In this report, we provide a comparative analysis of different techniques for user intent classification towards the task of app recommendation. We analyse the performance of different models and architectures for multi-label classification over a dataset with a relative large number of classes and only a handful examples of each class. We focus, in particular, on memory network architectures, and compare how well the different versions perform under the task constraints. Since the classifier is meant to serve as a module in a practical dialog system, it needs to be able to work with limited training data and incorporate new data on the fly. We devise a 1-shot learning task to test the models under the above constraint. We conclude that relatively simple versions of memory networks perform better than other approaches. Although, for tasks with very limited data, simple non-parametric methods perform comparably, without needing the extra training data.
[1]
Jeffrey Dean,et al.
Efficient Estimation of Word Representations in Vector Space
,
2013,
ICLR.
[2]
Alexander I. Rudnicky,et al.
An Intelligent Assistant for High-Level Task Understanding
,
2016,
IUI.
[3]
Jonas Mueller,et al.
Siamese Recurrent Architectures for Learning Sentence Similarity
,
2016,
AAAI.
[4]
Oriol Vinyals,et al.
Matching Networks for One Shot Learning
,
2016,
NIPS.
[5]
Alexander I. Rudnicky,et al.
Weakly supervised user intent detection for multi-domain dialogues
,
2016,
2016 IEEE Spoken Language Technology Workshop (SLT).
[6]
Jason Weston,et al.
End-To-End Memory Networks
,
2015,
NIPS.
[7]
Sanja Fidler,et al.
Skip-Thought Vectors
,
2015,
NIPS.
[8]
Ming Sun,et al.
Adapting Spoken Dialog Systems Towards Domains and Users
,
2016
.