Add functionality to display plenary videos

bin/create_hugo_data.py

@@ -494,13 +494,135 @@ def export_events(anthology, builddir, dryrun):
         else:
             data["title"] = f"{anthology.venues[main_venue].name} ({data['year']})"
 
+        # Add talks data if available
+        talks_data = []
+        for idx, talk in enumerate(event.talks or [], 1):
+            # Generate talk ID from video filename if available, otherwise use default pattern
+            if "video" in talk.attachments and talk.attachments["video"].name:
+                # Extract talk ID from video filename like "2022.acl-keynote.2.mp4"
+                video_name = talk.attachments["video"].name
+                if video_name.endswith(".mp4"):
+                    # Remove .mp4 extension to get the talk ID
+                    talk_id = video_name[:-4]
+                else:
+                    talk_id = video_name
+            else:
+                # Fallback to sequential numbering if no video
+                talk_id = f"{event.id}.talk-{idx}"
+
+            talk_data = {
+                "id": talk_id,
+                "title": talk.title.as_text(),
+                "title_html": remove_extra_whitespace(
+                    talk.title.as_html(allow_url=False)
+                ),
+                "speakers": [],  # Process speakers differently
+                "type": talk.type,
+            }
+            # Process speakers - NameSpecification objects
+            for speaker in talk.speakers:
+                speaker_dict = person_to_dict(speaker.id if speaker.id else "", speaker)
+                talk_data["speakers"].append(speaker_dict)
+            # Add video URL if available
+            if "video" in talk.attachments:
+                talk_data["video_url"] = talk.attachments["video"].url
+            # Add other attachments
+            attachments = []
+            for att_type, attachment in talk.attachments.items():
+                if att_type != "video":
+                    attachments.append(
+                        {
+                            "filename": attachment.name,
+                            "type": att_type.capitalize(),
+                            "url": attachment.url,
+                        }
+                    )
+            if attachments:
+                talk_data["attachments"] = attachments
+            talks_data.append(talk_data)
+        if talks_data:
+            data["talks"] = talks_data
+
         all_events[event.id] = data
 
     if not dryrun:
         with open(f"{builddir}/data/events.json", "wb") as f:
             f.write(ENCODER.encode(all_events))
 
 
+def export_talks(anthology, builddir, dryrun):
+    # Export talks data
+    all_talks = {}
+    print("Exporting talks...")
+
+    for event in anthology.events.values():
+        if not event.talks:
+            continue
+
+        for idx, talk in enumerate(event.talks, 1):
+            # Generate talk ID from video filename if available, otherwise use default pattern
+            if "video" in talk.attachments and talk.attachments["video"].name:
+                # Extract talk ID from video filename like "2022.acl-keynote.2.mp4"
+                video_name = talk.attachments["video"].name
+                if video_name.endswith(".mp4"):
+                    # Remove .mp4 extension to get the talk ID
+                    talk_id = video_name[:-4]
+                else:
+                    talk_id = video_name
+            else:
+                # Fallback to sequential numbering if no video
+                talk_id = f"{event.id}.talk-{idx}"
+
+            # Create talk data
+            talk_data = {
+                "id": talk_id,
+                "event_id": event.id,
+                "event_title": event.title.as_text() if event.title else f"{event.id}",
+                "title": talk.title.as_text(),
+                "title_html": remove_extra_whitespace(
+                    talk.title.as_html(allow_url=False)
+                ),
+                "speakers": [],
+                "type": talk.type,
+            }
+
+            # Process speakers
+            for speaker in talk.speakers:
+                speaker_data = person_to_dict(speaker.id if speaker.id else "", speaker)
+                talk_data["speakers"].append(speaker_data)
+
+            # Add video URL if available
+            if "video" in talk.attachments:
+                talk_data["video_url"] = talk.attachments["video"].url
+                talk_data["video_name"] = talk.attachments["video"].name
+
+            # Add other attachments
+            attachments = []
+            for att_type, attachment in talk.attachments.items():
+                if att_type != "video":
+                    attachments.append(
+                        {
+                            "filename": attachment.name,
+                            "type": att_type.capitalize(),
+                            "url": attachment.url,
+                        }
+                    )
+            if attachments:
+                talk_data["attachments"] = attachments
+
+            # Add location and dates from event
+            if event.location:
+                talk_data["location"] = event.location
+            if event.dates:
+                talk_data["dates"] = event.dates
+
+            all_talks[talk_id] = talk_data
+
+    if not dryrun:
+        with open(f"{builddir}/data/talks.json", "wb") as f:
+            f.write(ENCODER.encode(all_talks))
+
+
 def export_sigs(anthology, builddir, dryrun):
     all_sigs = {}
     print("Exporting SIGs...")
@@ -551,6 +673,7 @@ def export_anthology(anthology, builddir, clean=False, dryrun=False):
     export_people(anthology, builddir, dryrun)
     export_venues(anthology, builddir, dryrun)
     export_events(anthology, builddir, dryrun)
+    export_talks(anthology, builddir, dryrun)
     export_sigs(anthology, builddir, dryrun)
 
