Elements of Semantic Analysis in NLP

semantic interpretation in nlp

Of course, in very simple NLP systems there might not be any way to handle general world knowledge or specific discourse or situation knowledge, so the logical form is as far as the system will go. As an aside, we point out that Prolog, like any other programming language, has a built-in tokenizer that allows it to recognize valid data types that exist in Prolog. Insofar as Prolog can recognize these as not only tokens but also as Prolog commands, it is not just a tokenizer but a built-in reader. The built-in reader can be used to build a Prolog natural language tokenizer that can tokenize strings that consist of valid Prolog terms. Using this Prolog reader, and a built-in “operator” predicate to define other operators that can connect nouns, for instance, an elementary natural language processor can be built that can parse simple sentences.

  • Give an example of a yes-no question and a complement question to which the rules in the last section can apply.
  • Semantic Scholar is a free, AI-powered research tool for scientific literature, based at the Allen Institute for AI.
  • In this

    review of algoriths such as Word2Vec, GloVe, ELMo and BERT, we explore the idea

    of semantic spaces more generally beyond applicability to NLP.

  • Figure 5.6 shows two possible procedural semantics for the query, “Find all customers with last name of Smith.”, one as a database query in the Structured Query Language (SQL), and one implemented as a user-defined function in Python.
  • Another remarkable thing about human language is that it is all about symbols.
  • In the above sentence, the speaker is talking either about Lord Ram or about a person whose name is Ram.

It looks for such terms, matches them to the proper part of speech, and then tries to classify the larger phrase including the term. So, for example, it looks for common questions starting terms such as “what” “how,” “who,” “when,” etc. It can look for connectives, such as “then,” “either,” “both,” “and,” etc. to try to break up a sentence into clauses. It can recognize common greetings such as “Hello.” It can also recognize common prepositions and pronouns.

Semantic Analysis Examples

Here the sentence (S) is represented on the far left, and each stage to the right breaks it up on several lines. So moving from sentence, we break it up into a noun phrase (NP) and a verb phrase (VP), with the noun phrase consisting of the name “John,” the verb phrase consisting of the verb “ate” and a noun phrase, and that noun phrase consisting of the article “the” and the noun “cat.” In the following examples, we’re going to use two expressions of decomposition. The second expression occurs when we use the rules to express the actual analysis of a particular sentence; this is what parsing is.

semantic interpretation in nlp

But while entity extraction deals with proper nouns, context analysis is based around more general nouns. Notice that this second theme, “budget cuts”, doesn’t actually appear in the sentence we analyzed. Some of the more powerful NLP context analysis tools out there can identify larger themes and ideas that link many different text documents together, even when none of those documents use those exact words. Discourse integration and analysis can be used in SEO to ensure that appropriate tense is used, that the relationships expressed in the text make logical sense, and that there is overall coherency in the text analysed. This can be especially useful for programmatic SEO initiatives or text generation at scale. The analysis can also be used as part of international SEO localization, translation, or transcription tasks on big corpuses of data.

Deep Learning and Natural Language Processing

It captures some of the essential, common features of a wide variety of programming languages. As it directly supports abstraction, it is a more natural model of universal computation than a Turing machine. In other words, attribute grammar provides semantics to context-free grammar. Attribute grammar, when viewed as a parse tree can pass values or information among the nodes of a tree.

How is semantic parsing done in NLP?

Semantic parsing is the task of converting a natural language utterance to a logical form: a machine-understandable representation of its meaning. Semantic parsing can thus be understood as extracting the precise meaning of an utterance.

Figure 5.15 includes examples of DL expressions for some complex concept definitions. Procedural semantics are possible for very restricted domains, but quickly become cumbersome and hard to maintain. People will naturally express the same idea in many different ways and so it is useful to consider approaches that generalize more easily, which is one of the goals of a domain independent representation. A sentence has a main logical concept conveyed which we can name as the predicate. The arguments for the predicate can be identified from other parts of the sentence.

Future uses of NLP

Finite-state grammars are not recursive and thus can stumble on long sentences thus extended, perhaps stuck on extensive backtracking. Processing a sentence syntactically involves determining the subject and predicate and the place of nouns, verbs, pronouns, etc. Given the variety of ways to construct sentences in a natural language, it’s obvious that word order alone will not tell you much about these issues, and depending on word order alone would be frustrated anyway by the fact that sentences vary in length and can contain multiple clauses. Context analysis in NLP involves breaking down sentences into n-grams and noun phrases to extract the themes and facets within a collection of unstructured text documents. But nouns are the most useful in understanding the context of a conversation.


Assigning the correct grammatical label to each token is called PoS (Part of Speech) tagging and it’s not a piece of cake. Semantic Analysis is related to creating representations for the meaning of linguistic inputs. It deals with how to determine the meaning of the sentence from the meaning of its parts.

Semantic Analysis Approaches

In Sentiment analysis, our aim is to detect the emotions as positive, negative, or neutral in a text to denote urgency. In that case, it becomes an example of a homonym, as the meanings are unrelated to each other. In Meaning Representation, we employ these basic units to represent textual information. Semantic Analysis is a topic of NLP which is explained on the GeeksforGeeks blog. The entities involved in this text, along with their relationships, are shown below.

semantic interpretation in nlp

Thus at any given step in the analysis, each part of a sentence can be seen as a terminal or non-terminal. Terminals would be the actual individual words (you can’t analyze them further) and metadialog.com non-terminals would be clauses or phrases that are not yet fully broken down. So a non-terminal can be defined in terms of other elements, typically recursively, until terminals are reached.


Alan Turing’s paper “Turing Test” and Noam Chomsky’s book “Syntactic Structures” revolutionized rule-based translation in the history of NLP. After that, successful NLP systems such as SHRDLU, ELIZA, and chatbots were developed. Many machine learning algorithms, along with statistical modeling, were introduced. To allow them to understand language, usually over text or voice-recognition interactions,? Where users communicate in their own words, as if they were speaking (or typing) to a real human being. Integration with semantic and other cognitive technologies that enable a deeper understanding of human language allow chatbots to get even better at understanding and replying to more complex and longer-form requests.

semantic interpretation in nlp

Natural language processing is the process of enabling a computer to understand and interact with human language. Businesses use these capabilities to create engaging customer experiences while also being able to understand how people interact with them. With this knowledge, companies can design more personalized interactions with their target audiences. Using natural language processing allows businesses to quickly analyze large amounts of data at once which makes it easier for them to gain valuable insights into what resonates most with their customers. Natural language processing uses computer algorithms to process the spoken or written form of communication used by humans.

What is the meaning of semantic interpretation?

By semantic interpretation we mean the process of mapping a syntactically analyzed text of natural language to a representation of its meaning.

Leave a Comment

Your email address will not be published. Required fields are marked *

Shopping Cart