Latent Tree Learning with Ordered Neurons: What Parses Does It Produce?
Abstract
Recent latent tree learning models can learn constituency parsing without any exposure to human-annotated tree structures. One such model is ON-LSTM (Shen et al., 2019), which is trained on language modelling and has near-state-of-the-art performance on unsupervised parsing. In order to better understand the performance and consistency of the model as well as how the parses it generates are different from gold-standard PTB parses, we replicate the model with different restarts and examine their parses. We find that (1) the model has reasonably consistent parsing behaviors across different restarts, (2) the model struggles with the internal structures of complex noun phrases, (3) the model has a tendency to overestimate the height of the split points right before verbs. We speculate that both problems could potentially be solved by adopting a different training task other than unidirectional language modelling.
Cite
@article{arxiv.2010.04926,
title = {Latent Tree Learning with Ordered Neurons: What Parses Does It Produce?},
author = {Yian Zhang},
journal= {arXiv preprint arXiv:2010.04926},
year = {2020}
}
Comments
6 pages, 3 figures, 3 tables, to appear in Proceedings of the 2020 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP