<html><body><div style="font-family: arial, helvetica, sans-serif; font-size: 12pt; color: #000000"><div>Hi Adapters,<br><br>Models like RNN and Transformer have achieved impressive results in a variety of linguistic processing tasks, suggesting that they can induce non-trivial properties of language. <br><br>In this seminar, I want to present several papers to investigate to what extent they learn to track abstract hierarchical syntactic structure and if they understand the semantic meaning of the sentence. They probe the syntactic and semantic <span style="font-size: 12pt;">abilities of models by </span><span style="color: #000000; font-family: arial, helvetica, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: #ffffff; text-decoration-style: initial; text-decoration-color: initial; display: inline !important; float: none;" data-mce-style="color: #000000; font-family: arial, helvetica, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: #ffffff; text-decoration-style: initial; text-decoration-color: initial; display: inline !important; float: none;">linking the inner workings of a neural language model to linguistic theory, providing an impressive fusion between linguistics and research on neural networks.</span><br style="color: #000000; font-family: arial, helvetica, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: #ffffff; text-decoration-style: initial; text-decoration-color: initial;" data-mce-style="color: #000000; font-family: arial, helvetica, sans-serif; font-size: 16px; font-style: normal; font-variant-ligatures: normal; font-variant-caps: normal; font-weight: 400; letter-spacing: normal; orphans: 2; text-align: start; text-indent: 0px; text-transform: none; white-space: normal; widows: 2; word-spacing: 0px; -webkit-text-stroke-width: 0px; background-color: #ffffff; text-decoration-style: initial; text-decoration-color: initial;"><!--EndFragment--><div style="clear: both;" data-mce-style="clear: both;"><br data-mce-bogus="1"></div><br>Related papers:</div><div><a href="https://arxiv.org/abs/1803.11138" data-mce-href="https://arxiv.org/abs/1803.11138">Colorless Green Recurrent Networks Dream Hierarchically</a></div><div><a href="https://arxiv.org/abs/1909.00111" data-mce-href="https://arxiv.org/abs/1909.00111">Quantity doesn't buy quality syntax with neural language models</a><br><a href="https://arxiv.org/abs/1808.10627" data-mce-href="https://arxiv.org/abs/1808.10627">Do Language Models Understand Anything? On the Ability of LSTMs to Understand Negative Polarity Items</a><br></div><div><br><br>Hope you can gain a fresh perspective after the talk :))<br><br><br>Time: Wed 4:30pm<br><br>Venue: SEIEE 3-414<br><br> <br><br>Best regards,<br><br>Eve<br></div></div></body></html>