You might be interested in phonetic algorithms for similarly sounding words:
https://en.wikipedia.org/wiki/New_York_State_Identification_...
https://en.wikipedia.org/wiki/Soundex
Your specific example would be relevant to word-stemming and lemmatization. Stemming is the process of removing suffixes from words for standardization (e.g. swim, swims, swimming, swimmer could all be stemmed to just "swim") across inflections/conjugations. Lemmatization is similar but uses contexts. Actually, some stemmers wouldn't stem cargo to carg by default, but they definitely could be modified to exhibit that kind of behavior, or used as one step in a multistep standardization process
https://en.wikipedia.org/wiki/Stemming
https://en.wikipedia.org/wiki/Lemmatisation
Levenshtein distance is a good metric for individual comparisons but if you're doing a lot of pairwise comparisons/want to index it's not a great option sometimes.
https://en.wikipedia.org/wiki/Levenshtein_distance
You definitely want to also look into tries/prefix trees. These take each character in the word and use it for an O(1) index for the next level of the tree. For example, "brea" queries the top node "b", pointing the next node "r", then "e", then "a". If you next read "d", the trie would indicate that this represents a completed word-fragment at the b->r->e->a->d node of the trie. If you combine this data structure with a statistical model, you can use it for things like spell-checking and autocompletion
https://en.wikipedia.org/wiki/Trie
(I've edited this comment twice now to make it more clear, hopefully this is sufficient). Let me know if you'd like me to point you to any other resources. I've worked with NLP a decent amount and could even work with you guys, if interested my email is in my profile and we can arrange further conversations
https://en.wikipedia.org/wiki/New_York_State_Identification_...
https://en.wikipedia.org/wiki/Soundex
Your specific example would be relevant to word-stemming and lemmatization. Stemming is the process of removing suffixes from words for standardization (e.g. swim, swims, swimming, swimmer could all be stemmed to just "swim") across inflections/conjugations. Lemmatization is similar but uses contexts. Actually, some stemmers wouldn't stem cargo to carg by default, but they definitely could be modified to exhibit that kind of behavior, or used as one step in a multistep standardization process
https://en.wikipedia.org/wiki/Stemming
https://en.wikipedia.org/wiki/Lemmatisation
Levenshtein distance is a good metric for individual comparisons but if you're doing a lot of pairwise comparisons/want to index it's not a great option sometimes.
https://en.wikipedia.org/wiki/Levenshtein_distance
You definitely want to also look into tries/prefix trees. These take each character in the word and use it for an O(1) index for the next level of the tree. For example, "brea" queries the top node "b", pointing the next node "r", then "e", then "a". If you next read "d", the trie would indicate that this represents a completed word-fragment at the b->r->e->a->d node of the trie. If you combine this data structure with a statistical model, you can use it for things like spell-checking and autocompletion
https://en.wikipedia.org/wiki/Trie
(I've edited this comment twice now to make it more clear, hopefully this is sufficient). Let me know if you'd like me to point you to any other resources. I've worked with NLP a decent amount and could even work with you guys, if interested my email is in my profile and we can arrange further conversations