Part-of-Speech Tagging › The Ambiguity Problem
Language AI HandbookAll chapters Part-of-Speech Tagging › The Ambiguity ProblemOne section · Sections in this chapter4 / 18 ↓
Reading tools Definitions & inline links
Choose your expertise level to adjust how many terms are explained. Beginners see more tooltips, experts see fewer to maintain reading flow. Hover over underlined terms for instant definitions.
Article links
Make inline references clickable
The reason POS tagging is non-trivial is lexical ambiguity: most common words in English can function as more than one part of speech. The word "run" appears as VB in "I run every morning," VBZ in "She runs marathons," VBD in "He ran yesterday," VBN in "I have run before," and NN in "That was a good run." Selecting the correct tag requires examining the surrounding context.
# Ambiguous words and their possible tags with contexts
ambiguous_words = {
"light": {
"JJ": "We need a light snack before the concert.",
"NN": "The light at the end of the tunnel was faint.",
"VB": "Please light the candle for me.",
},
"book": {
"NN": "The book was fascinating from start to finish.",
"VB": "I need to book a flight to Paris.",
"VBP": "We book flights months in advance.",
},
"can": {
"MD": "She can swim across the lake.",
"NN": "Open the can and pour the soup.",
"VB": "They can vegetables in autumn.",
},
"fast": {
"JJ": "She is a fast runner.",
"RB": "He drove fast around the corner.",
"VB": "Many people fast during religious observances.",
"NN": "The fast lasted three days.",
},
}Lexical Ambiguity Examples ================================================================= 'light' (3 possible tags): JJ We need a [light] snack before the concert. NN The [light] at the end of the tunnel was faint. VB Please [light] the candle for me. 'book' (3 possible tags): NN The [book] was fascinating from start to finish. VB I need to [book] a flight to Paris. VBP We [book] flights months in advance. 'can' (3 possible tags): MD She [can] swim across the lake. NN Open the [can] and pour the soup. VB They [can] vegetables in autumn. 'fast' (4 possible tags): JJ She is a [fast] runner. RB He drove [fast] around the corner. VB Many people [fast] during religious observances. NN The [fast] lasted three days.
Research on large corpora shows that roughly 40% of word types in English are ambiguous, but because ambiguous words tend to be common words (like "can," "will," "run," "light"), they account for an even higher fraction of tokens. This means a POS tagger that always picks the most frequent tag for each word will still make mistakes on a significant portion of all words it encounters.
The key statistical insight is that while individual words are ambiguous, most contexts strongly constrain the correct tag. The word "light" after "the" is almost certainly an adjective or noun, not a verb. After a pronoun like "please," it is almost certainly a verb. Context resolves most ambiguity.
Why Ambiguity Is Harder Than It Looks
The scale of lexical ambiguity in English is worth dwelling on. The 40% figure for ambiguous word types is striking, but the distribution is highly skewed. The most common 100 words in English, which account for roughly half of all tokens in typical text, include words like "will," "that," "can," "right," "even," "about," "over," "just," "back," "still," "set," "run," "leave," "play," and "watch." Almost all of these can function as multiple parts of speech. These are the words a tagger encounters most often, and they are also the hardest to tag correctly.
The difficulty compounds because ambiguous words often cluster in the same sentences. Consider "Can you leave the light on and book a table?" Every content word in this sentence is ambiguous: "can" is a modal or a noun, "leave" is a verb or an adjective, "light" is a noun or an adjective, "book" is a verb or a noun, and "table" is a noun or a verb. The correct reading requires parsing the entire sentence structure, not just examining individual tokens.
The good news for tagger developers is that although ambiguous words are frequent, the correct reading in context is usually predictable. In a large corpus of annotated English text, approximately 97% of tokens can be tagged correctly by a tagger that knows only the word identity plus the identity of the one preceding word and the one following word. The residual 3% represents hard cases where longer-range context or world knowledge is required.
Types of Ambiguity
Not all ambiguity is created equal. It helps to distinguish several types:
Local ambiguity: The ambiguity can be resolved by looking at immediately adjacent words. The word "can" after "I" and before "swim" is almost certainly a modal. A simple bigram model resolves this.
Non-local ambiguity: Resolution requires context further away in the sentence. "The horse raced past the barn fell" is a garden-path sentence where "raced" initially looks like the main verb but is a reduced relative clause modifier. Resolving this requires recognizing the clause structure across the whole sentence.
Structural ambiguity: The ambiguity arises from multiple ways of attaching a phrase, not just from the word's category. "I saw the man with the telescope" is ambiguous between two readings of where the prepositional phrase attaches, and this structural ambiguity affects the POS interpretation of intermediate nodes.
Annotation ambiguity: Some tokens are underdetermined even for human experts. Linguistic guidelines sometimes resolve these by convention rather than principle, which means different annotation projects make different choices and taggers trained on those projects will disagree.
Understanding these types matters practically: local ambiguity is easy to resolve with context windows, non-local and structural ambiguity requires sequence-level modeling, and annotation ambiguity sets an irreducible ceiling on tagger accuracy.