Several of the corpora included with NLTK have been tagged for their part-of-speech. Here's an example of what you might see if you opened a file from the Brown Corpus with a text editor:

>>> nltk.corpus.brown.tagged_words()
[('The', 'AT'), ('Fulton', 'NP-TL'), ...]
>>> nltk.corpus.brown.tagged_words(tagset='universal')
[('The', 'DET'), ('Fulton', 'NOUN'), ...]

>>> print(nltk.corpus.nps_chat.tagged_words())
[('now', 'RB'), ('im', 'PRP'), ('left', 'VBD'), ...]
>>> nltk.corpus.conll2000.tagged_words()
[('Confidence', 'NN'), ('in', 'IN'), ('the', 'DT'), ...]
>>> nltk.corpus.treebank.tagged_words()
[('Pierre', 'NNP'), ('Vinken', 'NNP'), (',', ','), ...]

>>> nltk.corpus.brown.tagged_words(tagset='universal')
[('The', 'DET'), ('Fulton', 'NOUN'), ...]
>>> nltk.corpus.treebank.tagged_words(tagset='universal')
[('Pierre', 'NOUN'), ('Vinken', 'NOUN'), (',', '.'), ...]

>>> nltk.corpus.sinica_treebank.tagged_words()
[('ä', 'Neu'), ('åæ', 'Nad'), ('åç', 'Nba'), ...]
>>> nltk.corpus.indian.tagged_words()
[('মহিষের', 'NN'), ('সন্তান', 'NN'), (':', 'SYM'), ...]
>>> nltk.corpus.mac_morpho.tagged_words()
[('Jersei', 'N'), ('atinge', 'V'), ('m\xe9dia', 'N'), ...]
>>> nltk.corpus.conll2002.tagged_words()
[('Sao', 'NC'), ('Paulo', 'VMI'), ('(', 'Fpa'), ...]
>>> nltk.corpus.cess_cat.tagged_words()
[('El', 'da0ms0'), ('Tribunal_Suprem', 'np0000o'), ...]

If your environment is set up correctly, with appropriate editors and fonts, you should be able to display individual strings in a human-readable way. For example, 2.1 shows data accessed using nltk.corpus.indian.

Figure 2.1: POS-Tagged Data from Four Indian Languages: Bangla, Hindi, Marathi, and Telugu

If the corpus is also segmented into sentences, it will have a tagged_sents() method that divides up the tagged words into sentences rather than presenting them as one big list. This will be useful when we come to developing automatic taggers, as they are trained and tested on lists of sentences, not words.

2.3   A Universal Part-of-Speech Tagset

Tagged corpora use many different conventions for tagging words. To help us get started, we will be looking at a simplified tagset (shown in 2.1).

Table 2.1:

Universal Part-of-Speech Tagset

Let's see which of these tags are the most common in the news category of the Brown corpus:

>>> from nltk.corpus import brown
>>> brown_news_tagged = brown.tagged_words(categories='news', tagset='universal')
>>> tag_fd = nltk.FreqDist(tag for (word, tag) in brown_news_tagged)
>>> tag_fd.most_common()
[('NOUN', 30640), ('VERB', 14399), ('ADP', 12355), ('.', 11928), ('DET', 11389),
 ('ADJ', 6706), ('ADV', 3349), ('CONJ', 2717), ('PRON', 2535), ('PRT', 2264),
 ('NUM', 2166), ('X', 106)]

We can use these tags to do powerful searches using a graphical POS-concordance tool nltk.app.concordance(). Use it to search for any combination of words and POS tags, e.g. N N N N, hit/VD, hit/VN, or the ADJ man.

2.4   Nouns

Nouns generally refer to people, places, things, or concepts, e.g.: woman, Scotland, book, intelligence. Nouns can appear after determiners and adjectives, and can be the subject or object of the verb, as shown in 2.2.

Table 2.2:

Syntactic Patterns involving some Nouns

The simplified noun tags are N for common nouns like book, and NP for proper nouns like Scotland.

Let's inspect some tagged text to see what parts of speech occur before a noun, with the most frequent ones first. To begin with, we construct a list of bigrams whose members are themselves word-tag pairs such as (('The', 'DET'), ('Fulton', 'NP')) and (('Fulton', 'NP'), ('County', 'N')). Then we construct a FreqDist from the tag parts of the bigrams.

>>> word_tag_pairs = nltk.bigrams(brown_news_tagged)
>>> noun_preceders = [a[1] for (a, b) in word_tag_pairs if b[1] == 'NOUN']
>>> fdist = nltk.FreqDist(noun_preceders)
>>> [tag for (tag, _) in fdist.most_common()]
['NOUN', 'DET', 'ADJ', 'ADP', '.', 'VERB', 'CONJ', 'NUM', 'ADV', 'PRT', 'PRON', 'X']

This confirms our assertion that nouns occur after determiners and adjectives, including numeral adjectives (tagged as NUM).

2.5   Verbs

Verbs are words that describe events and actions, e.g. fall, eat in 2.3. In the context of a sentence, verbs typically express a relation involving the referents of one or more noun phrases.

Table 2.3:

Syntactic Patterns involving some Verbs

What are the most common verbs in news text? Let's sort all the verbs by frequency:

>>> wsj = nltk.corpus.treebank.tagged_words(tagset='universal')
>>> word_tag_fd = nltk.FreqDist(wsj)
>>> [wt[0] for (wt, _) in word_tag_fd.most_common() if wt[1] == 'VERB']
['is', 'said', 'are', 'was', 'be', 'has', 'have', 'will', 'says', 'would',
 'were', 'had', 'been', 'could', "'s", 'can', 'do', 'say', 'make', 'may',
 'did', 'rose', 'made', 'does', 'expected', 'buy', 'take', 'get', 'might',
 'sell', 'added', 'sold', 'help', 'including', 'should', 'reported', ...]

