Pragmatics

Chapter 5
Pragmatics :

What is Pragmatics in NLP?

Here are two definitions that were given for the term Pragmatics in nlp:
• In 1962, Austin = Pragmatics is the study of "how to do things with words".
• In 2003, Leech & Weisser = Pragmatics is the branch of linguistics that seeks to explain the meaning
of linguistics messages in terms of their context of use".
 Pragmatic analysis deals with word knowledge outside of texts and queries, which is comprehension.
The many components of language that require real-world knowledge are derived from the pragmatic
analysis that focuses on what was described and is reinterpreted by what it truly meant.
 It discusses the entire communicative and social content and how interpretation is impacted by it. It
entails removing the context from which language is meaningfully used. In this approach, what was
stated is constantly the major focus and what was meant is constantly the secondary focus.
 Using a set of guidelines that characterize cooperative dialogues, aids users in discovering the
intended outcome. For instance, "shut the window?" should be taken as a request rather than an order.
What Would Happen if Pragmatics Didn't Exist?
All linguistic contact and exchanges are based on pragmatics. It is an essential component of
language comprehension and the responses that result from it. Therefore, there would be little
knowledge of intention and meaning without the function of pragmatics.
We want to show you what life would be like without pragmatics to illustrate this.
'Can you pass the salt?'
Literal Meaning: Are you physically capable of doing this task? Literal Answer: "Yes"
(Pragmatic Intention: Could you pass the salt my way? Pragmatic Reaction: Hand the speaker
the salt.)
'What time do you call this?'
 Literal Meaning: What time is it, literally? Literal Reaction: A time (for example, "twenty to
one").
Difference Between Pragmatics and Semantics
Now semantics is a term that sounds similar to pragmatics. Semantics is the study
of meaning and helps get a sense of meaning in context to speakers, writers,
readers, or even learners. So how is it different from pragmatics in nlp?
 Semantics is one area of linguistics, whereas pragmatics is another. Pragmatics
focuses on concerns of usage, whereas Semantics is all about questions of
meaning. It addresses the part of the meaning that depends on context.
Semantics examines the mystery of what signs mean. Pragmatics, on the other
hand, examines how signs relate to their users and interpreters.
Key Points on Pragmatics Analysis in NLP
1. Context Matters Most
Pragmatics interprets meaning based on situation, speaker, time, and place, not just the words.
2. Focus on Speaker Intent
It's about what the speaker wants to do — request, promise, ask, criticize — not just what they say.
3. Speech Acts
Every utterance performs an action: stating, asking, commanding, apologizing, etc.
4. Deictic Expressions (Deixis)
Words like here, now, you, this require contextual anchoring to understand.
5. Implicature
Meaning is often implied, not directly stated (e.g., "It's late" = Let's go home).
6. Presupposition
Speakers assume certain background facts (e.g., "She quit smoking" presupposes she smoked before).
7. Politeness & Social Norms
Pragmatics handles how things are said, such as indirect requests or tone (e.g., softening with
"Would you mind...?").
8. Sarcasm & Irony
Pragmatic analysis helps detect non-literal language, often missed in basic sentiment analysis.
9. Commonsense Reasoning
Pragmatic systems use world knowledge (like ConceptNet or COMET) to infer unstated facts.
10. Used in Smart Applications
Powers chatbots, dialogue systems, sarcasm detectors, intent recognition, and social media
monitoring tools.
Aspects :
1. Context Awareness
• Understands who is speaking, to whom, when, where, and why.
• Crucial for interpreting deictic terms (e.g., here, now, that).
2. Speaker Intent (Illocutionary Force)
• Identifies what the speaker intends to do with their utterance:
• Request, question, command, inform, etc.
3. Speech Acts
• Classifies utterances into:
• Assertives (state facts)
• Directives (requests, commands)
• Commissives (promises)
• Expressives (apologies, thanks)
• Declarations (changing reality, e.g., "I now pronounce...")
4. Implicature
• Interprets indirect or implied meaning.
• E.g., "It’s chilly here" → Suggestion to close the window.
5. Commonsense and World Knowledge
• Integrates background knowledge to fill gaps in logic or understand unstated facts.
• E.g., "He dropped the glass. It shattered." → Understands that glass breaks.
Discourse reference resolution :

