1 2 3<!DOCTYPE html> 4<html lang="en"> 5<head> 6 7 <!-- Required meta tags --> 8 <meta charset="utf-8"/> 9 <meta 10 name="viewport" 11 content="width=device-width, initial-scale=1, shrink-to-fit=no" 12 /> 13 14 <!-- External Javascript libs_ext --> 15
15<script src="https://cdn.jsdelivr.net/npm/d3@5/dist/d3.min.js"></script>
15 16 17
17<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/handlebars.min.js" 18 integrity="sha256-/PJBs6QWvXijOFIX04kZpLb6ZtSQckdOIavLWKKOgXU=" 19 crossorigin="anonymous"></script>
19 20 21
21<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/jquery.min.js" 22 integrity="sha256-CSXorXvZcTkaix6Yvo6HppcZGetbYMGWSFlBw8HfCJo=" 23 crossorigin="anonymous"></script>
23 24 25
25<script 26 src="https://cdn.jsdelivr.net/npm/[email protected]/dist/umd/popper.min.js" 27 integrity="sha384-Q6E9RHvbIyZFJoft+2mJbHaEWldlvI9IOYy5n3zV9zzTtmI3UksdQRVvoxMfooAo" 28 crossorigin="anonymous" 29 ></script>
29 30 31
31<script src="https://cdn.jsdelivr.net/npm/[email protected]/dist/js/bootstrap.min.js" 32 integrity="sha256-WqU1JavFxSAMcLP2WIOI+GB2zWmShMI82mTpLDcqFUg=" 33 crossorigin="anonymous"></script>
33 34 35
35<script src="https://cdn.jsdelivr.net/npm/[email protected]/min/moment.min.js" 36 integrity="sha256-4iQZ6BVL4qNKlQ27TExEhBN1HFPvAvAMbFavKKosSWQ=" 37 crossorigin="anonymous"></script>
37 38 39
39<script src="https://cdn.jsdelivr.net/npm/[email protected]/builds/moment-timezone-with-data.min.js" 40 integrity="sha256-IWYg4uIC8/erItNXYvLtyYHioRi2zT1TFva8qaAU/ww=" 41 crossorigin="anonymous"></script>
41 42 43 44 <!-- Library libs_ext --> 45
45<script src="static/js/libs_ext/typeahead.bundle.js"></script>
45 46 47 48 <!-- Internal Libs --> 49
49<script src="static/js/data/api.js"></script>
49 50 51 52
52<script> 53 var auth0_domain = "dev-ma80app1.us.auth0.com"; 54 var auth0_client_id = "ptF3gg7K6X0VN0FxOeCAVbKURrAis82d"; 55 </script>
55 56
56<script src="https://cdn.auth0.com/js/auth0-spa-js/1.7/auth0-spa-js.production.js"></script>
56 57
57<script src="static/js/modules/auth0protect.js"></script>
57 58 59 60 <!-- External CSS --> 61 <link rel="stylesheet" 62 href="https://cdn.jsdelivr.net/npm/[email protected]/dist/css/bootstrap.min.css" 63 integrity="sha256-YLGeXaapI0/5IgZopewRJcFXomhRMlYYjugPLSyNjTY=" 64 crossorigin="anonymous"> 65 66 <!-- External Fonts (no google for china) --> 67 <link 68 href="static/css/Lato.css" 69 rel="stylesheet" 70 /> 71 <link href="static/css/Exo.css" rel="stylesheet"/> 72 <link 73 href="static/css/Cuprum.css" 74 rel="stylesheet" 75 /> 76 <link rel="stylesheet" href="static/css/main.css"/> 77<!-- <link rel="stylesheet" href="static/css/fa_regular.css"/>--> 78 <link rel="stylesheet" href="static/css/fa_solid.css"/> 79 <link rel="stylesheet" href="static/css/lazy_load.css"/> 80 <link rel="stylesheet" href="static/css/typeahead.css"/> 81 82 <title>INLG 2022</title> 83 84</head> 85 86<body> 87<!-- NAV --> 88 89<nav 90 class="navbar sticky-top navbar-expand-lg navbar-light bg-light mr-auto" 91 id="main-nav" 92> 93 <div class="container"> 94 <a class="navbar-brand" href="index.html"> 95 <img 96 class="logo" src="https://inlg2021.github.io/img/logo.png" 97 height="auto" 98 width="90px" 99 /> 100 </a> 101 102 <a class="navbar-brand" href="index.html">15th International Natural Language Generation Conference</a> 103 104 <button 105 class="navbar-toggler" 106 type="button" 107 data-toggle="collapse" 108 data-target="#navbarNav" 109 aria-controls="navbarNav" 110 aria-expanded="false" 111 aria-label="Toggle navigation" 112 > 113 <span class="navbar-toggler-icon"></span> 114 </button> 115 <div 116 class="collapse navbar-collapse text-right flex-grow-1" 117 id="navbarNav" 118 > 119 <ul class="navbar-nav ml-auto"> 120 <li class="nav-item