 

data/xml/2021.acl.xml

@@ -12778,108 +12778,108 @@ The source code has been made available at \url{https://github.com/liam0949/DCLO
     <talk>
       <title>Keynote 1: Advancing Technological Equity in Speech and Language Processing</title>
       <speaker><first>Helen</first><last>Meng</last></speaker>
-      <url type="video">2021.acl.keynote1.mp4</url>
+      <url type="video">2021.acl-keynote.1.mp4</url>
     </talk>
     <talk>
       <title>Keynote 2: Learning and Processing Language from Wearables: Opportunities and Challenges</title>
       <speaker><first>Alejandrina</first><last>Cristia</last></speaker>
-      <url type="video">2021.acl.keynote2.mp4</url>
+      <url type="video">2021.acl-keynote.2.mp4</url>
     </talk>
     <talk>
       <title>Keynote 3: Reliable Characterizations of <fixed-case>NLP</fixed-case> Systems as a Social Responsibility</title>
       <speaker><first>Christopher</first><last>Potts</last></speaker>
-      <url type="video">2021.acl.keynote3.mp4</url>
+      <url type="video">2021.acl-keynote.3.mp4</url>
     </talk>
     <talk>
       <title>Opening Session</title>
       <speaker><first>Chengqing</first><last>Zong</last></speaker>
       <speaker><first>Roberto</first><last>Navigli</last></speaker>
       <speaker><first>Fei</first><last>Xia</last></speaker>
       <speaker><first>Wenjie</first><last>Li</last></speaker>
-      <url type="video">2021.acl.opening-session.mp4</url>
+      <url type="video">2021.acl-opening.1.mp4</url>
     </talk>
     <talk>
       <title>Presidential Address</title>
       <speaker><first>Rada</first><last>Mihalcea</last></speaker>
-      <url type="video">2021.acl.presidential-address.mp4</url>
+      <url type="video">2021.acl-presidential.1.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: Business Manager Report</title>
       <speaker><first>Priscilla</first><last>Rasmussen</last></speaker>
-      <url type="video">2021.acl.business-meeting1.mp4</url>
+      <url type="video">2021.acl-business.1.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: Conference Officer Report</title>
       <speaker><first>Yusuke</first><last>Miyao</last></speaker>
-      <url type="video">2021.acl.business-meeting2.mp4</url>
+      <url type="video">2021.acl-business.2.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: <fixed-case>EACL</fixed-case> Report</title>
       <speaker><first>Shuly</first><last>Wintner</last></speaker>
-      <url type="video">2021.acl.business-meeting3.mp4</url>
+      <url type="video">2021.acl-business.3.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: <fixed-case>NAACL</fixed-case> Report</title>
       <speaker><first>Colin</first><last>Cherry</last></speaker>
-      <url type="video">2021.acl.business-meeting4.mp4</url>
+      <url type="video">2021.acl-business.4.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: <fixed-case>CL</fixed-case> Report</title>
       <speaker><first>Hwee Tou</first><last>Ng</last></speaker>
-      <url type="video">2021.acl.business-meeting5.mp4</url>
+      <url type="video">2021.acl-business.5.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: <fixed-case>TACL</fixed-case> Report</title>
       <speaker><first>Brian</first><last>Roark</last></speaker>
-      <url type="video">2021.acl.business-meeting6.mp4</url>
+      <url type="video">2021.acl-business.6.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: <fixed-case>ACL</fixed-case> <fixed-case>R</fixed-case>olling <fixed-case>R</fixed-case>eview Report</title>
       <speaker><first>Amanda</first><last>Stent</last></speaker>
-      <url type="video">2021.acl.business-meeting7.mp4</url>
+      <url type="video">2021.acl-business.7.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: <fixed-case>ACL</fixed-case> <fixed-case>A</fixed-case>nthology Report</title>
       <speaker><first>Matt</first><last>Post</last></speaker>
-      <url type="video">2021.acl.business-meeting8.mp4</url>
+      <url type="video">2021.acl-business.8.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: Professional Conduct Committee Report</title>
       <speaker><first>Graeme</first><last>Hirst</last></speaker>
       <speaker><first>Emily M.</first><last>Bender</last></speaker>
-      <url type="video">2021.acl.business-meeting9.mp4</url>
+      <url type="video">2021.acl-business.9.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: Publicity Director Report</title>
       <speaker><first>Barbara</first><last>Plank</last></speaker>
       <speaker><first>Sarvnaz</first><last>Karimi</last></speaker>
       <speaker><first>Caroline</first><last>Lawrence</last></speaker>
-      <url type="video">2021.acl.business-meeting10.mp4</url>
+      <url type="video">2021.acl-business.10.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: Secretary's Report</title>
       <speaker><first>Shiqi</first><last>Zhao</last></speaker>
-      <url type="video">2021.acl.business-meeting11.mp4</url>
+      <url type="video">2021.acl-business.11.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: Treasurer's Report</title>
       <speaker><first>David</first><last>Yarowsky</last></speaker>
-      <url type="video">2021.acl.business-meeting12.mp4</url>
+      <url type="video">2021.acl-business.12.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: Sponsorship Director Report</title>
       <speaker><first>Chris</first><last>Callison-Burch</last></speaker>
-      <url type="video">2021.acl.business-meeting13.mp4</url>
+      <url type="video">2021.acl-business.13.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: <fixed-case>ACL</fixed-case> 2023 Call for Bids</title>
       <speaker><first>Timothy</first><last>Baldwin</last></speaker>
-      <url type="video">2021.acl.business-meeting111.mp4</url>
+      <url type="video">2021.acl-business.14.mp4</url>
     </talk>
     <talk>
       <title>Business Meeting: <fixed-case>ACL</fixed-case> 2024 Call for Bids</title>
       <speaker><first>Iryna</first><last>Gurevych</last></speaker>
-      <url type="video">2021.acl.business-meeting121.mp4</url>
+      <url type="video">2021.acl-business.15.mp4</url>
     </talk>
     <talk>
       <title>Panel: Green <fixed-case>NLP</fixed-case></title>
@@ -12894,23 +12894,23 @@ The source code has been made available at \url{https://github.com/liam0949/DCLO
       <speaker><first>Mona</first><last>Diab</last></speaker>
       <speaker><first>Iryna</first><last>Gurevych</last></speaker>
       <speaker><first>Yue</first><last>Zhang</last></speaker>
-      <url type="video">2021.acl.panel.mp4</url>
+      <url type="video">2021.acl-panel.1.mp4</url>
     </talk>
     <talk>
       <title>Distinguished Service Awards and Test of Time Awards Session</title>
       <speaker><first>Rada</first><last>Mihalcea</last></speaker>
-      <url type="video">2021.acl.test-of-time-award.mp4</url>
+      <url type="video">2021.acl-award.1.mp4</url>
     </talk>
     <talk>
       <title>Lifetime Achievement Award Session</title>
       <speaker><first>Rada</first><last>Mihalcea</last></speaker>
       <speaker><first>Junichi</first><last>Tsujii</last></speaker>
-      <url type="video">2021.acl.lifetime-achievement-award.mp4</url>
+      <url type="video">2021.acl-award.2.mp4</url>
     </talk>
     <talk>
       <title>Best Papers Awards Session</title>
       <speaker><first>Timothy</first><last>Baldwin</last></speaker>
-      <url type="video">2021.acl.best-papers.mp4</url>
+      <url type="video">2021.acl-award.3.mp4</url>
     </talk>
     <talk>
       <title>Closing Session</title>
@@ -12925,7 +12925,7 @@ The source code has been made available at \url{https://github.com/liam0949/DCLO
       <speaker><first>Roberto</first><last>Navigli</last></speaker>
       <speaker><first>Fei</first><last>Xia</last></speaker>
       <speaker><first>Maggie</first><last>Li</last></speaker>
-      <url type="video">2021.acl.closing-session.mp4</url>
+      <url type="video">2021.acl-closing.1.mp4</url>
     </talk>
     <colocated>
       <volume-id>2021.findings-acl</volume-id>

