The sentence clustering algorithm works well for my usage, could you tell me what algorithm it uses and if there are any related papers?
The sentence clustering algorithm uses a graph based algorithm which attempts to find clusters as well as topic cues simultaneously. It captures similar sentences by its word composition, which is why it works well mainly for English only (since it was primarily tested in this language). We have not published our algorithm as yet, looking to do that in the near future. Thank you for your interest!