Abstract
There is a lot of research interest in encoding variable length sentences into fixed length vectors, in a way that preserves the sentence meanings. Two common methods include representations based on averaging word vectors, and representations based on the hidden states of recurrent neural networks such as LSTMs. The sentence vectors are used as features for subsequent machine learning tasks or for pre-training in the context of deep learning. However, not much is known about the properties that are encoded in these sentence representations and about the language information they capture. We propose a framework that facilitates better understanding of the encoded representations. We define prediction tasks around isolated aspects of sentence structure (namely sentence length, word content, and word order), and score representations by the ability to train a classifier to solve each prediction task when using the representation as input. We demonstrate the potential contribution of the approach by analyzing different sentence representation mechanisms. The analysis sheds light on the relative strengths of different sentence embedding methods with respect to these low level prediction tasks, and on the effect of the encoded vector's dimensionality on the resulting representations.
Original language | English |
---|---|
State | Published - 2017 |
Externally published | Yes |
Event | 5th International Conference on Learning Representations, ICLR 2017 - Toulon, France Duration: 24 Apr 2017 → 26 Apr 2017 |
Conference
Conference | 5th International Conference on Learning Representations, ICLR 2017 |
---|---|
Country/Territory | France |
City | Toulon |
Period | 24/04/17 → 26/04/17 |
Bibliographical note
Publisher Copyright:© ICLR 2019 - Conference Track Proceedings. All rights reserved.