word | sentence | In obsolete terms the difference between word and sentenceis that word is a proverb or motto while sentence is to utter sententiously. As nouns the difference between word and sentenceis that word is the smallest unit of language which has a particular meaning and can be expressed by itself; the smallest discrete, meaningful unit of language. Contrast morpheme while sentence is sense; meaning; significance. As verbs the difference between word and sentenceis that word is to say or write (something) using particular words; to phrase (something) while sentence is to declare a sentence on a convicted person; to doom; to condemn to punishment. As an interjection wordis truth, indeed, to tell or speak the truth; the shortened form of the statement, «My word is my bond,» an expression eventually shortened to «Word is bond,» before it finally got cut to just «Word,» which is its most commonly used form. Other Comparisons: What’s the difference?
|
Introduction
When we think of functions, we automatically assume math and numbers. In fact, in Racket and any other functional programming language, we can have functions that manipulate non-numerical values.
Words
Let’s say you defined a procedure called square
:
(define (square x) (* x x))
But later wanted to access the actual word 'square
instead of the procedure, we would simply type 'square
(single quotation mark followed by the word square) to get the literal word. Notice how you do not need parentheses around the expression if you working with just a single word.
Sentences
Sentences are just a collection of words grouped together with parentheses. To create a sentence, you need need one quotation outside the parentheses, like this '(hi hey hello)
. Try practicing a bit by writing one or two words and sentences.
Test Your Understanding
Try each of the following in the Racket interpreter.
'61AS
'(I love 61AS!)
('I 'love '61AS!)
quote
The '
you saw in the above sections is actually an abbreviation for a function called quote
. This means that:
'x
is equivalent to(quote x)
'(hi hey hello)
is equivalent to(quote (hi hey hello))
quote
is different from most other procedures in that it does not evaluate its argument. Functions that exhibit this type of behavior are special forms. You do not need to understand special forms for now; we will go more in depth on this topic in a later subsection. For now, it will suffice to know that quote
is a function that takes in one argument and returns it as a word or sentence. Take the following example:
-> (define x 4)
x
-> x
4
-> (quote x)
x
-> 'x
x
Since quote
is used quite often, it is given the abbreviation '
, a single quotation mark. Remember that, although it may seem this way in its abbreviated form, quote
is simply a function that can be called like any other function in Racket.
Word and Sentence Selectors
When working with words and sentences, it would help to have procedures that manipulate them. The procedures themselves are simple. Combining them correctly to accomplish your goal is going to the hard part. For now, here is a list of procedures you can use to select data from words or sentences.
first
first
takes in a word and returns the first letter of the word, or takes in a sentence and returns the first word of the sentence.
-> (first 'hello)
'h
-> (first '(hi hey hello))
'hi
last
last
takes in a word and returns the last letter of the word, or takes in a sentence and returns the last word of the sentence.
-> (last 'hello)
'o
-> (last '(hi hey hello))
'hello
butfirst
or bf
butfirst
, or its abbreviated version bf
, takes in a word and returns all but the first letter of the word, or takes in a sentence and returns all but the first word of the sentence.
-> (butfirst 'hello)
'ello
-> (bf 'hello)
'ello
-> (butfirst '(hi hey hello))
'(hey hello)
-> (bf '(hi hey hello))
'(hey hello)
butlast
or bl
butlast
, or its abbreviated version bl
, takes in a word and returns all but the last letter of the word, or takes in a sentence and returns all but the last word of the sentence.
-> (butlast 'hello)
'hell
-> (bl 'hello)
'hell
-> (butlast '(hi hey hello))
'(hi hey)
-> (bl '(hi hey hello))
'(hi hey)
item
item
takes in a number n
and a word and returns the n
th letter in the word. Or, it takes in a number n
and a sentence and returns the n
th word in the sentence.
-> (item 2 'hello)
'e
-> (item 2 '(hi hey hello))
'hey
Test Your Understanding
Try and guess what Racket will output for the following expressions, then check your answers with the Racket interpreter.
(first '(foo foo))
(bf '(foo foo))
(equal? (first '(foo foo)) (bf '(foo foo)))
equal?
is a function that checks if two elements are the same.
Word and Sentence Constructors
Now that we can take apart a word or sentence, lets learn how to put them
together.
word
word
takes in any number of words as arguments concatenates them into one big word.
-> (word 'play 'ground)
'playground
-> (word 'fo 'o 'b 'ar)
'foobar
-> (word 'cs '61 'as)
'cs61as
sentence
or se
sentence
, or its abbreviated version se
, takes in any number of words or sentences as arguments and creates one sentence of all of its arguments.
-> (sentence 'I 'love 'cs '61as!)
'(I love cs 61as!)
-> (se 'foo 'bar)
'(foo bar)
-> (se 'foo '(foo bar) 'bar)
'(foo foo bar bar)
The Empty Word
There is an empty word that you can combine with other words which will have no effect when used. This is represented by ""
.
-> (word 'foo "")
'foo
-> (word "" 'foo)
'foo
-> (word "" "")
""
The Empty Sentence
There is also an empty sentence that you can combine with other sentences which will have no effect when used. This is represented by '()
.
-> (se 'hi 'there '())
(hi there)
-> (se '() 'hi 'there)
(hi there)
-> (se 'hi '() 'there)
(hi there)
-> (se '() '() '())
'()
At the moment it may not be clear as to why need these empty words and sentences. Keep these in mind for now, as they will be very useful when we learn recursion in Lesson 0-3.
Test Your Understanding
Note: This is Exercise 1 on your Homework.
Let’s build some functions to deal with words and sentences. We’ll define the second
procedure for you — this procedure returns the second letter in a word, or the second word in a sentence.
(define (second item)
(first (bf item)))
- Write a procedure `first-two` that takes a word as its argument, returning a two-letter word containing the first two letters of the argument.
- Write a procedure `two-first` that takes two words as arguments, returning a two-letter word containing the first letters of the two arguments.
- Now write a procedure `two-first-sent` that takes a two-word sentence as argument, returning a two-letter word containing the first letters of the two words.
Pitfalls
Basically the only punctuation you can use when working with words and sentences are !
and ?
. You have already seen that the quote '
has a special meaning in Racket. The period and comma also have special meaning, so you cannot use those, either.
As you saw in an earlier exercise, there’s a difference between a word and a sentence containing one word. For example, people often mistakenly assume that the butfirst
of a two-word sentence such as (computer science)
is 'science
. In actuality, it is a sentence with one word: (science)
. Another way of proving the difference between a word and a one-word sentence is by count
-ing both of them:
-> (bf '(computer science))
'(science)
-> (count (bf '(computer science)))
1 ;; because there is ONE word in the sentence.
-> (first (bf '(computer science)))
'science
> (count (first (bf '(computer science))))
7 ;; because there are SEVEN letters in the word 'science
Takeaways
- We can build words and sentences using
word
andsentence
, respectively. - We can also make words and sentences using a quote.
- We can retrieve parts of a word or parts of a sentence by using procedures like
first
,butfirst
,last
andbutlast
.
While writing your essay, you may feel the passion for using specific words that could be challenging for the reader to understand what you are referring to. In this guide, we teach you how to define a word in an essay, on a text, sentence or within a paragraph.
In as much as you understand the easy topic inside out, the potential reader may hang while reading new vocabularies.
It could be awkward if you write word-to-word definitions from your dictionary. Also, it could disorganize or be confusing if you use the definition in the wrong part.
The best way to use definitions effectively is by using your own words and remaining concise. You can opt to introduce definitions in the essay’s body instead of in the introduction.
Before elaborating the word in definition terms, determine the word is unusual enough to require a definition.
While is it acceptable for you to define technical jargon in your essay, avoid defining every advanced vocabulary in the essay.