Note that the items being counted in the frequency distribution are word-tag pairs. Since words and tags are paired, we can treat the word as a condition and the tag as an event, and initialize a conditional frequency distribution with a list of condition-event pairs. This lets us see a frequency-ordered list of tags given a word:

>>> cfd1 = nltk.ConditionalFreqDist(wsj)
>>> cfd1['yield'].most_common()
[('VERB', 28), ('NOUN', 20)]
>>> cfd1['cut'].most_common()
[('VERB', 25), ('NOUN', 3)]

We can reverse the order of the pairs, so that the tags are the conditions, and the words are the events. Now we can see likely words for a given tag. We will do this for the WSJ tagset rather than the universal tagset:

>>> wsj = nltk.corpus.treebank.tagged_words()
>>> cfd2 = nltk.ConditionalFreqDist((tag, word) for (word, tag) in wsj)
>>> list(cfd2['VBN'])
['been', 'expected', 'made', 'compared', 'based', 'priced', 'used', 'sold',
'named', 'designed', 'held', 'fined', 'taken', 'paid', 'traded', 'said', ...]

To clarify the distinction between VBD (past tense) and VBN (past participle), let's find words which can be both VBD and VBN, and see some surrounding text:

>>> [w for w in cfd1.conditions() if 'VBD' in cfd1[w] and 'VBN' in cfd1[w]]
['Asked', 'accelerated', 'accepted', 'accused', 'acquired', 'added', 'adopted', ...]
>>> idx1 = wsj.index(('kicked', 'VBD'))
>>> wsj[idx1-4:idx1+1]
[('While', 'IN'), ('program', 'NN'), ('trades', 'NNS'), ('swiftly', 'RB'),
 ('kicked', 'VBD')]
>>> idx2 = wsj.index(('kicked', 'VBN'))
>>> wsj[idx2-4:idx2+1]
[('head', 'NN'), ('of', 'IN'), ('state', 'NN'), ('has', 'VBZ'), ('kicked', 'VBN')]

In this case, we see that the past participle of kicked is preceded by a form of the auxiliary verb have. Is this generally true?

2.6   Adjectives and Adverbs

Two other important word classes are adjectives and adverbs. Adjectives describe nouns, and can be used as modifiers (e.g. large in the large pizza), or in predicates (e.g. the pizza is large). English adjectives can have internal structure (e.g. fall+ing in the falling stocks). Adverbs modify verbs to specify the time, manner, place or direction of the event described by the verb (e.g. quickly in the stocks fell quickly). Adverbs may also modify adjectives (e.g. really in Mary's teacher was really nice).

English has several categories of closed class words in addition to prepositions, such as articles (also often called determiners) (e.g., the, a), modals (e.g., should, may), and personal pronouns (e.g., she, they). Each dictionary and grammar classifies these words differently.

Let's find the most frequent nouns of each noun part-of-speech type. The program in 2.2 finds all tags starting with NN, and provides a few example words for each one. You will see that there are many variants of NN; the most important contain $ for possessive nouns, S for plural nouns (since plural nouns typically end in s) and P for proper nouns. In addition, most of the tags have suffix modifiers: -NC for citations, -HL for words in headlines and -TL for titles (a feature of Brown tabs).

def findtags(tag_prefix, tagged_text):
    cfd = nltk.ConditionalFreqDist((tag, word) for (word, tag) in tagged_text
                                  if tag.startswith(tag_prefix))
    return dict((tag, cfd[tag].most_common(5)) for tag in cfd.conditions())

>>> tagdict = findtags('NN', nltk.corpus.brown.tagged_words(categories='news'))
>>> for tag in sorted(tagdict):
...     print(tag, tagdict[tag])
...
NN [('year', 137), ('time', 97), ('state', 88), ('week', 85), ('man', 72)]
NN$ [("year's", 13), ("world's", 8), ("state's", 7), ("nation's", 6), ("company's", 6)]
NN$-HL [("Golf's", 1), ("Navy's", 1)]
NN$-TL [("President's", 11), ("Army's", 3), ("Gallery's", 3), ("University's", 3), ("League's", 3)]
NN-HL [('sp.', 2), ('problem', 2), ('Question', 2), ('business', 2), ('Salary', 2)]
NN-NC [('eva', 1), ('aya', 1), ('ova', 1)]
NN-TL [('President', 88), ('House', 68), ('State', 59), ('University', 42), ('City', 41)]
NN-TL-HL [('Fort', 2), ('Dr.', 1), ('Oak', 1), ('Street', 1), ('Basin', 1)]
NNS [('years', 101), ('members', 69), ('people', 52), ('sales', 51), ('men', 46)]
NNS$ [("children's", 7), ("women's", 5), ("janitors'", 3), ("men's", 3), ("taxpayers'", 2)]
NNS$-HL [("Dealers'", 1), ("Idols'", 1)]
NNS$-TL [("Women's", 4), ("States'", 3), ("Giants'", 2), ("Bros.'", 1), ("Writers'", 1)]
NNS-HL [('comments', 1), ('Offenses', 1), ('Sacrifices', 1), ('funds', 1), ('Results', 1)]
NNS-TL [('States', 38), ('Nations', 11), ('Masters', 10), ('Rules', 9), ('Communists', 9)]
NNS-TL-HL [('Nations', 1)]

When we come to constructing part-of-speech taggers later in this chapter, we will use the unsimplified tags.

2.8   Exploring Tagged Corpora

Let's briefly return to the kinds of exploration of corpora we saw in previous chapters, this time exploiting POS tags.

Suppose we're studying the word often and want to see how it is used in text. We could ask to see the words that follow often

>>> brown_learned_text = brown.words(categories='learned')
>>> sorted(set(b for (a, b) in nltk.bigrams(brown_learned_text) if a == 'often'))
[',', '.', 'accomplished', 'analytically', 'appear', 'apt', 'associated', 'assuming',
'became', 'become', 'been', 'began', 'call', 'called', 'carefully', 'chose', ...]

