, it tags each word in a sentence with the part of speech for that word. Knowing the part of speech of words in a sentence is important for understanding it. De nombreux autres logiciels peuvent fonctionner pour le français mais doivent être entraînés sur un corpus français pré-étiqueté : le French Treebank[3] ou le corpus Sequoia[4] peuvent être utilisés dans ce sens. Calculating Probabilities 3:38. Part of Speech Tagging As an initial review of parts of speech, if you need a refresher, the following Schoolhouse Rocks videos should get you squared away: A noun is a person, place, or thing. Part-of-Speech(POS) Tagging. Transformation-based learning (TBL) does not provide tag probabilities. Transformation based tagging is also called Brill tagging. In this step, we install NLTK module in Python. It draws the inspiration from both the previous explained taggers − rule-based and stochastic. Common English parts of speech are noun, verb, adjective, adverb, pronoun, preposition, conjunction, etc. This is where the statistical model comes in, which enables spaCy to make a prediction of which tag or label most likely applies in this context. In traditional grammar, a part of speech or part-of-speech (abbreviated as POS or PoS) is a category of words (or, more generally, of lexical items) that have similar grammatical properties. Even more impressive, it also labels by tense, and more. Part-of-speech tagging with spaCy Proceedings of the 12th international conference on Computational linguistics and intelligent text processing - Volume Part I, pp. Part-of-speech tagging with spaCy. Memory-based learning is a form of supervised learning based on similarity-based reasoning. It is also called n-gram approach. Smoothing and language modeling is defined explicitly in rule-based taggers. For example, a sequence of hidden coin tossing experiments is done and we see only the observation sequence consisting of heads and tails. It refers to the process of classifying words into their parts of speech (also known as words classes or lexical categories).