Semantic Double-Pass Merging for improved keyphrase generation

Nobody has claimed this yet.

Does it makes sence to utilize SDPM algorythm for keyBERT? This basically looks similarity forward, and then for the second time looks backward. This can be applicable to the keyphrases to better group them and the second pass can remove or split the words in a keyphrase if its not close enough.

Double-pass merging approach first groups content by semantic similarity, then merges similar groups within a skip window, allowing it to connect related content that may not be consecutive in the text. This technique is particularly useful for documents with recurring themes or concepts spread apart.

Here is explanation of how this works.
https://bitpeak.com/chunking-methods-in-rag-methods-comparison/
https://docs.chonkie.ai/chunkers/sdpm-chunker

Read the linked SDPM explanations first, then inspect KeyBERT's current keyphrase grouping and similarity flow. Define how a forward and backward pass should group recurring concepts and split weakly related words, and identify how the result can be evaluated against the existing behavior.

Written by the indexing model from the issue text.