However, it's probably more instructive use the tagged_words() method to look at the part-of-speech tag of the following words:

>>> brown_lrnd_tagged = brown.tagged_words(categories='learned', tagset='universal')
>>> tags = [b[1] for (a, b) in nltk.bigrams(brown_lrnd_tagged) if a[0] == 'often']
>>> fd = nltk.FreqDist(tags)
>>> fd.tabulate()
 PRT  ADV  ADP    . VERB  ADJ
   2    8    7    4   37    6

Notice that the most high-frequency parts of speech following often are verbs. Nouns never appear in this position (in this particular corpus).

Next, let's look at some larger context, and find words involving particular sequences of tags and words (in this case "<Verb> to <Verb>"). In code-three-word-phrase we consider each three-word window in the sentence , and check if they meet our criterion . If the tags match, we print the corresponding words .

from nltk.corpus import brown
def process(sentence):
    for (w1,t1), (w2,t2), (w3,t3) in nltk.trigrams(sentence): 
        if (t1.startswith('V') and t2 == 'TO' and t3.startswith('V')): 
            print(w1, w2, w3) 

>>> for tagged_sent in brown.tagged_sents():
...     process(tagged_sent)
...
combined to achieve
continue to place
serve to protect
wanted to wait
allowed to place
expected to become
...

Finally, let's look for words that are highly ambiguous as to their part of speech tag. Understanding why such words are tagged as they are in each context can help us clarify the distinctions between the tags.

>>> brown_news_tagged = brown.tagged_words(categories='news', tagset='universal')
>>> data = nltk.ConditionalFreqDist((word.lower(), tag)
...                                 for (word, tag) in brown_news_tagged)
>>> for word in sorted(data.conditions()):
...     if len(data[word]) > 3:
...         tags = [tag for (tag, _) in data[word].most_common()]
...         print(word, ' '.join(tags))
...
best ADJ ADV NP V
better ADJ ADV V DET
close ADV ADJ V N
cut V N VN VD
even ADV DET ADJ V
grant NP N V -
hit V VD VN N
lay ADJ V NP VD
left VD ADJ N VN
like CNJ V ADJ P -
near P ADV ADJ DET
open ADJ V N ADV
past N ADJ DET P
present ADJ ADV V N
read V VN VD NP
right ADJ N DET ADV
second NUM ADV DET N
set VN V VD N -
that CNJ V WH DET

A text, as we have seen, is treated in Python as a list of words. An important property of lists is that we can "look up" a particular item by giving its index, e.g. text1[100]. Notice how we specify a number, and get back a word. We can think of a list as a simple kind of table, as shown in 3.1.

Figure 3.1: List Look-up: we access the contents of a Python list with the help of an integer index.

Contrast this situation with frequency distributions (3), where we specify a word, and get back a number, e.g. fdist['monstrous'], which tells us the number of times a given word has occurred in a text. Look-up using words is familiar to anyone who has used a dictionary. Some more examples are shown in 3.2.

Figure 3.2: Dictionary Look-up: we access the entry of a dictionary using a key such as someone's name, a web domain, or an English word; other names for dictionary are map, hashmap, hash, and associative array.

In the case of a phonebook, we look up an entry using a name, and get back a number. When we type a domain name in a web browser, the computer looks this up to get back an IP address. A word frequency table allows us to look up a word and find its frequency in a text collection. In all these cases, we are mapping from names to numbers, rather than the other way around as with a list. In general, we would like to be able to map between arbitrary types of information. 3.1 lists a variety of linguistic objects, along with what they map.

Table 3.1:

Linguistic Objects as Mappings from Keys to Values

Most often, we are mapping from a "word" to some structured object. For example, a document index maps from a word (which we can represent as a string), to a list of pages (represented as a list of integers). In this section, we will see how to represent such mappings in Python.

3.2   Dictionaries in Python

Python provides a dictionary data type that can be used for mapping between arbitrary types. It is like a conventional dictionary, in that it gives you an efficient way to look things up. However, as we see from 3.1, it has a much wider range of uses.

To illustrate, we define pos to be an empty dictionary and then add four entries to it, specifying the part-of-speech of some words. We add entries to a dictionary using the familiar square bracket notation:

>>> pos = {}
>>> pos
{}
>>> pos['colorless'] = 'ADJ' 
>>> pos
{'colorless': 'ADJ'}
>>> pos['ideas'] = 'N'
>>> pos['sleep'] = 'V'
>>> pos['furiously'] = 'ADV'
>>> pos 
{'furiously': 'ADV', 'ideas': 'N', 'colorless': 'ADJ', 'sleep': 'V'}

So, for example, says that the part-of-speech of colorless is adjective, or more specifically, that the key 'colorless' is assigned the value 'ADJ' in dictionary pos. When we inspect the value of pos we see a set of key-value pairs. Once we have populated the dictionary in this way, we can employ the keys to retrieve values:

>>> pos['ideas']
'N'
>>> pos['colorless']
'ADJ'

Of course, we might accidentally use a key that hasn't been assigned a value.

>>> pos['green']
Traceback (most recent call last):
  File "<stdin>", line 1, in ?
KeyError: 'green'

This raises an important question. Unlike lists and strings, where we can use len() to work out which integers will be legal indexes, how do we work out the legal keys for a dictionary? If the dictionary is not too big, we can simply inspect its contents by evaluating the variable pos. As we saw above (line ), this gives us the key-value pairs. Notice that they are not in the same order they were originally entered; this is because dictionaries are not sequences but mappings (cf. 3.2), and the keys are not inherently ordered.

Alternatively, to just find the keys, we can convert the dictionary to a list — or use the dictionary in a context where a list is expected, as the parameter of sorted() , or in a for loop .

>>> list(pos) 
['ideas', 'furiously', 'colorless', 'sleep']
>>> sorted(pos) 
['colorless', 'furiously', 'ideas', 'sleep']
>>> [w for w in pos if w.endswith('s')] 
['colorless', 'ideas']

As well as iterating over all keys in the dictionary with a for loop, we can use the for loop as we did for printing lists:

>>> for word in sorted(pos):
...     print(word + ":", pos[word])
...
colorless: ADJ
furiously: ADV
sleep: V
ideas: N

Finally, the dictionary methods keys(), values() and items() allow us to access the keys, values, and key-value pairs as separate lists. We can even sort tuples , which orders them according to their first element (and if the first elements are the same, it uses their second elements).

