Abstract
Recent work in NLP shows that LSTM language models capture hierarchical structure in language data. In contrast to existing work, we consider the learning process that leads to their compositional behavior. For a closer look at how an LSTM’s sequential representations are composed hierarchically, we present a related measure of Decompositional Interdependence (DI) between word meanings in an LSTM, based on their gate interactions. We connect this measure to syntax with experiments on English language data, where DI is higher on pairs of words with lower syntactic distance. To explore the inductive biases that cause these compositional representations to arise during training, we conduct simple experiments on synthetic data. These synthetic experiments support a specific hypothesis about how hierarchical structures are discovered over the course of training: that LSTM constituent representations are learned bottom-up, relying on effective representations of their shorter children, rather than learning the longer-range relations independently from children.
Original language | English |
---|---|
Title of host publication | Findings of the Association for Computational Linguistics: EMNLP 2020 |
Publisher | Association for Computational Linguistics |
Pages | 2797-2809 |
Number of pages | 13 |
ISBN (Print) | 978-1-952148-90-3 |
DOIs | |
Publication status | Published - 16 Nov 2020 |
Event | The 2020 Conference on Empirical Methods in Natural Language Processing - Virtual conference Duration: 16 Nov 2020 → 20 Nov 2020 https://2020.emnlp.org/ |
Conference
Conference | The 2020 Conference on Empirical Methods in Natural Language Processing |
---|---|
Abbreviated title | EMNLP 2020 |
City | Virtual conference |
Period | 16/11/20 → 20/11/20 |
Internet address |