Merge pull request #98 from stanfordnlp/gh-pages-ryan-sept23

more updates
stanfordnlp · Sep 27, 2023 · 8dd55f1 · 8dd55f1
2 parents d6f7dc1 + f5cea08
commit 8dd55f1
Show file tree

Hide file tree

Showing 13 changed files with 21 additions and 21 deletions.
diff --git a/_people/patrick.md b/_people/patrick.md
diff --git a/_publications/7_hindsight_ICLR2022.md → _publications/10_hindsight_ICLR2022.md b/_publications/7_hindsight_ICLR2022.md → _publications/10_hindsight_ICLR2022.md
diff --git a/_publications/1_technical_paper_2023.md b/_publications/1_technical_paper_2023.md
@@ -0,0 +1,6 @@
+---
+title: "Dialogue Distillery: Crafting Interpolable, Interpretable, and Introspectable Dialogue from LLMs"
+authors: Ryan A. Chi, Jeremy Kim, Scott Hickmann, Siyan Li, Gordon Chi, Thanawan Atchariyachanvanit, Katherine Yu, Nathan A. Chi, Gary Dai, Shashank Rammoorthy, Ji Hun Wang, Parth Sarthi, Virginia Adams, Brian Y. Xu, Brian Z. Xu, Kristie Park, Steven Cao, and Christopher D. Manning
+venue: Alexa Prize Proceedings 2023
+extlink: https://assets.amazon.science/c6/bc/589db16944f1a185305802f8393e/chirpy-cardinal-dialogue-distillery-crafting-interpolable-interpretable-and-introspectable-dialogue-from-llms.pdf
+---
diff --git a/_publications/2_siyan_sigdial_2022.md b/_publications/2_siyan_sigdial_2022.md
@@ -0,0 +1,6 @@
+---
+title: "When can I Speak? Predicting Initiation Points for Spoken Dialogue Agents"
+authors: Siyan Li, Ashwin Paranjape, Christopher Manning
+venue: Special Interest Group on Discourse and Dialogue (SIGDIAL), 2022
+extlink: https://aclanthology.org/2022.sigdial-1.22/
+---
diff --git a/_publications/3_sigdial_2022.md b/_publications/3_sigdial_2022.md
@@ -0,0 +1,6 @@
+---
+title: "Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent"
+authors: Ethan A. Chi, Ashwin Paranjape, Abigail See, Caleb Chiam, Trenton Chang, Kathleen Kenealy, Swee Kiat Lim, Amelia Hardy, Chetanya Rastogi, Haojun Li, Alexander Iyabor, Yutong He, Hari Sowrirajan, Peng Qi, Kaushik Ram Sadagopan, Nguyet Minh Phu, Dilara Soylu, Jillian Tang, Avanika Narayan, Giovanni Campagna, Christopher Manning
+venue: Special Interest Group on Discourse and Dialogue (SIGDIAL), 2022
+extlink: https://aclanthology.org/2022.sigdial-1.37/
+---
diff --git a/_publications/1_technical_paper_2020.md → _publications/4_technical_paper_2020.md b/_publications/1_technical_paper_2020.md → _publications/4_technical_paper_2020.md
@@ -2,7 +2,6 @@
 title: "Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations"
 authors: Ashwin Paranjape*, Abigail See*, Kathleen Kenealy, Haojun Li, Amelia Hardy, Peng Qi, Kaushik Ram Sadagopan, Nguyet Minh Phu, Dilara Soylu, Christopher D. Manning
 venue: Alexa Prize Proceedings 2020
-extlink: https://m.media-amazon.com/images/G/01/mobile-apps/dex/alexa/alexaprize/assets/challenge3/proceedings/Stanford-Chirpy_Cardinal1.pdf
-extsupplementary: https://m.media-amazon.com/images/G/01/mobile-apps/dex/alexa/alexaprize/assets/challenge3/proceedings/Stanford-Chirpy_Cardinal2.pdf 
+extlink: https://aclanthology.org/2022.sigdial-1.37/
 ---