active"> 121 <a class="nav-link" href="index.html">Home</a> 122 </li> 123 124 <li class="nav-item "> 125 <a class="nav-link" href="calls.html">Calls</a> 126 </li> 127 128 <li class="nav-item "> 129 <a class="nav-link" href="organizers.html">Organizers</a> 130 </li> 131 132 <li class="nav-item dropdown"> 133 <a class="nav-link dropdown-toggle" href="#" id="navbarDropdown" role="button" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false"> 134 Program 135 </a> 136 <div class="dropdown-menu" aria-labelledby="navbarDropdown"> 137 <a class="dropdown-item" href="speakers.html">Keynotes</a> 138 <a class="dropdown-item" href="panels.html">Panel</a> 139 <a class="dropdown-item" href="accepted_papers.html">Accepted Papers</a> 140 <a class="dropdown-item" href="papers.html">Papers</a> 141 <a class="dropdown-item" href="workshops.html">Workshops</a> 142 <a class="dropdown-item" href="tutorials.html">Tutorials</a> 143 <a class="dropdown-item" href="hackathons.html">Hackathon</a> 144 <a class="dropdown-item" href="genchal.html">GenChal</a> 145 </div> 146 </li> 147 148 <li class="nav-item "> 149 <a class="nav-link" href="calendar.html">Schedule</a> 150 </li> 151 152 <li class="nav-item "> 153 <a class="nav-link" href="sponsors.html">Sponsors</a> 154 </li> 155 156 <li class="nav-item "> 157 <a class="nav-link" href="registration.html">Registration</a> 158 </li> 159 160 <li class="nav-item "> 161 <a class="nav-link" href="help.html">Help</a> 162 </li> 163 </ul> 164 </div> 165 </div> 166</nav> 167 168 169 170<!-- User Overrides --> 171 172<style> 173 .back { 174 background: url("static/images/main.jpg") no-repeat center; 175 background-size: cover; 176 } 177 .back h2 { 178 font-family: "Lato", sans-serif; 179 font-weight: 900; 180 } 181</style> 182 183<div class="jumbotron jumbotron-fluid back" style="padding-bottom: 20px;"> 184 <div class="row header p-6 m-5"> 185 <div class="p-1 mx-auto text-center text-white col-md-9 col-sm-12"> 186 <h2> 187 15th International Natural Language Generation Conference 188 </h2> 189 <h2 class="p-5"> 190 18-22 July 2022 191 </h2> 192 </div> 193 </div> 194</div> 195 196 197<div class="container"> 198 <!-- Tabs --> 199 <div class="tabs"> 200 201 </div> 202 <!-- Content --> 203 <div class="content"> 204 205 206<!-- Organizers --> 207<div class="border-top my-3"></div> 208<div class="row p-4" id="faq"> 209 <div class="col-12 bd-content"> 210 <h2 class="text-center">Speakers</h2> 211 </div> 212</div> 213 214 215<div class="row"> 216 <div class="col-12" id="accordionExample"> 217 <div class="card m-2"> 218 <div class="card-header"> 219 <a 220 class="" 221 href="#DimitraGkatzia" 222 data-toggle="collapse" 223 data-target="#collapse1-1" 224 aria-expanded="true" 225 aria-controls="collapse1-1" 226 > 227 Dimitra Gkatzia</a>
227, Edinburgh Napier University 228 </div> 229 <div 230 id="collapse1-1" 231 class="collapse" 232 aria-labelledby="headingOne" 233 data-parent="#accordionExample" 234 > 235 <div class="card-body"> 236 <div class="row"> 237 <div class="col-md-2 col-sm-5"> 238 <img src="https://inlgmeeting.github.io/static/images/dimitra.jpg" width="100%" class="img-thumbnail" /> 239 </div> 240 <div class="col-md-10 col-sm-6"> 241 <h3> 242 243 NLG for Human-Robot Interaction: Challenges and Opportunities 244 245 </h3> 246 247 <span class="font-weight-bold">Abstract:</span> 248 <p>Human-robot interaction (HRI) focuses on researching the interaction between humans and (mostly) physical robots. Despite the media coverage of robots displaying human-level capabilities in conversational dialogue and NLG, in reality, such robots use simple template-based approaches and follow pre-scripted interactions. In this talk, I will initially provide an overview of current approaches to NLG for HRI focusing on the limitations of current approaches and emphasising the challenges of developing flexible NLG approaches for HRI. Finally, I will provide an overview of our project <a href="https://gow.epsrc.ukri.org/NGBOViewGrant.aspx?GrantRef=EP/T014598/1">CiViL: Commonsense and Visually-enhanced natural Language generation</a> and discuss future directions.