Update ethics-for-nlp.md

events/ethics-for-nlp/ethics-for-nlp.md

@@ -17,6 +17,7 @@ Organised by the Stockholm, Uppsala and Umeå interest group in ethics for NLP
 
 ### Table of Contents
 * [Programme](#programme)
+* [How to find us](#map)
 * [Workshop description](#description)
 * [Invited speakers](#speakers)
 * [Lightning talks](#talks)
@@ -49,6 +50,10 @@ Organised by the Stockholm, Uppsala and Umeå interest group in ethics for NLP
 * __16:30__ Summaries of discussions and final thoughts
 * __17:30__ Close
 
+### How to find us<a name="map"></a>
+<img align="center" width="480" src="venue_map.png"/>
+
+
 ### Workshop description<a name="description"></a>
 
 AI tasks related to modelling human language and that focus on decision making (such as identification of patient diagnoses and driving) have developed substantially over the last several years. In many areas it has been claimed that AI learning from data alone has achieved human-like performance, sometimes even better, but due to the nature of these models it is very hard to inspect directly what such models have learned. Instead, we can only observe their performance, which might be biased in one or more ways, and which has societal and environmental implications.