>>> list(pos.keys())
['colorless', 'furiously', 'sleep', 'ideas']
>>> list(pos.values())
['ADJ', 'ADV', 'V', 'N']
>>> list(pos.items())
[('colorless', 'ADJ'), ('furiously', 'ADV'), ('sleep', 'V'), ('ideas', 'N')]
>>> for key, val in sorted(pos.items()): 
...     print(key + ":", val)
...
colorless: ADJ
furiously: ADV
ideas: N
sleep: V

We want to be sure that when we look something up in a dictionary, we only get one value for each key. Now suppose we try to use a dictionary to store the fact that the word sleep can be used as both a verb and a noun:

>>> pos['sleep'] = 'V'
>>> pos['sleep']
'V'
>>> pos['sleep'] = 'N'
>>> pos['sleep']
'N'

Initially, pos['sleep'] is given the value 'V'. But this is immediately overwritten with the new value 'N'. In other words, there can only be one entry in the dictionary for 'sleep'. However, there is a way of storing multiple values in that entry: we use a list value, e.g. pos['sleep'] = ['N', 'V']. In fact, this is what we saw in 4 for the CMU Pronouncing Dictionary, which stores multiple pronunciations for a single word.

3.3   Defining Dictionaries

We can use the same key-value pair format to create a dictionary. There's a couple of ways to do this, and we will normally use the first:

>>> pos = {'colorless': 'ADJ', 'ideas': 'N', 'sleep': 'V', 'furiously': 'ADV'}
>>> pos = dict(colorless='ADJ', ideas='N', sleep='V', furiously='ADV')

Note that dictionary keys must be immutable types, such as strings and tuples. If we try to define a dictionary using a mutable key, we get a TypeError:

>>> pos = {['ideas', 'blogs', 'adventures']: 'N'}
Traceback (most recent call last):
  File "<stdin>", line 1, in <module>
TypeError: list objects are unhashable

3.4   Default Dictionaries

If we try to access a key that is not in a dictionary, we get an error. However, its often useful if a dictionary can automatically create an entry for this new key and give it a default value, such as zero or the empty list. For this reason, a special kind of dictionary called a defaultdict is available. In order to use it, we have to supply a parameter which can be used to create the default value, e.g. int, float, str, list, dict, tuple.

>>> from collections import defaultdict
>>> frequency = defaultdict(int)
>>> frequency['colorless'] = 4
>>> frequency['ideas']
0
>>> pos = defaultdict(list)
>>> pos['sleep'] = ['NOUN', 'VERB']
>>> pos['ideas']
[]

The above examples specified the default value of a dictionary entry to be the default value of a particular data type. However, we can specify any default value we like, simply by providing the name of a function that can be called with no arguments to create the required value. Let's return to our part-of-speech example, and create a dictionary whose default value for any entry is 'N' . When we access a non-existent entry , it is automatically added to the dictionary .

>>> pos = defaultdict(lambda: 'NOUN') 
>>> pos['colorless'] = 'ADJ'
>>> pos['blog'] 
'NOUN'
>>> list(pos.items())
[('blog', 'NOUN'), ('colorless', 'ADJ')] # [_automatically-added]

>>> f = lambda: 'NOUN'
>>> f()
'NOUN'
>>> def g():
...     return 'NOUN'
>>> g()
'NOUN'

Let's see how default dictionaries could be used in a more substantial language processing task. Many language processing tasks — including tagging — struggle to correctly process the hapaxes of a text. They can perform better with a fixed vocabulary and a guarantee that no new words will appear. We can preprocess a text to replace low-frequency words with a special "out of vocabulary" token UNK, with the help of a default dictionary. (Can you work out how to do this without reading on?)

We need to create a default dictionary that maps each word to its replacement. The most frequent n words will be mapped to themselves. Everything else will be mapped to UNK.

>>> alice = nltk.corpus.gutenberg.words('carroll-alice.txt')
>>> vocab = nltk.FreqDist(alice)
>>> v1000 = [word for (word, _) in vocab.most_common(1000)]
>>> mapping = defaultdict(lambda: 'UNK')
>>> for v in v1000:
...     mapping[v] = v
...
>>> alice2 = [mapping[v] for v in alice]
>>> alice2[:100]
['UNK', 'Alice', "'", 's', 'UNK', 'in', 'UNK', 'by', 'UNK', 'UNK', 'UNK',
'UNK', 'CHAPTER', 'I', '.', 'UNK', 'the', 'Rabbit', '-', 'UNK', 'Alice',
'was', 'beginning', 'to', 'get', 'very', 'tired', 'of', 'sitting', 'by',
'her', 'sister', 'on', 'the', 'UNK', ',', 'and', 'of', 'having', 'nothing',
'to', 'do', ':', 'once', 'or', 'twice', 'she', 'had', 'UNK', 'into', 'the',
'book', 'her', 'sister', 'was', 'UNK', ',', 'but', 'it', 'had', 'no',
'pictures', 'or', 'UNK', 'in', 'it', ',', "'", 'and', 'what', 'is', 'the',
'use', 'of', 'a', 'book', ",'", 'thought', 'Alice', "'", 'without',
'pictures', 'or', 'conversation', "?'" ...]
>>> len(set(alice2))
1001

3.5   Incrementally Updating a Dictionary

We can employ dictionaries to count occurrences, emulating the method for tallying words shown in fig-tally. We begin by initializing an empty defaultdict, then process each part-of-speech tag in the text. If the tag hasn't been seen before, it will have a zero count by default. Each time we encounter a tag, we increment its count using the += operator.