</p> 249 250 <br /> 251 252 <span class="font-weight-bold">Bio:</span> 253 Dimitra Gkatzia is an Associate Professor at the School of Computing at Edinburgh Napier University and a SICSA AI Theme co-lead. Dimitra is interested in making computers and robots interact in a human-like way using natural language, while at the same time respecting the privacy of the users. Her current work on Human-Robot Interaction focuses on the interplay between various modalities (vision, speech, knowledge-bases) in real-world settings for human-robot teaming scenarios. Her work in this area focuses on enhancing computers/robots' c
253onversational capabilities with 'commensense' similar to the ones present in human-human communication. She is also interested in NLG evaluation practices as well as addressing the challenges of NLG in low-resource settings where example relevant tools are scarce and data is not freely available, or it is hard to acquire due to challenges such as privacy issues or low numbers of native speakers of a language. 254 255 </div> 256 </div> 257 </div> 258 </div> 259 </div> 260 </div> 261</div> 262 263 264<div class="row"> 265 <div class="col-12" id="accordionExample"> 266 <div class="card m-2"> 267 <div class="card-header"> 268 <a 269 class="" 270 href="#EmielKrahmer" 271 data-toggle="collapse" 272 data-target="#collapse2-2" 273 aria-expanded="true" 274 aria-controls="collapse2-2" 275 > 276 Emiel Krahmer</a>, Tilburg University 277 </div> 278 <div 279 id="collapse2-2" 280 class="collapse" 281 aria-labelledby="headingOne" 282 data-parent="#accordionExample" 283 > 284 <div class="card-body"> 285 <div class="row"> 286 <div class="col-md-2 col-sm-5"> 287 <img src="https://inlgmeeting.github.io/static/images/emielkrahmer.jpg" width="100%" class="img-thumbnail" /> 288 </div> 289 <div class="col-md-10 col-sm-6"> 290 <h3> 291 292 From Generating Personalised Risk Descriptions to Data-driven Health Narratives: Applying NLG to Healthcare Data 293 294 </h3> 295 296 <span class="font-weight-bold">Abstract:</span> 297 <p>Even though the health domain has been mentioned as a potential application domain for NLG since the early days of the field, one thing that has changed recently is the emergence of large and growing amounts of patient-generated health data in hospitals and other care facilities (think of self-reported outcome measures, electronic health records, registry data). Hospitals are urgently looking for ways to make this data accessible in a personalised manner for both patients and clinicians. Naturally, this is a task for which NLG lends itself very well. In this talk, I describe how traditional NLG tasks, such as the generation of referring expressions and of narratives, re-emerge in this health domain. I also highlight which particular evaluation questions this raises, such as, for example, what kind of information do patients actually want? In which format do they prefer this information? What cognitive implications does access to this information have? In the final part of the talk I touch upon a number of broader questions, such as is there room for transformers in this application domain, and what are ethical and privacy issues for this kind of application.