A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2010.02423v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
On the Role of Supervision in Unsupervised Constituency Parsing
[article]
<span title="2020-10-07">2020</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2020-10-06">2020</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.02423v1">arXiv:2010.02423v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rqcvirsunzdr7a2l3gfe5afgbi">fatcat:rqcvirsunzdr7a2l3gfe5afgbi</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.02423v1">arXiv:2010.02423v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/rqcvirsunzdr7a2l3gfe5afgbi">fatcat:rqcvirsunzdr7a2l3gfe5afgbi</a> </span>
We analyze several recent unsupervised constituency parsing models, which are tuned with respect to the parsing F_1 score on the Wall Street Journal (WSJ) development set (1,700 sentences). We introduce strong baselines for them, by training an existing supervised parsing model (Kitaev and Klein, 2018) on the same labeled examples they access. When training on the 1,700 examples, or even when using only 50 examples for training and 5 for development, such a few-shot parsing approach can
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.02423v2">arXiv:2010.02423v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/whvfc7ijanf7jba76lshflha7m">fatcat:whvfc7ijanf7jba76lshflha7m</a>
</span>
more »
... rm all the unsupervised parsing methods by a significant margin. Few-shot parsing can be further improved by a simple data augmentation method and self-training. This suggests that, in order to arrive at fair conclusions, we should carefully consider the amount of labeled data used for model development. We propose two protocols for future work on unsupervised parsing: (i) use fully unsupervised criteria for hyperparameter tuning and model selection; (ii) use as few labeled examples as possible for model development, and compare to few-shot parsing trained on the same labeled examples.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201013150226/https://arxiv.org/pdf/2010.02423v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext">
<button class="ui simple right pointing dropdown compact black labeled icon button serp-button">
<i class="icon ia-icon"></i>
Web Archive
[PDF]
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2010.02423v2" title="arxiv.org access">
<button class="ui compact blue labeled icon button serp-button">
<i class="file alternate outline icon"></i>
arxiv.org
</button>
</a>