Rephrase the definition with your own words. You must include a full quotation if you are word-to-word definition from the dictionary. For instance, you can make the sentence flow better by
defining a word like ‘workout’, as follows: “Workout is an exercise of improving one’s fitness and performance.”
If you are using in-text citations, you should cite the dictionary or the textbook that you took the definition from when you end the sentences.
When it is the first time you are using such a source, then use the full title backed by the abbreviation. By doing correct referencing of the definition source you used, you will be avoiding plagiarism in your essay.
Let the definition be in the body and not the introduction since the introduction ought to catch the reader’s attention as you lay your thesis. Alternatively, you want to avoid defining a word, then use synonyms.
Keep the definition as short as possible. But, if you believe the definition could belong, then you can break it into shorter sentences to bring clarity to your essay.
Do you want to explain something in the mid of the sentence without confusing the reader?
While it is true that you may be harboring a lot of terminologies in your context that require some explanation, you must do it tactfully to promote the flow of your sentences well.
There are three ways you can insert a definition in the mid sentences as provided by the following examples.
1. By Using Commas
You can use commas as a way of punctuating your sentence to enhance the meaning. For example:
“John and Joseph had to see Bill gates, the leader of Microsoft Corporation, and advise him….”
2. Em and En Dashes
They are not synonymous with hyphens but needed to punctuate your sentence and restore your intended meaning. For example, we can paraphrase the above sentence to appear as follows:
“John and Joseph had to see Bill gates — the leader of Microsoft Corporation — and advise him….”
3. Parenthetical Aside
It is also another suitable method to use when inserting a definition in the mid sentences to update the reader with additional facts.
“John and Joseph had to see Bill gates (the leader of Microsoft Corporation) and advise him….”
How to Quote a Definition in a Sentence/Essay
When writing your essay, you will encounter such issues which are usually unavoidable. If we assume that you are using APA style for referencing, one must quote a definition inside double-quotes.
That is “Definition” and put the author-year and page numbers.
A definition in an essay examples
- McCarthy and George (1990) defined the essay as “a literary composition which represents author’s arguments on a specific topic.” P.87
- An essay is “a literary composition which represents author’s arguments on a specific topic.” (McCarthy and George, 1990, P.87)
- McCarthy and George (1990, P.87) defined an essay as “a literary composition which represents author’s arguments on a specific topic.”
Such definitions come in handy when you are writing essays that require you to understand one thing well. A good is example is when writing a comparison essay or a definition essay. Let us explore how to write a definition essay here.
Tips How to Write a Definition essay
A definition essay could be a piece of writing where you write your own meaning. One must ensure that you research your definition well and support it by the evidence.
In addition, it could be an explanation of what specific terms means in your context. This becomes a paragraph. Check out how to write good definition paragraphs and understand them from another perspective.
Some of the terms could have literal meanings like a phone, tablet, or spoon.
Other abstracts such as truth, love, or success will depend on the person’s point of view.
Different papers carry varying meanings hence when writing one, you must be precise to help the reader understanding what you are talking about.
It could be reasonable if you remain unique as you write a definition essay. Avoid expressing meaning using the same words.
Before you choose a definition essay topic, ensure that you select an abstract word that has a complex meaning. Also, ensure that the same word is indisputable.
Tips How to Define a Word in a Text or Paragraph
1. Select a Word
The main point of view when writing an essay is selecting an idea or concept. Select a word that will describe an idea like Hate, Love, etc. ensure that you understand the term you are choosing completely.
You can read from the dictionary but avoid extracting the definition from there but explain it in your own words.
Suppose your concept is open, then find your unique define based on experience. After that, find the basis to support your definitions.
2. Select a Word That You Know
It is suitable to settle for the word that you are familiar with and you have a basic understanding of the word. Doing so helps you to write easily. For example, you can select a word like ‘pride’ because you understand its meaning and what it feels as you use it in your context.