</p> 298 299 <br /> 300 301 <span class="font-weight-bold">Bio:</span> 302 Prof. Dr. Emiel Krahmer is a full professor in the Tilburg School of Humanities and Digital Sciences. In his research, he studies how people communicate with each other, and how computers can be taught to communicate in a similar fashion, to improve communication between humans and machines. His current research is positioned at the intersection of artificial intelligence, natural language processing and human communication studies, and has applications in, for example, media (e.g., automatic moderation and summarization of online discussions), health (e.g., data-driven treatment decision aids; chatbots for smoking cessation) and education (e.g., social robots teaching children a second language). 303 304 </div> 305 </div> 306 </div> 307 </div> 308 </div> 309 </div> 310</div> 311 312 313<div class="row"> 314 <div class="col-12" id="accordionExample"> 315 <div class="card m-2"> 316 <div class="card-header"> 317 <a 318 class="" 319 href="#MargaretMitchell" 320 data-toggle="collapse" 321 data-target="#collapse3-3" 322 aria-expanded="true" 323 aria-controls="collapse3-3" 324 > 325 Margaret Mitchell</a>, Huggingface 326 </div> 327 <div 328 id="collapse3-3" 329 class="collapse" 330 aria-labelledby="headingOne" 331 data-parent="#accordionExample" 332 > 333 <div class="card-body"> 334 <div class="row"> 335 <div class="col-md-2 col-sm-5"> 336 <img src="https://inlgmeeting.github.io/static/images/margaret.jpg" width="100%" class="img-thumbnail" /> 337 </div> 338 <div class="col-md-10 col-sm-6"> 339 <h3> 340 341 Advancing Natural Language Generation (for better or worse) 342 343 </h3> 344 345 <br /> 346
347 <span class="font-weight-bold">Bio:</span> 348 Margaret Mitchell is a researcher working on Ethical AI, currently focused on the ins and outs of ethics-informed AI development in tech. She has published over 50 papers on natural language generation, assistive technology, computer vision, and AI ethics, and holds multiple patents in the areas of conversation generation and sentiment classification. She currently works at Hugging Face driving forward work in the ML development ecosystem, ML data governance, AI evaluation, and AI ethics. She previously worked at Google AI as a Staff Research Scientist, where she founded and co-led Google's Ethical AI group, focused on foundational AI ethics research and operationalizing AI ethics Google-internally. Before joining Google, she was a researcher at Microsoft Research, focused on computer vision-to-language generation; and was a postdoc at Johns Hopkins, focused on Bayesian modeling and information extraction. She holds a PhD in Computer Science from the University of Aberdeen and a Master's in computational linguistics from the University of Washington. While earning her degrees, she also worked from 2005-2012 on machine learning, neurological disorders, and assistive technology at Oregon Health and Science University. She has spearheaded a number of workshops and initiatives at the intersections of diversity, inclusion, computer science, and ethics. Her work has received awards from Secretary of Defense Ash Carter and the American Foundation for the Blind, and has been implemented by multiple technology companies. She likes gardening, dogs, and cats. 349 350 </div> 351 </div> 352 </div> 353 </div> 354 </div> 355 </div> 356</div> 357 358 359<div class="row"> 360 <div class="col-12" id="accordionExample"> 361 <div class="card m-2"> 362 <div class="card-header"> 363 <a 364 class="" 365 href="#speaker4" 366 data-toggle="collapse" 367 data-target="#collapse4-4" 368 aria-expanded="true" 369 aria-controls="collapse4-4" 370 > 371 Mohit Bansal</a>, University of North Carolina (UNC) Chapel Hill 372 </div> 373 <div 374 id="collapse4-4" 375 class="collapse" 376 