Questions tagged [lemmas]
The lemmas tag has no usage guidance.
12
questions
0
votes
0answers
34 views
Rationale for grouping my list of trauma collocates into nouns and adjectives
Context: I have a dataset of words within a 5-word window of trauma (i.e., trauma collocates) and they've been parsed into parts of speech (nouns, adjectives, verbs, etc.). I am wanting to look at the ...
1
vote
0answers
48 views
Should Estonian word endings be tokenized or lemmatized for natural language understanding?
In Estonian, "in London" is translated as "Londonis". Now if we want to apply natural language understanding to this, then should I tokenize "London" and "is" separately? Or should I lemmatize "...
2
votes
1answer
219 views
Why do "determining" and "determined" have different lemmas?
I'm doing text processing with Google Cloud Language and sometimes the returned lemmas don't match my expectations. For example:
The lemma of "determining" is "determine"
The lemma of the adjective "...
4
votes
1answer
2k views
difference between the root, lemma and stem for a derived word
I am a bit confused with the usage of the terms root, lemma and stem. My understanding of the terms are as follows.
Root:The central (free) morpheme which has the content to which other bound ...
1
vote
0answers
52 views
What do we call the process of creating all of the possible morphological extractions of a given word?
In NLP, we have two directions. One is NLU (natural language understanding) which deals with a given text to analyze it, like:
language detection
normalization and text cleaning
tokenization and ...
1
vote
1answer
102 views
Does WordNet only contains Lemmas?
It seems to be an implicit assumption that wordnet only contains lemmas.
Eg in Combine dictionary lemmatization with stemmer.
I feel confidant it is a correct one, the Wordnet interface refers to ...
-1
votes
2answers
784 views
Looking for word to lemma free database
I want to write a simple program in Java, which being fed with English texts will be able to generate word usage statisitcs (e.g. topmost frequently used words in English).
For that purpose I need a ...
4
votes
1answer
405 views
Combine dictionary lemmatization with stemmer
I'm doing lemmatization as part of a classifier right now.
My question is, if it makes sense to first use a dictionary lookup, to find the lemmas (wordnet) and after that additionally, to apply a (...
2
votes
2answers
404 views
Is it sensible to ask for the lemma of an adverb?
Is lemma defined for adverbs? For example, what is the lemma of diagonally? An even more difficult example would be "What is the lemma of nationally?" Is it nationally, national ,or nation? Or lemma ...
1
vote
0answers
1k views
What are the advantages of using a morpheme-based dictionary in a speech recognition system?
What are the advantages of using a morphologically-based / lemma-based dictionary in a speech recognition system as opposed to a dictionary of 'Orthography' + 'transcription' or other types (which I ...
0
votes
2answers
177 views
Software to form a word frequency list for a Spanish book
I've actually found one called "textstat", but it doesn't recognize different word forms of one word.
So are there programs that do detect comía, come, cómelo, comiera as forms of comer?
8
votes
2answers
3k views
What is the notion of lemma?
Psycholinguistically, a lemma is an abstract conceptual form of a word. However from a lexicographic perspective, the lemma is merely the aorist or canonical form of a word.
In English, the lemma of ...
