A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit <a rel="external noopener" href="https://arxiv.org/pdf/2109.03926v2.pdf">the original URL</a>. The file type is <code>application/pdf</code>.
Transformers in the loop: Polarity in neural models of language
[article]
<span title="2022-03-17">2022</span>
<i >
arXiv
</i>
<span class="release-stage" >pre-print</span>
Preserved Fulltext
Other Versions
<span title="2021-09-08">2021</span>
<span class="release-stage" >pre-print</span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03926v1">arXiv:2109.03926v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3gamerw7hfgslhsfo4vzx6okoi">fatcat:3gamerw7hfgslhsfo4vzx6okoi</a> </span>
<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03926v1">arXiv:2109.03926v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3gamerw7hfgslhsfo4vzx6okoi">fatcat:3gamerw7hfgslhsfo4vzx6okoi</a> </span>
Representation of linguistic phenomena in computational language models is typically assessed against the predictions of existing linguistic theories of these phenomena. Using the notion of polarity as a case study, we show that this is not always the most adequate set-up. We probe polarity via so-called 'negative polarity items' (in particular, English 'any') in two pre-trained Transformer-based models (BERT and GPT-2). We show that - at least for polarity - metrics derived from language
<span class="external-identifiers">
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03926v2">arXiv:2109.03926v2</a>
<a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/h6zenpcpy5fprktmgrpfybzvuu">fatcat:h6zenpcpy5fprktmgrpfybzvuu</a>
</span>
more »
... are more consistent with data from psycholinguistic experiments than linguistic theory predictions. Establishing this allows us to more adequately evaluate the performance of language models and also to use language models to discover new insights into natural language grammar beyond existing linguistic theories. This work contributes to establishing closer ties between psycholinguistic experiments and experiments with language models.
<a target="_blank" rel="noopener" href="https://web.archive.org/web/20220325191949/https://arxiv.org/pdf/2109.03926v2.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]
<div class="menu fulltext-thumbnail">
<img src="https://blobs.fatcat.wiki/thumbnail/pdf/a4/18/a418c0daa98a3639e1b1bd682c68644250259944.180px.jpg" alt="fulltext thumbnail" loading="lazy">
</div>
</button>
</a>
<a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2109.03926v2" 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>