aria-labelledby="headingOne" 377 data-parent="#accordionExample" 378 > 379 <div class="card-body"> 380 <div class="row"> 381 <div class="col-md-2 col-sm-5"> 382 <img src="https://inlgmeeting.github.io/static/images/mohit.png" width="100%" class="img-thumbnail" /> 383 </div> 384 <div class="col-md-10 col-sm-6"> 385 <h3> 386 387 Modeling and Evaluating Faithful Generation in Language and Vision 388 389 </h3> 390 391 <span class="font-weight-bold">Abstract:</span> 392 <p>Faithfulness is a key aspect of accurate and trustworthy generation in diverse modalities such as language and vision. In this talk, I will present work towards modeling and evaluating faithfulness in summarization and multimodal tasks. First, we will discuss our earlier work on multi-task and reinforcement learning methods to incorporate auxiliary faithfulness-promoting skills such as entailment and back-translation validity. We will then describe abstractive summarization models that holistically address the problem of faithfulness during pre-training and fine-tuning. Next, we will explore improved summary faithfulness evaluation methods based on human-automation balance and semantic graph representations. Lastly, we will briefly discuss faithful, fine-grained skill evaluation of text-to-image generation models.</p> 393 394 <br /> 395 396 <span class="font-weight-bold">Bio:</span> 397 Dr. Mohit Bansal is the John R. & Louise S. Parker Professor in the Computer Science department at University of North Carolina (UNC) Chapel Hill. He received his PhD from UC Berkeley and his BTech from IIT Kanpur. His research expertise is in natural language processing and multimodal machine learning, with a particular focus on grounded and embodied semantics, human-like language generation and Q&A/dialogue, and interpretable and generalizable deep learning. He is a recipient of the DARPA Director's Fellowship, NSF CAREER Award, and Army Young Investigator Award. His service includes ACL Executive Committee, ACM Doctoral Dissertation Award Committee, Program Co-Chair for CoNLL 2019, ACL Americas Sponsorship Co-Chair, and Associate/Action
397Editor for TACL, CL, IEEE/ACM TASLP, and CSL journals. 398 399 </div> 400 </div> 401 </div> 402 </div> 403 </div> 404 </div> 405</div> 406 407 408 409 </div> 410</div> 411 412 413 414<!-- Google Analytics -->
415<script 416 async 417 src="https://www.googletagmanager.com/gtag/js?id=UA-" 418></script>
vendor: 1 bytes, line 418
418
419<script> 420 window.dataLayer = window.dataLayer || []; 421 422 function gtag() { 423 dataLayer.push(arguments); 424 } 425 426 gtag("js", new Date()); 427 gtag("config", "UA-"); 428</script>
428 429 430<!-- Footer --> 431<footer class="footer bg-light p-4"> 432 <div class="container"> 433 <p class="float-right"><a href="#">Back to Top</a></p> 434 <p class="text-center">© 2020 INLG 2022 Organizers</p> 435 </div> 436</footer> 437 438<!-- Code for hash tags -->
439<script type="text/javascript"> 440 $(document).ready(function () { 441 if (window.location.hash !== "") { 442 $(`a[href="${window.location.hash}"]`).tab("show"); 443 } 444 445 $("a[data-toggle='tab']").on("shown.bs.tab", function (e) { 446 const hash = $(e.target).attr("href"); 447 if (hash.substr(0, 1) === "#") { 448 const position = $(window).scrollTop(); 449 window.location.replace(`#${hash.substr(1)}`); 450 $(window).scrollTop(position); 451 } 452 }); 453 }); 454</script>
454 455<!--
455<script src="static/js/modules/lazyLoad.js"></script>
455--> 456 457</body> 458</html>
Line numbers count LF bytes from the start of the resource, as the search results do. Vendor segments are library code the classifier recognised; they are stored but not indexed. Bytes are shown as Latin1 characters, one per byte.