search

NTMC-Community / MatchZoo

Facilitating the design, comparison and sharing of deep text matching models.
Apache License 2.0
3.82k stars 898 forks source link

What is the most popular loss for doc ranking and What is the most popular loss for text similarity? #775

Closed guotong1988 closed 4 years ago

guotong1988 commented 4 years ago

Based on my understanding, both the doc ranking task and text similarity task take sentence pairs as model input. We use different loss to get better result for each of them. Thank you very much.

faneshion commented 4 years ago

For ranking, hinge loss and cross-entropy loss are the most popular ones. You can try these.