>>> from collections import defaultdict
>>> counts = defaultdict(int)
>>> from nltk.corpus import brown
>>> for (word, tag) in brown.tagged_words(categories='news', tagset='universal'):
...     counts[tag] += 1
...
>>> counts['NOUN']
30640
>>> sorted(counts)
['ADJ', 'PRT', 'ADV', 'X', 'CONJ', 'PRON', 'VERB', '.', 'NUM', 'NOUN', 'ADP', 'DET']

>>> from operator import itemgetter
>>> sorted(counts.items(), key=itemgetter(1), reverse=True)
[('NOUN', 30640), ('VERB', 14399), ('ADP', 12355), ('.', 11928), ...]
>>> [t for t, c in sorted(counts.items(), key=itemgetter(1), reverse=True)]
['NOUN', 'VERB', 'ADP', '.', 'DET', 'ADJ', 'ADV', 'CONJ', 'PRON', 'PRT', 'NUM', 'X']

The listing in 3.3 illustrates an important idiom for sorting a dictionary by its values, to show words in decreasing order of frequency. The first parameter of sorted() is the items to sort, a list of tuples consisting of a POS tag and a frequency. The second parameter specifies the sort key using a function itemgetter(). In general, itemgetter(n) returns a function that can be called on some other sequence object to obtain the nth element, e.g.:

>>> pair = ('NP', 8336)
>>> pair[1]
8336
>>> itemgetter(1)(pair)
8336

The last parameter of sorted() specifies that the items should be returned in reverse order, i.e. decreasing values of frequency.

There's a second useful programming idiom at the beginning of 3.3, where we initialize a defaultdict and then use a for loop to update its values. Here's a schematic version:

Here's another instance of this pattern, where we index words according to their last two letters:

>>> last_letters = defaultdict(list)
>>> words = nltk.corpus.words.words('en')
>>> for word in words:
...     key = word[-2:]
...     last_letters[key].append(word)
...
>>> last_letters['ly']
['abactinally', 'abandonedly', 'abasedly', 'abashedly', 'abashlessly', 'abbreviately',
'abdominally', 'abhorrently', 'abidingly', 'abiogenetically', 'abiologically', ...]
>>> last_letters['zy']
['blazy', 'bleezy', 'blowzy', 'boozy', 'breezy', 'bronzy', 'buzzy', 'Chazy', ...]

The following example uses the same pattern to create an anagram dictionary. (You might experiment with the third line to get an idea of why this program works.)

>>> anagrams = defaultdict(list)
>>> for word in words:
...     key = ''.join(sorted(word))
...     anagrams[key].append(word)
...
>>> anagrams['aeilnrt']
['entrail', 'latrine', 'ratline', 'reliant', 'retinal', 'trenail']

Since accumulating words like this is such a common task, NLTK provides a more convenient way of creating a defaultdict(list), in the form of nltk.Index().

>>> anagrams = nltk.Index((''.join(sorted(w)), w) for w in words)
>>> anagrams['aeilnrt']
['entrail', 'latrine', 'ratline', 'reliant', 'retinal', 'trenail']

3.6   Complex Keys and Values

We can use default dictionaries with complex keys and values. Let's study the range of possible tags for a word, given the word itself, and the tag of the previous word. We will see how this information can be used by a POS tagger.

>>> pos = defaultdict(lambda: defaultdict(int))
>>> brown_news_tagged = brown.tagged_words(categories='news', tagset='universal')
>>> for ((w1, t1), (w2, t2)) in nltk.bigrams(brown_news_tagged): 
...     pos[(t1, w2)][t2] += 1 
...
>>> pos[('DET', 'right')] 
defaultdict(<class 'int'>, {'ADJ': 11, 'NOUN': 5})

This example uses a dictionary whose default value for an entry is a dictionary (whose default value is int(), i.e. zero). Notice how we iterated over the bigrams of the tagged corpus, processing a pair of word-tag pairs for each iteration . Each time through the loop we updated our pos dictionary's entry for (t1, w2), a tag and its following word . When we look up an item in pos we must specify a compound key , and we get back a dictionary object. A POS tagger could use such information to decide that the word right, when preceded by a determiner, should be tagged as ADJ.

3.7   Inverting a Dictionary

Dictionaries support efficient lookup, so long as you want to get the value for any key. If d is a dictionary and k is a key, we type d[k] and immediately obtain the value. Finding a key given a value is slower and more cumbersome:

>>> counts = defaultdict(int)
>>> for word in nltk.corpus.gutenberg.words('milton-paradise.txt'):
...     counts[word] += 1
...
>>> [key for (key, value) in counts.items() if value == 32]
['brought', 'Him', 'virtue', 'Against', 'There', 'thine', 'King', 'mortal',
'every', 'been']

If we expect to do this kind of "reverse lookup" often, it helps to construct a dictionary that maps values to keys. In the case that no two keys have the same value, this is an easy thing to do. We just get all the key-value pairs in the dictionary, and create a new dictionary of value-key pairs. The next example also illustrates another way of initializing a dictionary pos with key-value pairs.

>>> pos = {'colorless': 'ADJ', 'ideas': 'N', 'sleep': 'V', 'furiously': 'ADV'}
>>> pos2 = dict((value, key) for (key, value) in pos.items())
>>> pos2['N']
'ideas'

Let's first make our part-of-speech dictionary a bit more realistic and add some more words to pos using the dictionary update() method, to create the situation where multiple keys have the same value. Then the technique just shown for reverse lookup will no longer work (why not?). Instead, we have to use append() to accumulate the words for each part-of-speech, as follows:

>>> pos.update({'cats': 'N', 'scratch': 'V', 'peacefully': 'ADV', 'old': 'ADJ'})
>>> pos2 = defaultdict(list)
>>> for key, value in pos.items():
...     pos2[value].append(key)
...
>>> pos2['ADV']
['peacefully', 'furiously']

Now we have inverted the pos dictionary, and can look up any part-of-speech and find all words having that part-of-speech. We can do the same thing even more simply using NLTK's support for indexing as follows:

>>> pos2 = nltk.Index((value, key) for (key, value) in pos.items())
>>> pos2['ADV']
['peacefully', 'furiously']

A summary of Python's dictionary methods is given in 3.2.

Table 3.2:

Python's Dictionary Methods: A summary of commonly-used methods and idioms involving dictionaries.