 Discourse Reference Resolution is the process of identifying what words (usually pronouns
or noun phrases) refer to what entities in a conversation or text.
 It connects pronouns and other expressions to the correct things or people they refer to
across a passage.
 Discourse segmentations may be defined as determining the types of structures for large
discourse. It is quite difficult to implement discourse segmentation, but it is very important
for information retrieval, text summarization and information extraction kind of
applications.
Unsupervised Discourse Segmentation
 The class of unsupervised discourse segmentation is often represented as linear segmentation. We can
understand the task of linear segmentation with the help of an example. In the example, there is a task
of segmenting the text into multi-paragraph units; the units represent the passage of the original text.
These algorithms are dependent on cohesion that may be defined as the use of certain linguistic devices
to tie the textual units together. On the other hand, lexicon cohesion is the cohesion that is indicated by
the relationship between two or more words in two units like the use of synonyms.
Supervised Discourse Segmentation
The earlier method does not have any hand-labeled segment boundaries. On the other hand, supervised
discourse segmentation needs to have boundary-labeled training data. It is very easy to acquire the same.
In supervised discourse segmentation, discourse marker or cue words play an important role. Discourse
marker or cue word is a word or phrase that functions to signal discourse structure. These discourse
markers are domain-specific.
Text Coherence
 Lexical repetition is a way to find the structure in a discourse, but it does not satisfy the requirement of
being coherent discourse. To achieve the coherent discourse, we must focus on coherence relations in
specific.
 Interpretation of the sentences from any discourse is another important task and to achieve this we need
to know who or what entity is being talked about. Here, interpretation reference is the key
element. Reference may be defined as the linguistic expression to denote an entity or individual. For
example, in the passage, Ram, the manager of ABC bank, saw his friend Shyam at a shop. He went to
meet him, the linguistic expressions like Ram, His, He are reference.
Reference Phenomenon

 In theoretical linguistics, reference is the act by which a linguistic expression

(typically a noun phrase or pronoun) is used to identify or denote an entity
whether real or imagined within a discourse or the external world.
 Coined in the philosophy of language by Frege, Russell, and Strawson, and
later developed in pragmatics by Stephen Levinson and others.
Referential Expressions
The core unit in reference is the Referential Expression (RE) — a word or phrase
that points to an entity.
Common Referential Expressions:
• Proper nouns: John, Paris
• Definite noun phrases: the book, my car
• Pronouns: he, she, it, they
• Demonstratives: this, that
• Referring expression − The natural language expression that is used to perform reference is called a referring expression. For
example, the passage used above is a referring expression.
• Referent − It is the entity that is referred. For example, in the last given example Ram is a referent.
• Corefer − When two expressions are used to refer to the same entity, they are called corefers. For example, Ram and he are
corefers.
• Antecedent − The term has the license to use another term. For example, Ram is the antecedent of the reference he.
• Anaphora & Anaphoric − It may be defined as the reference to an entity that has been previously introduced into the sentence.
And, the referring expression is called anaphoric.
• Discourse model − The model that contains the representations of the entities that have been referred to in the discourse and
the relationship they are engaged in.

Types of Referring Expressions

Let us now see the different types of referring expressions. The five types of referring expressions are described below −

Indefinite Noun Phrases

Such kind of reference represents the entities that are new to the hearer into the discourse context. For example − in the sentence
Ram had gone around one day to bring him some food − some is an indefinite reference.

Definite Noun Phrases

 Opposite to above, such kind of reference represents the entities that are not new or identifiable to the hearer into the discourse
context. For example, in the sentence - I used to read The Times of India The Times of India is a definite reference.
Constraint on Coreference Resolution
In English, the main problem for coreference resolution is the pronoun it. The
reason behind this is that the pronoun it has many uses. For example, it can
refer much like he and she. The pronoun it also refers to the things that do not
refer to specific things. For example, Its raining. It is really good.

Pronominal Anaphora Resolution

 Unlike the coreference resolution, pronominal anaphora resolution may be
defined as the task of finding the antecedent for a single pronoun. For
example, the pronoun is his and the task of pronominal anaphora resolution is
to find the word Ram because Ram is the antecedent.
• Syntactic Constraints:
• These rules govern how words are arranged in a sentence, ensuring it is grammatically
correct. Examples include:Word order: The order of words, like subject-verb-object in English, is a
syntactic constraint.
• Number agreement: Verbs must agree in number with their subjects (e.g., "The cat is sleeping,"
not "The cat are sleeping").
• Phrase structure: Sentences are built from hierarchical structures like noun phrases and verb
phrases.

• Semantic Constraints:
• These rules relate to the meaning and relationships between words. Examples include:Semantic
features: Words have semantic features that define their meaning, such as "human" being a feature
of "person" or "man".
• Selectional restrictions: Words have restrictions on the kinds of words they can combine with,
such as "walk" needing an agent (someone who walks).
• World knowledge: Semantic constraints also draw on our understanding of the world, like knowing
that "a knife can cut" but "a table can't".
• Interplay between Syntax and Semantics:
• While syntax focuses on structure, semantics focuses on meaning, both are essential for understanding language.
• Semantic constraints can guide syntactic analysis, helping to disambiguate sentences that have multiple possible
grammatical interpretations.
• For example, understanding the meaning of "I saw a man in the park" might help determine if "man" is the subject
or the object of the verb, rather than being treated as an adjective.
• Similarly, syntactic structure can provide clues about the meaning of words, especially when dealing with unfamiliar
words or concepts.

• Importance in NLP:

• NLP systems rely on both syntactic and semantic analysis to understand, generate, and translate natural language
effectively.

• Syntactic parsing helps break down sentences into their grammatical components, while semantic analysis interprets
the meaning of these components.
• By incorporating both types of constraints, NLP systems can handle the complexities of natural language and
achieve more accurate and meaningful results.

• [Link]
912