3. Select a Word With Different Meanings
Selecting a word with plural meanings comes in handy when you believe it will bring a different meaning to various people. As you write about it, there is an opportunity to involve your understanding and interpretations of other people.
For example, one can select a word like “love” because it comes with varying meanings. Every person will understand and interoperate it uniquely.
4. Avoid Specific Things and Objects
Stay away from selecting such things as “cups “or “pillow” because it complicates your writing because you cannot write a lot on specific objects. That makes the essay appear superficial and not shrewd enough.
5. Go Online
With an internet connection, you can seek an online platform and get enough information about what you want. The internet has several scholarly academic blogs and articles.
Additionally, you can still access videos created by smart people who deeply researched different words and sharing them with you.
6. Access the Dictionary
It is true that every official word has a deeper dictionary meaning. Tactfully, it is vital that you familiarize yourself with yourself before using it in your contexts.
You must take a closer look at the definition structure before deciding to use it. Ensure that you explain it in your own understanding when writing about it.
7. Know the Origin of the Word
Before using a specific word, it is critical to study and understand its origin. One way of researching the word is involving encyclopedias to get theories and ideas about that particular word.
For instance, if you are picking a word in the medical field, then you should consult the encyclopedia in the medical field.
8. Ask Colleagues
While it is crucial to have your perspective about the word, you can still ask friends and family about the meaning of that particular word.
Let them explain to you what it feels when you mention such a particular word. Later, you can record the answers and utilize them as your sources.
Joseph is a freelance journalist and a part-time writer who has a special interest in the gig economy. He writes on news, digital ideas, trends, and changes in the gig economy. When not writing, Joseph is hiking and climbing mountains.
Although
the borderline between various linguistic units is not always sharp
and clear, we shall try to define every new term on its first
appearance at once simply and unambiguously, if not always very
rigorously. The approximate definition of the term word
has already been given in the opening page of the book.
The
important point to remember about
definitions
is that they should indicate the most essential characteristic
features of the notion expressed by the term under discussion, the
features by which this notion is distinguished from other similar
notions. For instance, in defining the word one must distinguish it
from other linguistic units, such as the phoneme, the morpheme, or
the word-group. In contrast with a definition, a description
aims at enumerating all the essential features of a notion.
To
make things easier we shall begin by a preliminary description,
illustrating it with some examples.
The
word
may be described as the basic unit of language. Uniting meaning and
form, it is composed of one or more morphemes, each consisting of one
or more spoken sounds or their written representation. Morphemes as
we have already said are also meaningful units but they cannot be
used independently, they are always parts of words whereas words can
be used as a complete utterance (e. g. Listen!).
The
combinations of morphemes within words are subject to certain linking
conditions. When a derivational affix is added a new word is formed,
thus, listen
and
listener
are
different words. In fulfilling different grammatical functions words
may take functional affixes: listen
and
listened
are
different forms of the same word. Different forms of the same word
can be also built analytically with the help of auxiliaries. E.g.:
The
world should listen then as I am listening now (Shelley).
When
used in sentences together with other words they are syntactically
organised. Their freedom of entering into syntactic constructions is
limited by many factors, rules and constraints (e. g.: They
told me this story but
not *They
spoke me this story).
The
definition of every basic notion is a very hard task: the definition
of a word is one of the most difficult in linguistics because the
27
simplest
word has many different aspects. It has a sound form because it is a
certain arrangement of phonemes; it has its morphological structure,
being also a certain arrangement of morphemes; when used in actual
speech, it may occur in different word forms, different syntactic
functions and signal various meanings. Being the central element of
any language system, the word is a sort of focus for the problems of
phonology, lexicology, syntax, morphology and also for some other
sciences that have to deal with language and speech, such as
philosophy and psychology, and probably quite a few other branches of
knowledge. All attempts to characterise the word are necessarily
specific for each domain of science and are therefore considered
one-sided by the representatives of all the other domains and
criticised for incompleteness. The variants of definitions were so
numerous that some authors (A. Rossetti, D.N. Shmelev) collecting
them produced works of impressive scope and bulk.