4.1   The Default Tagger

The simplest possible tagger assigns the same tag to each token. This may seem to be a rather banal step, but it establishes an important baseline for tagger performance. In order to get the best result, we tag each word with the most likely tag. Let's find out which tag is most likely (now using the unsimplified tagset):

>>> tags = [tag for (word, tag) in brown.tagged_words(categories='news')]
>>> nltk.FreqDist(tags).max()
'NN'

Now we can create a tagger that tags everything as NN.

>>> raw = 'I do not like green eggs and ham, I do not like them Sam I am!'
>>> tokens = word_tokenize(raw)
>>> default_tagger = nltk.DefaultTagger('NN')
>>> default_tagger.tag(tokens)
[('I', 'NN'), ('do', 'NN'), ('not', 'NN'), ('like', 'NN'), ('green', 'NN'),
('eggs', 'NN'), ('and', 'NN'), ('ham', 'NN'), (',', 'NN'), ('I', 'NN'),
('do', 'NN'), ('not', 'NN'), ('like', 'NN'), ('them', 'NN'), ('Sam', 'NN'),
('I', 'NN'), ('am', 'NN'), ('!', 'NN')]

Unsurprisingly, this method performs rather poorly. On a typical corpus, it will tag only about an eighth of the tokens correctly, as we see below:

>>> default_tagger.evaluate(brown_tagged_sents)
0.13089484257215028

Default taggers assign their tag to every single word, even words that have never been encountered before. As it happens, once we have processed several thousand words of English text, most new words will be nouns. As we will see, this means that default taggers can help to improve the robustness of a language processing system. We will return to them shortly.

4.2   The Regular Expression Tagger

The regular expression tagger assigns tags to tokens on the basis of matching patterns. For instance, we might guess that any word ending in ed is the past participle of a verb, and any word ending with 's is a possessive noun. We can express these as a list of regular expressions:

>>> patterns = [
...     (r'.*ing$', 'VBG'),               # gerunds
...     (r'.*ed$', 'VBD'),                # simple past
...     (r'.*es$', 'VBZ'),                # 3rd singular present
...     (r'.*ould$', 'MD'),               # modals
...     (r'.*\'s$', 'NN$'),               # possessive nouns
...     (r'.*s$', 'NNS'),                 # plural nouns
...     (r'^-?[0-9]+(.[0-9]+)?$', 'CD'),  # cardinal numbers
...     (r'.*', 'NN')                     # nouns (default)
... ]

Note that these are processed in order, and the first one that matches is applied. Now we can set up a tagger and use it to tag a sentence. Now its right about a fifth of the time.

>>> regexp_tagger = nltk.RegexpTagger(patterns)
>>> regexp_tagger.tag(brown_sents[3])
[('``', 'NN'), ('Only', 'NN'), ('a', 'NN'), ('relative', 'NN'), ('handful', 'NN'),
('of', 'NN'), ('such', 'NN'), ('reports', 'NNS'), ('was', 'NNS'), ('received', 'VBD'),
("''", 'NN'), (',', 'NN'), ('the', 'NN'), ('jury', 'NN'), ('said', 'NN'), (',', 'NN'),
('``', 'NN'), ('considering', 'VBG'), ('the', 'NN'), ('widespread', 'NN'), ...]
>>> regexp_tagger.evaluate(brown_tagged_sents)
0.20326391789486245

The final regular expression «.*» is a catch-all that tags everything as a noun. This is equivalent to the default tagger (only much less efficient). Instead of re-specifying this as part of the regular expression tagger, is there a way to combine this tagger with the default tagger? We will see how to do this shortly.

4.3   The Lookup Tagger

A lot of high-frequency words do not have the NN tag. Let's find the hundred most frequent words and store their most likely tag. We can then use this information as the model for a "lookup tagger" (an NLTK UnigramTagger):

>>> fd = nltk.FreqDist(brown.words(categories='news'))
>>> cfd = nltk.ConditionalFreqDist(brown.tagged_words(categories='news'))
>>> most_freq_words = fd.most_common(100)
>>> likely_tags = dict((word, cfd[word].max()) for (word, _) in most_freq_words)
>>> baseline_tagger = nltk.UnigramTagger(model=likely_tags)
>>> baseline_tagger.evaluate(brown_tagged_sents)
0.45578495136941344

It should come as no surprise by now that simply knowing the tags for the 100 most frequent words enables us to tag a large fraction of tokens correctly (nearly half in fact). Let's see what it does on some untagged input text:

>>> sent = brown.sents(categories='news')[3]
>>> baseline_tagger.tag(sent)
[('``', '``'), ('Only', None), ('a', 'AT'), ('relative', None),
('handful', None), ('of', 'IN'), ('such', None), ('reports', None),
('was', 'BEDZ'), ('received', None), ("''", "''"), (',', ','),
('the', 'AT'), ('jury', None), ('said', 'VBD'), (',', ','),
('``', '``'), ('considering', None), ('the', 'AT'), ('widespread', None),
('interest', None), ('in', 'IN'), ('the', 'AT'), ('election', None),
(',', ','), ('the', 'AT'), ('number', None), ('of', 'IN'),
('voters', None), ('and', 'CC'), ('the', 'AT'), ('size', None),
('of', 'IN'), ('this', 'DT'), ('city', None), ("''", "''"), ('.', '.')]

Many words have been assigned a tag of None, because they were not among the 100 most frequent words. In these cases we would like to assign the default tag of NN. In other words, we want to use the lookup table first, and if it is unable to assign a tag, then use the default tagger, a process known as backoff (5). We do this by specifying one tagger as a parameter to the other, as shown below. Now the lookup tagger will only store word-tag pairs for words other than nouns, and whenever it cannot assign a tag to a word it will invoke the default tagger.