data/xml/2021.emnlp.xml

@@ -14122,25 +14122,25 @@
     <talk>
       <title>Keynote 1: Where next? Towards multi-text consumption via three inspired research lines</title>
       <speaker><first>Ido</first><last>Dagan</last></speaker>
-      <url type="video">2021.emnlp.keynote1.mp4</url>
+      <url type="video">2021.emnlp-keynote.1.mp4</url>
     </talk>
     <talk>
       <title>Keynote 2: The language system in the human brain</title>
       <speaker><first>Evelina</first><last>Fedorenko</last></speaker>
-      <url type="video">2021.emnlp.keynote2.mp4</url>
+      <url type="video">2021.emnlp-keynote.2.mp4</url>
     </talk>
     <talk>
       <title>Keynote 3: <fixed-case>LT4All</fixed-case>!? Rethinking the Agenda</title>
       <speaker><first>Steven</first><last>Bird</last></speaker>
-      <url type="video">2021.emnlp.keynote3.mp4</url>
+      <url type="video">2021.emnlp-keynote.3.mp4</url>
     </talk>
     <talk>
       <title>Opening Session</title>
       <speaker><first>Sien</first><last>Moens</last></speaker>
       <speaker><first>Xuanjing</first><last>Huang</last></speaker>
       <speaker><first>Lucia</first><last>Specia</last></speaker>
       <speaker><first>Scott</first><last>Yih</last></speaker>
-      <url type="video">2021.emnlp.opening-session.mp4</url>
+      <url type="video">2021.emnlp-opening.1.mp4</url>
     </talk>
     <talk>
       <title>Best Papers Awards Session and Closing Session</title>
@@ -14151,7 +14151,7 @@
       <speaker><first>Key-Sun</first><last>Choi</last></speaker>
       <speaker><first>Noah A.</first><last>Smith</last></speaker>
       <speaker><first>Chia-Hui</first><last>Chang</last></speaker>
-      <url type="video">2021.emnlp.closing-session.mp4</url>
+      <url type="video">2021.emnlp-closing.1.mp4</url>
     </talk>
     <colocated>
       <volume-id>2021.findings-emnlp</volume-id>