A
few examples will suffice to show that any definition is conditioned
by the aims and interests of its author.
Thomas
Hobbes (1588-1679),
one
of the great English philosophers, revealed a materialistic approach
to the problem of nomination when he wrote that words are not mere
sounds but names of matter. Three centuries later the great Russian
physiologist I.P. Pavlov (1849-1936)
examined
the word in connection with his studies of the second signal system,
and defined it as a universal signal that can substitute any other
signal from the environment in evoking a response in a human
organism. One of the latest developments of science and engineering
is machine translation. It also deals with words and requires a
rigorous definition for them. It runs as follows: a word is a
sequence of graphemes which can occur between spaces, or the
representation of such a sequence on morphemic level.
Within
the scope of linguistics the word has been defined syntactically,
semantically, phonologically and by combining various approaches.
It
has been syntactically defined for instance as “the minimum
sentence” by H. Sweet and much later by L. Bloomfield as “a
minimum free form”. This last definition, although structural in
orientation, may be said to be, to a certain degree, equivalent to
Sweet’s, as practically it amounts to the same thing: free forms
are later defined as “forms which occur as sentences”.
E.
Sapir takes into consideration the syntactic and semantic aspects
when he calls the word “one of the smallest completely satisfying
bits of isolated ‘meaning’, into which the sentence resolves
itself”. Sapir also points out one more, very important
characteristic of the word, its indivisibility:
“It cannot be cut into without a disturbance of meaning, one or two
other or both of the several parts remaining as a helpless waif on
our hands”. The essence of indivisibility will be clear from a
comparison of the article a
and
the prefix a-
in
a
lion and
alive.
A lion is
a word-group because we can separate its elements and insert other
words between them: a
living lion, a dead lion. Alive is
a word: it is indivisible, i.e. structurally impermeable: nothing can
be inserted between its elements. The morpheme a-
is
not free, is not a word. The
28
situation
becomes more complicated if we cannot be guided by solid spelling.’
“The Oxford English Dictionary», for instance, does not
include the
reciprocal pronouns each
other and
one
another under
separate headings, although
they should certainly be analysed as word-units, not as word-groups
since they have become indivisible: we now say with
each other and
with
one another instead
of the older forms one
with another or
each
with the other.1
Altogether
is
one word according to its spelling, but how is one to treat all
right, which
is rather a similar combination?
When
discussing the internal cohesion of the word the English linguist
John Lyons points out that it should be discussed in terms of two
criteria “positional
mobility”
and
“uninterruptability”.
To illustrate the first he segments into morphemes the following
sentence:
the
—
boy
—
s
—
walk
—
ed
—
slow
—
ly
—
up
—
the
—
hill
The
sentence may be regarded as a sequence of ten morphemes, which occur
in a particular order relative to one another. There are several
possible changes in this order which yield an acceptable English
sentence:
slow
—
ly
—
the
—
boy
—
s
—
walk
—
ed
—
up
—
the
—
hill
up —
the
—
hill
—
slow
—
ly
—
walk
—
ed
—
the
—
boy
—
s
Yet
under all the permutations certain groups of morphemes behave as
‘blocks’ —
they
occur always together, and in the same order relative to one another.
There is no possibility of the sequence s
—
the
—
boy,
ly —
slow,
ed —
walk.
