Try align then segment

[evamaxfield]

Building off of: https://aclanthology.org/2020.lrec-1.829.pdf

Use semantic similarity between each minutes item to a sentence in transcript, then using the trained model for segmentation classification, classify sentences that are breaking. Find the nearest segmentation markings to the most similar breaking sentences.

i.e.

part 1:

s1, s2, s3, sn...
     ^ most similar to t1

part 2:

s1, s2, s3, sn...
     ^ most similar to t1
^a       ^b

where a and b are delimiter sentences (topic breaks)

[evamaxfield]

delimiter sentences can be from random forest classified (with single delim label or start and end labels) or simple "most similar delimiter sentence between two topics" (this can also be broken into start and end most similar or simply "most similar single delim vector")

• random forest classified single delim
• random forest classified start and end delim
• most similar nearby single delim sentence before and after topic
• most similar nearby start delim before and most similar end delim after