Citation form of a word, e.g. Sing is the lemma for "sing", "sang", "sung"- dictionaries don't have separate definitions for the lemma. Each lemma can have multiple meanings.

Lemma

2 words are synonymous if they are interchangeable in any sentence without changing the true conditions of the sentence, having the same positional meaning. When one word has a sense that its meaning is nearly or completely identical to a sense of another word, the 2 words are considered 2 synonyms.

Synonym

A hypothesis that there is always a difference in meaning for words in different linguistic forms, e.g. Water and H2O are synonymous, but there is still a difference in the words related context genre, and this difference should be considered part of the difference in meanings.

Principle of Contrast

The attributes that two words are associated by co-participating in the same context, such as an event, or a group of semantic domain.

Word Relatedness

Relations between words included but not limited to their meanings; an important component of tasks such as question answering, paraphrasing and summarization.

Word Similarity

A semantic frame is a set of words that have represent roles in an event. For example, in a semantics frame: {buyer, seller, goods}, money are the lexical components of a commercial transaction, they are the semantics roles that can attribute to a word. 

Semantic Frames and Roles

The aspects of a word's meaning that are related to the emotions, sentiment, opinions, or evaluations from authors and readers. For example, the difference in affective meanings between the words "copy", "replica" and "reproduction". Important dimensions of affective meanings are valence, arousal and dominance.


Connotations in NLP

Lexical Semantic Resources (LSRs) is a lexical database that organizes the relation between synsets via lexical and semantic relations. 

Lexical Semantic Resources (LSRs)

University of Michigan - Ann Arbor

- Information extraction
- Machine translation
- Discourse, dialogue and pragmatics
- Natural language generation
- Speech recognition
- Lexical semantics
- Phonology / morphology
- Language resources

Natural language processing in ACM Computing Classification

An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition
https://www.cs.colorado.edu/~martin/slp2.html

Speech and Language Processing (2nd edition)

NLG, a subfield of artificial intelligence (AI), is a software process that automatically transforms data into plain-English content.

Natural language generation

Speech recognition

Phonology / Phonetics

Knowledge of the meaningful components of words; more specifically, the way words break down into components that carry meanings like singular vs. plural, I'm, can't, etc.

Morphology

Lexical semantics

Knowledge about linguistic units larger than a single utterance

Discourse

Knowledge of the relationship of meaning to the goals and intentions of the speaker.

Pragmatics

Information extraction

Because the space of possible target sentences is extremely large, a translation system often assigns scores to candidate outputs and uses a search procedure to find a strong result. If the final translation is poor, optimization verification can help determine whether the problem came from search failing to find the best-scoring candidate or from the scoring function itself ranking the wrong candidates too highly.

Learn Before

Related

Learn After