“One
of the characteristics of the word is that it tends to be internally
stable (in terms of the order of the component morphemes), but
positionally mobile (permutable with other words in the same
sentence)”.2
A
purely semantic treatment will be found in Stephen Ullmann’s
explanation: with him connected discourse, if analysed from the
semantic point of view, “will fall into a certain number of
meaningful segments which are ultimately composed of meaningful
units. These meaningful units are called words.»3
The
semantic-phonological approach may be illustrated by A.H.Gardiner’s
definition: “A word is an articulate sound-symbol in its aspect of
denoting something which is spoken about.»4
The
eminent French linguist A. Meillet (1866-1936)
combines
the semantic, phonological and grammatical criteria and advances a
formula which underlies many subsequent definitions, both abroad and
in our country, including the one given in the beginning of this
book: “A word is defined by the association of a particular meaning
with a
1Sapir
E. Language.
An Introduction to the Study of Speech. London, 1921,
P.
35.
2 Lyons,
John. Introduction
to Theoretical Linguistics. Cambridge: Univ. Press, 1969.
P. 203.
3 Ullmann
St. The
Principles of Semantics. Glasgow, 1957.
P.
30.
4 Gardiner
A.H. The
Definition of the Word and the Sentence //
The
British Journal of Psychology. 1922.
XII.
P. 355
(quoted
from: Ullmann
St.,
Op.
cit., P. 51).
29
particular
group of sounds capable of a particular grammatical employment.»1
This
definition does not permit us to distinguish words from phrases
because not only child,
but
a
pretty child as
well are combinations of a particular group of sounds with a
particular meaning capable of a particular grammatical employment.
We
can, nevertheless, accept this formula with some modifications,
adding that a word is the smallest significant unit of a given
language capable of functioning alone and characterised by positional
mobility
within
a sentence, morphological
uninterruptability
and semantic
integrity.2
All these criteria are necessary because they permit us to create a
basis for the oppositions between the word and the phrase, the word
and the phoneme, and the word and the morpheme: their common feature
is that they are all units of the language, their difference lies in
the fact that the phoneme is not significant, and a morpheme cannot
be used as a complete utterance.
Another
reason for this supplement is the widespread scepticism concerning
the subject. It has even become a debatable point whether a word is a
linguistic unit and not an arbitrary segment of speech. This opinion
is put forth by S. Potter, who writes that “unlike a phoneme or a
syllable, a word is not a linguistic unit at all.»3
He calls it a conventional and arbitrary segment of utterance, and
finally adopts the already mentioned
definition of L. Bloomfield. This position is, however, as
we have already mentioned, untenable, and in fact S. Potter himself
makes ample use of the word as a unit in his linguistic analysis.
The
weak point of all the above definitions is that they do not establish
the relationship between language and thought, which is formulated if
we treat the word as a dialectical unity of form and content, in
which the form is the spoken or written expression which calls up a
specific meaning, whereas the content is the meaning rendering the
emotion or the concept in the mind of the speaker which he intends to
convey to his listener.
Summing
up our review of different definitions, we come to the conclusion
that they are bound to be strongly dependent upon the line of
approach, the aim the scholar has in view. For a comprehensive word
theory, therefore, a description seems more appropriate than a
definition.
The
problem of creating a word theory based upon the materialistic
understanding of the relationship between word and thought on the one
hand, and language and society, on the other, has been one of the
most discussed for many years. The efforts of many eminent scholars
such as V.V. Vinogradov, A. I. Smirnitsky, O.S. Akhmanova, M.D.
Stepanova, A.A. Ufimtseva —
to
name but a few, resulted in throwing light
1Meillet
A. Linguistique
historique et linguistique generate. Paris,
1926.
Vol.
I. P. 30.
2 It
might be objected that such words as articles, conjunctions and a few
other words
never occur as sentences, but they are not numerous and could be
collected into a
list of exceptions.
3 See:
Potter
S. Modern
Linguistics. London, 1957.
P.
78.
30
on this problem and achieved a
clear presentation of the word as a basic unit of the language. The
main points may now be summarised.
The
word
is the
fundamental
unit
of language.
It is a dialectical
unity
of form
and
content.
Its content or meaning is not identical to notion, but it may reflect
human notions, and in this sense may be considered as the form of
their existence. Concepts fixed in the meaning of words are formed as
generalised and approximately correct reflections of reality,
therefore in signifying them words reflect reality in their content.
