ruidan / Unsupervised-Aspect-Extraction

Code for acl2017 paper "An unsupervised neural attention model for aspect extraction"
Apache License 2.0
335 stars 117 forks source link

Question about "ortho_reg: loss - max_margin_loss" #15

Closed mangohero1985 closed 5 years ago

mangohero1985 commented 5 years ago

Hi Ruidan, thank you for the really excellent research and coding. I was also really lucky to hear your presentation in ACL2017.

In the ending of each training epoch, you showed an info about "ortho_reg: loss - max_margin_loss". I don't really understand the meaning of this. Could you please explain it? or you can show me some references about it. Thank you so much.

mangohero1985 commented 5 years ago

Was it from this "L(θ) = J(θ) + λU(θ) "?

ruidan commented 5 years ago

The ortho_reg refers to the orthogonal regularisation term described in the paper section 3.4, which is denoted by U in the overall objective loss in the above formula.