updated

potam/projects.html

@@ -64,9 +64,41 @@ <h1>Heading One</h1>
                         
                         <p>Donec id elit non mi pSed posuere consectetur est at <a href="#">This is a link</a>. Nullam id dolor id nibh ultricies vehicula ut id elit. Fusce dapibus, tellus ac cursus commodo, tortor mauris condimentum nibh, <span class="highlight">Highlight span</span> ut fermentum massa justo sit amet risus.</p>
 -->
+<h3 id = "10"> Cognitively-Motivated Deep Learning (2019-) </h3>
+
+For too many decades the emphasis in our community has been on task-specific decoding performance
+ rather than creating models that have good generalization power and, especially, good induction properties,
+ i.e., can learn from one-to-five examples just like humans do.
+  My vision is creating cognitively-motivated representations (aka models) that
+ radically depart from the unified metric space fallacy (aka the real-world bias)
+  and respect macroscopic cognitive principles such as low-dimensionality,
+  hierarchy, abstraction, two-tier architecture (system 1 vs system 2) etc.
+  Instead of following the popular path in representation modeling of
+  adding these constraints as training tricks in deep neural nets or regularization
+  terms in autoencoder training, we propose instead <em> a top-down hierarchical manifold
+ representation </em> that explicitly (by design) respects cognitive principles.
+ In our recent work, we show that by <em> creating and reasoning using an ensemble of
+ sparse, low-dimensional subspaces we achieve human-like performance not only
+ for decoding but also for induction </em> (learning) lexical semantics.
+
+<h3 id = "9"> Natural Multiparty Dialogue Interaction (2021-2022) </h3>
+
+While most task-oriented dialogues assume conversations between the agent and one user at a time, dialogue systems are increasingly expected 
+to communicate with multiple users simultaneously who make decisions collaboratively. To facilitate development of such systems, in collaboration with colleagues at Amazon we released the Multi-User MultiWOZ dataset: task-oriented dialogues among two users and one agent. 
+Multiparty dialogues reflect interesting dynamics of collaborative decision-making in task-oriented scenarios, e.g., social chatter and deliberation. 
+Supported by this data, we proposed the novel task of multi-user contextual query rewriting: to rewrite a task-oriented chat between two users as a concise task-oriented query that retains only task-relevant information and that is directly consumable by the dialogue system. 
+We demonstrated that in multi-user dialogues, using predicted rewrites substantially improves dialogue state tracking without modifying existing dialogue systems that are trained for single-user dialogues. Further, this method surpasses training a medium-sized model directly on multi-user dialogues and generalizes to unseen domains.
+
+<h3 id = "8"> Behavioral Signals: Emotion and Behavioral Tracking in the Lab and in the Wild (2017-2021) </h3>
+
+Despite significant progress, emotion AI  remains a challenging R&D area  especially when technology is being transferred from the academic lab to a startup industrial setting. 
+In collaboration with the team at Behavioral Signals, we introduced a series of innovations towards building a general purpose emotion AI conversational
+platform, the OliverAPI. Specifically progress has been made in the areas of data imbalance, data sparseness and data augmentation, as well as, multimodal fusion using novel neural network architectures.  A series of practical considerations have also been addressed including data annotation, cultural/social biases in the data, scalability and performance. 
+These technologies have been applied to a wide-range of use-cases in the real world from conversational speech analysis to multimedia processing, mental health and human-robot interaction.
+
 
 <h3 id = "7"> BabyRobot: Child-Robot Communication (2016-2019) </h3>
-I am the technical coordinator of the EU-IST H2020 BabyRobot project.
+I served as the technical coordinator of the EU-IST H2020 BabyRobot project.
 In <a href="https://sites.google.com/site/babyrobotproject/">the BabyRobot project</a>
 we model human-robot communication as a three-step process: sharing attention, establishing common ground and forming shared goals. 
 Our main goal is to create robots that analyze and track human behavior over time in the context of their surroundings (situational) using audio-visual monitoring in order to establish common ground and intention-reading capabilities. In BabyRobot we focus on the typically developing and autistic spectrum children user population in order to define, implement and evaluate child-robot interaction application scenarios for developing specific socio-affective, communication and collaboration skills.
@@ -160,6 +192,9 @@ <h3 id = "6"> Past Projects: 2000-2010 </h3>
 				    	<h3>List of Projects</h3>
 
 <ul>
+<li><a href="projects.html#10"> Cognitively Motivated Deep Learning </a></li>
+<li><a href="projects.html#9"> Natural Multipary Dialogue Interaction </a></li>
+<li><a href="projects.html#8"> Behavioral Signals: Emotion and Behavioral Tracking </a></li>
 <li><a href="projects.html#7"> BabyRobot: Child-Robot Communication and Collaboration </a></li>
 <li><a href="projects.html#1"> SpeDial: Spoken Dialogue Analytics  </a></li>
 <li><a href="projects.html#2"> BabyAffect: Affective and behavioral modeling of early lexicalizations of ASD and TD children  </a></li>