The
acoustic aspect of the word serves to name objects of reality, not to
reflect them. In this sense the word may be regarded as a sign. This
sign, however, is not arbitrary but motivated by the whole process of
its development. That is to say, when a word first comes into
existence it is built out of the elements already available in the
language and according to the existing patterns.
Соседние файлы в предмете [НЕСОРТИРОВАННОЕ]
- #
- #
- #
- #
- #
- #
- #
- #
- #
- #
- #
A technology that strives to understand human communication must be able to understand meaning in language. In this post, we take a deeper look at a core component of our expert.ai technology, the semantic disambiguator, and how it determines word meaning and sentence meaning via disambiguation.
To start, let’s clarify our definitions of words and sentences from a linguistic point of view.
Word Meaning and Sentence Meaning in Semantics
Semantics is the study of the meaning of words, phrases, sentences and text. This can be broken down into subcategories such as formal semantics (logical aspects of meaning), conceptual semantics (cognitive structure of meaning) and today’s focus of lexical semantics (word and phrase meaning).
A “word” is a string of characters that can have different meanings (jaguar: car or animal?; driver: one who drives a vehicle or the part of a computer?; rows, the plural noun or the third singular person of the verb to row?). A “sentence” is a group of words that express a complete thought. To fully capture the meaning of a sentence, we need to understand how words relate to other words.
Going Back to School
To understand word meaning and sentence meaning, our semantic disambiguator engine must be able to automatically resolve ambiguities with any word in a text.
Let’s consider this sentence:
John Smith is accused of the murders of two police officers.
To understand the word meaning and sentence meaning in any phrase, the disambiguator performs four consecutive phases of analysis:
Lexical Analysis
During this phase, the stream of text is broken up into meaningful elements called tokens. The sequence of “atomic” elements resulting from this process will be further elaborated in the next phase of analysis.
- John > human proper noun
- Smith > human proper noun
- is > verb
- accused > noun
- of > preposition
- the > article
Grammatical Analysis
During this phase, each token in the text is assigned a part of speech. The semantic disambiguator can recognize any inflected forms and conjugations as well as identify nouns, proper nouns and so on.
Starting from a mere sequence of tokens, what results from this elaboration is a sequence of elements. Some of them have been grouped to form collocations (e.g., police officer) and every token or group of tokens is represented by a block that identifies its part of speech.
- John Smith > human proper noun
- is accused > predicate nominal
Syntactical Analysis
During this phase, the disambiguator operates several word grouping operations on different levels to reproduce the way that words are linked to one another to form sentences. Sentences are further analyzed to attribute a logical role to each phrase (subject, predicate, object, verb, complement, etc.) and identify relationships between them and other complements whenever possible. In our example, the sentence is made of a single independent clause, where John Smith is recognized as subject of the sentence.
- John Smith > subject
- is accused > nominal predicate
Semantic Analysis
During the last and most complex phase, the tokens recognized during grammatical analysis are associated with a specific meaning. Though each token can be associated to several concepts, the choice is made by considering the base form of each token with respect to its part of speech, the grammatical and syntactical characteristics of the token, the position of the token in the sentence and its relation to the syntactical elements surrounding it.
Like the human brain, the disambiguator eliminates all candidate terms for each token except one, which will be definitively assigned to the token. When it comes across an unknown element in a text (e.g., human proper names), it tries to infer word meaning and sentence meaning by considering the context in which each token appears to determine its meaning.
- Is accused > to accuse > to blame
- police officer > policeman, police woman, law enforcement officer
Want to learn more about the disambiguation process? Take a deep dive in our brief, “Disambiguation: The Key to Contextualization“.
Originally published October 2016, updated May 2022.
Hybrid AI Runs on Semantics
Discover the role semantics plays in symbolic AI and what that does for hybrid AI.
Learn More