 We present Chirpy Cardinal, an open-domain dialogue agent, as a research plat- form for the 2019 Alexa Prize competition. Building an open-domain socialbot that talks to real people is challenging – such a system must meet multiple user expectations such as broad world knowledge, conversational style, and emotional connection. Our socialbot engages users on their terms – prioritizing their interests, feelings and autonomy. As a result, our socialbot provides a responsive, person- alized user experience, capable of talking knowledgeably about a wide variety of topics, as well as chatting empathetically about ordinary life. Neural generation plays a key role in achieving these goals, providing the backbone for our con- versational and emotional tone. At the end of the competition, Chirpy Cardinal progressed to the finals with an average rating of 3.6/5.0, a median conversation duration of 2 minutes 16 seconds, and a 90th percentile duration of over 12 minutes.
diff --git a/_publications/2_humanlike_PCMI_NAACL2021.md → _publications/5_humanlike_PCMI_NAACL2021.md b/_publications/2_humanlike_PCMI_NAACL2021.md → _publications/5_humanlike_PCMI_NAACL2021.md
diff --git a/_publications/3_initiative_SIGDIAL2021.md → _publications/6_initiative_SIGDIAL2021.md b/_publications/3_initiative_SIGDIAL2021.md → _publications/6_initiative_SIGDIAL2021.md
diff --git a/_publications/4_offensiveuser_SIGDIAL2021.md → _publications/7_offensiveuser_SIGDIAL2021.md b/_publications/4_offensiveuser_SIGDIAL2021.md → _publications/7_offensiveuser_SIGDIAL2021.md
diff --git a/...ions/5_userdissatisfaction_SIGDIAL2021.md → ...ions/8_userdissatisfaction_SIGDIAL2021.md b/...ions/5_userdissatisfaction_SIGDIAL2021.md → ...ions/8_userdissatisfaction_SIGDIAL2021.md
diff --git a/_publications/6_technical_paper_2021.md → _publications/9_technical_paper_2021.md b/_publications/6_technical_paper_2021.md → _publications/9_technical_paper_2021.md
diff --git a/index.md b/index.md
@@ -9,7 +9,7 @@ permalink: /
 <img style='float:right;' src="{{site.baseurl}}/assets/images/chirpy_logo_optimized.svg" width="140" height="140">
 <h1 class='fs-9'> Welcome to <strong>Chirpy Cardinal</strong>. </h1>
 We are a <a href="https://nlp.stanford.edu/">Stanford NLP</a> research group focussed on open-domain conversational dialogue. <br><br>
-Our research is informed by hundreds of thousands of people chatting with our bot Chirpy Cardinal via the <a href="https://developer.amazon.com/alexaprize">Alexa Prize</a>, a university competition to advance conversational AI. <br><br>
+Our research is informed by hundreds of thousands of people chatting with our bot Chirpy Cardinal via the <a href="https://developer.amazon.com/alexaprize">Alexa Prize</a>, a university competition to advance conversational AI. In <a href="https://twitter.com/AmazonScience/status/1701697037807313148">2023</a>, we won <b>1st Place (Science Prize).</b><br><br>
 In collaboration with <a href="https://oval.cs.stanford.edu">Open Virtual Assistant Lab (OVAL)</a>, we have open-sourced our award-winning socialbot from Alexa Prize 2020/2021. 
 </div>
 
@@ -22,7 +22,7 @@ In collaboration with <a href="https://oval.cs.stanford.edu">Open Virtual Assist
 {: .fs-6 .fw-300 }
 
 ## Publications and Media
-* [**SIGDIAL 2022**](
+* [**SIGDIAL 2022**](https://aclanthology.org/2022.sigdial-1.22/): New research paper on predicting lead-time to initiation.
 * [**ICLR 2022**](https://openreview.net/pdf?id=Vr_BTpw3wz): New research paper on jointly training neural retriever and generator for knowledge-grounded conversations.
 * [**NAACL 2021 and SIGDIAL 2021**](/chirpycardinal/publications): 4 new research papers accepted! 
 * [**Stanford AI Lab Blog**](https://ai.stanford.edu/blog/chirpy-cardinal/): _Inside Chirpy Cardinal: Stanford's Open-Source Social Chatbot that Won 2nd place in the Alexa Prize_

diff --git a/live_hindsight.md b/live_hindsight.md