>>> baseline_tagger = nltk.UnigramTagger(model=likely_tags,
...                                      backoff=nltk.DefaultTagger('NN'))

Let's put all this together and write a program to create and evaluate lookup taggers having a range of sizes, in 4.1.

def performance(cfd, wordlist):
    lt = dict((word, cfd[word].max()) for word in wordlist)
    baseline_tagger = nltk.UnigramTagger(model=lt, backoff=nltk.DefaultTagger('NN'))
    return baseline_tagger.evaluate(brown.tagged_sents(categories='news'))

def display():
    import pylab
    word_freqs = nltk.FreqDist(brown.words(categories='news')).most_common()
    words_by_freq = [w for (w, _) in word_freqs]
    cfd = nltk.ConditionalFreqDist(brown.tagged_words(categories='news'))
    sizes = 2 ** pylab.arange(15)
    perfs = [performance(cfd, words_by_freq[:size]) for size in sizes]
    pylab.plot(sizes, perfs, '-bo')
    pylab.title('Lookup Tagger Performance with Varying Model Size')
    pylab.xlabel('Model Size')
    pylab.ylabel('Performance')
    pylab.show()

>>> display()                                  

Figure 4.2: Lookup Tagger

Observe that performance initially increases rapidly as the model size grows, eventually reaching a plateau, when large increases in model size yield little improvement in performance. (This example used the pylab plotting package, discussed in 4.8.)

4.4   Evaluation

In the above examples, you will have noticed an emphasis on accuracy scores. In fact, evaluating the performance of such tools is a central theme in NLP. Recall the processing pipeline in fig-sds; any errors in the output of one module are greatly multiplied in the downstream modules.

We evaluate the performance of a tagger relative to the tags a human expert would assign. Since we don't usually have access to an expert and impartial human judge, we make do instead with gold standard test data. This is a corpus which has been manually annotated and which is accepted as a standard against which the guesses of an automatic system are assessed. The tagger is regarded as being correct if the tag it guesses for a given word is the same as the gold standard tag.

5.1   Unigram Tagging

Unigram taggers are based on a simple statistical algorithm: for each token, assign the tag that is most likely for that particular token. For example, it will assign the tag JJ to any occurrence of the word frequent, since frequent is used as an adjective (e.g. a frequent word) more often than it is used as a verb (e.g. I frequent this cafe). A unigram tagger behaves just like a lookup tagger (4), except there is a more convenient technique for setting it up, called training. In the following code sample, we train a unigram tagger, use it to tag a sentence, then evaluate:

>>> from nltk.corpus import brown
>>> brown_tagged_sents = brown.tagged_sents(categories='news')
>>> brown_sents = brown.sents(categories='news')
>>> unigram_tagger = nltk.UnigramTagger(brown_tagged_sents)
>>> unigram_tagger.tag(brown_sents[2007])
[('Various', 'JJ'), ('of', 'IN'), ('the', 'AT'), ('apartments', 'NNS'),
('are', 'BER'), ('of', 'IN'), ('the', 'AT'), ('terrace', 'NN'), ('type', 'NN'),
(',', ','), ('being', 'BEG'), ('on', 'IN'), ('the', 'AT'), ('ground', 'NN'),
('floor', 'NN'), ('so', 'QL'), ('that', 'CS'), ('entrance', 'NN'), ('is', 'BEZ'),
('direct', 'JJ'), ('.', '.')]
>>> unigram_tagger.evaluate(brown_tagged_sents)
0.9349006503968017

We train a UnigramTagger by specifying tagged sentence data as a parameter when we initialize the tagger. The training process involves inspecting the tag of each word and storing the most likely tag for any word in a dictionary, stored inside the tagger.

An n-gram tagger is a generalization of a unigram tagger whose context is the current word together with the part-of-speech tags of the n-1 preceding tokens, as shown in 5.1. The tag to be chosen, t_n, is circled, and the context is shaded in grey. In the example of an n-gram tagger shown in 5.1, we have n=3; that is, we consider the tags of the two preceding words in addition to the current word. An n-gram tagger picks the tag that is most likely in the given context.

Figure 5.1: Tagger Context

The NgramTagger class uses a tagged training corpus to determine which part-of-speech tag is most likely for each context. Here we see a special case of an n-gram tagger, namely a bigram tagger. First we train it, then use it to tag untagged sentences:

>>> bigram_tagger = nltk.BigramTagger(train_sents)
>>> bigram_tagger.tag(brown_sents[2007])
[('Various', 'JJ'), ('of', 'IN'), ('the', 'AT'), ('apartments', 'NNS'),
('are', 'BER'), ('of', 'IN'), ('the', 'AT'), ('terrace', 'NN'),
('type', 'NN'), (',', ','), ('being', 'BEG'), ('on', 'IN'), ('the', 'AT'),
('ground', 'NN'), ('floor', 'NN'), ('so', 'CS'), ('that', 'CS'),
('entrance', 'NN'), ('is', 'BEZ'), ('direct', 'JJ'), ('.', '.')]
>>> unseen_sent = brown_sents[4203]
>>> bigram_tagger.tag(unseen_sent)
[('The', 'AT'), ('population', 'NN'), ('of', 'IN'), ('the', 'AT'), ('Congo', 'NP'),
('is', 'BEZ'), ('13.5', None), ('million', None), (',', None), ('divided', None),
('into', None), ('at', None), ('least', None), ('seven', None), ('major', None),
('``', None), ('culture', None), ('clusters', None), ("''", None), ('and', None),
('innumerable', None), ('tribes', None), ('speaking', None), ('400', None),
('separate', None), ('dialects', None), ('.', None)]

Notice that the bigram tagger manages to tag every word in a sentence it saw during training, but does badly on an unseen sentence. As soon as it encounters a new word (i.e., 13.5), it is unable to assign a tag. It cannot tag the following word (i.e., million) even if it was seen during training, simply because it never saw it during training with a None tag on the previous word. Consequently, the tagger fails to tag the rest of the sentence. Its overall accuracy score is very low:

>>> bigram_tagger.evaluate(test_sents)
0.102063...

As n gets larger, the specificity of the contexts increases, as does the chance that the data we wish to tag contains contexts that were not present in the training data. This is known as the sparse data problem, and is quite pervasive in NLP. As a consequence, there is a trade-off between the accuracy and the coverage of our results (and this is related to the precision/recall trade-off in information retrieval).

Our approach to tagging unknown words still uses backoff to a regular-expression tagger or a default tagger. These are unable to make use of context. Thus, if our tagger encountered the word blog, not seen during training, it would assign it the same tag, regardless of whether this word appeared in the context the blog or to blog. How can we do better with these unknown words, or out-of-vocabulary items?

A useful method to tag unknown words based on context is to limit the vocabulary of a tagger to the most frequent n words, and to replace every other word with a special word UNK using the method shown in 3. During training, a unigram tagger will probably learn that UNK is usually a noun. However, the n-gram taggers will detect contexts in which it has some other tag. For example, if the preceding word is to (tagged TO), then UNK will probably be tagged as a verb.

5.6   Storing Taggers

Training a tagger on a large corpus may take a significant time. Instead of training a tagger every time we need one, it is convenient to save a trained tagger in a file for later re-use. Let's save our tagger t2 to a file t2.pkl.

>>> from pickle import dump
>>> output = open('t2.pkl', 'wb')
>>> dump(t2, output, -1)
>>> output.close()

Now, in a separate Python process, we can load our saved tagger.

>>> from pickle import load
>>> input = open('t2.pkl', 'rb')
>>> tagger = load(input)
>>> input.close()

Now let's check that it can be used for tagging.

>>> text = """The board's action shows what free enterprise
...     is up against in our complex maze of regulatory laws ."""
>>> tokens = text.split()
>>> tagger.tag(tokens)
[('The', 'AT'), ("board's", 'NN$'), ('action', 'NN'), ('shows', 'NNS'),
('what', 'WDT'), ('free', 'JJ'), ('enterprise', 'NN'), ('is', 'BEZ'),
('up', 'RP'), ('against', 'IN'), ('in', 'IN'), ('our', 'PP$'), ('complex', 'JJ'),
('maze', 'NN'), ('of', 'IN'), ('regulatory', 'NN'), ('laws', 'NNS'), ('.', '.')]

5.7   Performance Limitations

What is the upper limit to the performance of an n-gram tagger? Consider the case of a trigram tagger. How many cases of part-of-speech ambiguity does it encounter? We can determine the answer to this question empirically:

>>> cfd = nltk.ConditionalFreqDist(
...            ((x[1], y[1], z[0]), z[1])
...            for sent in brown_tagged_sents
...            for x, y, z in nltk.trigrams(sent))
>>> ambiguous_contexts = [c for c in cfd.conditions() if len(cfd[c]) > 1]
>>> sum(cfd[c].N() for c in ambiguous_contexts) / cfd.N()
0.049297702068029296

Thus, one out of twenty trigrams is ambiguous [EXAMPLES]. Given the current word and the previous two tags, in 5% of cases there is more than one tag that could be legitimately assigned to the current word according to the training data. Assuming we always pick the most likely tag in such ambiguous contexts, we can derive a lower bound on the performance of a trigram tagger.

Another way to investigate the performance of a tagger is to study its mistakes. Some tags may be harder than others to assign, and it might be possible to treat them specially by pre- or post-processing the data. A convenient way to look at tagging errors is the confusion matrix. It charts expected tags (the gold standard) against actual tags generated by a tagger:

>>> test_tags = [tag for sent in brown.sents(categories='editorial')
...                  for (word, tag) in t2.tag(sent)]
>>> gold_tags = [tag for (word, tag) in brown.tagged_words(categories='editorial')]
>>> print(nltk.ConfusionMatrix(gold_tags, test_tags))           

We have seen that ambiguity in the training data leads to an upper limit in tagger performance. Sometimes more context will resolve the ambiguity. In other cases however, as noted by (Church, Young, & Bloothooft, 1996), the ambiguity can only be resolved with reference to syntax, or to world knowledge. Despite these imperfections, part-of-speech tagging has played a central role in the rise of statistical approaches to natural language processing. In the early 1990s, the surprising accuracy of statistical taggers was a striking demonstration that it was possible to solve one small part of the language understanding problem, namely part-of-speech disambiguation, without reference to deeper sources of linguistic knowledge. Can this idea be pushed further? In 7., we shall see that it can.

7.1   Morphological Clues

The internal structure of a word may give useful clues as to the word's category. For example, -ness is a suffix that combines with an adjective to produce a noun, e.g. happy → happiness, ill → illness. So if we encounter a word that ends in -ness, this is very likely to be a noun. Similarly, -ment is a suffix that combines with some verbs to produce a noun, e.g. govern → government and establish → establishment.

English verbs can also be morphologically complex. For instance, the present participle of a verb ends in -ing, and expresses the idea of ongoing, incomplete action (e.g. falling, eating). The -ing suffix also appears on nouns derived from verbs, e.g. the falling of the leaves (this is known as the gerund).

All languages acquire new lexical items. A list of words recently added to the Oxford Dictionary of English includes cyberslacker, fatoush, blamestorm, SARS, cantopop, bupkis, noughties, muggle, and robata. Notice that all these new words are nouns, and this is reflected in calling nouns an open class. By contrast, prepositions are regarded as a closed class. That is, there is a limited set of words belonging to the class (e.g., above, along, at, below, beside, between, during, for, from, in, near, on, outside, over, past, through, towards, under, up, with), and membership of the set only changes very gradually over time.

Common tagsets often capture some morpho-syntactic information; that is, information about the kind of morphological markings that words receive by virtue of their syntactic role. Consider, for example, the selection of distinct grammatical forms of the word go illustrated in the following sentences:

We can easily imagine a tagset in which the four distinct grammatical forms just discussed were all tagged as VB. Although this would be adequate for some purposes, a more fine-grained tagset provides useful information about these forms that can help other processors that try to detect patterns in tag sequences. The Brown tagset captures these distinctions, as summarized in 7.1.

Table 7.1:

Some morphosyntactic distinctions in the Brown tagset

In addition to this set of verb tags, the various forms of the verb to be have special tags: be/BE, being/BEG, am/BEM, are/BER, is/BEZ, been/BEN, were/BED and was/BEDZ (plus extra tags for negative forms of the verb). All told, this fine-grained tagging of verbs means that an automatic tagger that uses this tagset is effectively carrying out a limited amount of morphological analysis.