Knowledge Bases

• Type: Block seminar
• Lecturer: Simon Razniewski, Paramita Mirza
• Credits: 7 ECTS credits
• Registration: Course is full, unfortunately no further registrations can be accepted
• Dates: November 16 & 23, 2017 (introductory meetings) and March 6 & 7, 2018 (block seminar).

The seminar is a block seminar and will take place on two (consecutive) days at the end of February or beginning of March--the exact days to be agreed with the participants. There will also be two meetings at the beginning of the semester, for which participation is mandatory.

• November 16, 2017 -- Slides for the kick-off meeting are available [pdf]
• November 16, 2017 -- Please fill in the Doodle for the block seminar days
• November 20, 2017 -- Template for seminar paper available [zip]
• November 22, 2017 -- Based on the Doodle, the block seminar dates have been fixed to March 6 and 7
• November 23, 2017 -- Slides from the second meeting are online [pdf]
• December 6, 2017 -- Tentative block seminar schedule is online (see below)

Representation, collection and extraction of general knowledge in knowledge bases (KBs) is at the core of many AI applications. In this seminar, we cover a range of topics around KBs, in particular factual KBs (e.g., Wikidata, YAGO, DBPedia), common-sense KBs (e.g., science knowledge, howto-knowledge, script knowledge) and non-textual KBs (e.g., ImageNet). We explore how these KBs are constructed and how they are used in various applications such as question answering (QA), story/script prediction and biography generation. We also explore learning new facts over KBs.

• October 4, 2017 -- Registration deadline
• November 16, 2017 -- Kick-off meeting (participation is mandatory) [pdf]
  • Time: 11:30 am - 13:00 am
  • Place: Room 23, MPI-Inf building (E 1.4, ground level)
    • Explanation of the structure and organization of the seminar
    • Brief introduction to knowledge bases
    • Presentation of the topics
• November 23, 2017 -- "How to prepare and present a seminar talk" (participation is mandatory)
  • Time: 11:30 am - 13:00 am
  • Place: Room 23, MPI-Inf building (E 1.4, ground level)
    • As this is a block seminar, it is particularly crucial that the students' presentations are of high quality. This lecture aims at preparing the participants in such a way that their slides and presentations will be of high quality.
    • Topic assignment: students prepare a preferred ranked list of proposed topics, we will do the live assignment based on a randomly decided order.
• December 13, 2017, 23:59 -- students send a suggestion of the outline of their seminar paper, including an itemization of the planned content for each section.
• January 31, 2018, 23:59 -- students submit their final seminar paper.
• February 20, 2018, 23:59 -- students send preliminary slides
• March 3, 2018, 23:59 -- students send their final slides which they will use in the block seminar
• March 6, 2018 -- Block seminar, Day 1 - Room 433, MPI-Inf building (E 1.4, 4th floor)
• March 7, 2018 -- Block seminar, Day 2 - Room 433, MPI-Inf building (E 1.4, 4th floor)

Format: 25 minutes presentation, 10 minutes discussion

March 6:
 10:00-10:35 1: Collaborative KBs: Wikidata (Safura Isayeva)
 10:35-11:10 2: Structured information extraction: DBpedia and YAGO (Mang Zhao)
   10 minutes break
 11:20-11:55 3: KB population in the TAC 2016 challenge (Nitisha Jain)
 11:55-12:30 4: General common-sense KBs: ConceptNet and WebChild (Xueting Li)
   1 hour lunch break
 13:30-14:05 5: Domain-specific activity KBs (Anu Goel)
 14:05-14:40 6: The Allen AI science challenge & building a science KB: Aristo (Frederick Schmitt)
   10 minutes break
 14:50-15:25 7: KB association rule mining (Joscha Cüppers)

March 7:
 10:00-10:35 8: Enriching KBs with named events: EVIN (Harshita Jhavar)
 10:35-11:10 9: Exploring and profiling KBs (Adrian Spirescu)
   10 minutes break
 11:20-11:55 10: KB question answering (Shrestha Ghosh)
 11:55-12:30 11: Hybrid question answering using KBs and text (Aydan Rende)
   1 hour lunch break
 13:30-14:05 12: Non-encyclopedic QA in the science domain (Khansa Rekik)
 14:05-14:40 13: Biography generation (David Neisens)
   5 minutes break
 14:45-15:00 Closing remarks

• Participation in the kick-off meeting, the "How to prepare and present a seminar talk" lecture, and both days of the block seminar is mandatory.
• Students will be assigned a particular topic and have to submit a seminar paper (template will be provided) and give a presentation (25 minutes + 10 minutes for discussion) over the topic.
• Grading will be based on:
  • the report
  • the presentation
  • knowledge on the subject (as evidenced in the discussion after the presentation)
  • activity in the discussions
  • ability to stick to deadlines
• Attention: According to the study regulations, you are only allowed to withdraw from the seminar within three weeks after the kick-off meeting, i.e., until December 7. Later withdrawal counts as "failed".

Area I: Knowledge Bases

• 1: Collaborative KBs: Wikidata -- Safura Isayeva (Simon)
  • Wikidata: a free collaborative knowledge base (Vrandečić & Krötzsch, CACM 2014) [pdf]
  • Introducing Wikidata to the linked data web (Erxleben et al., ISWC 2014) [pdf]
• 2: Structured information extraction: DBpedia and YAGO -- Mang Zhao (Simon)
  • DBpedia – A large-scale, multilingual knowledge base extracted from Wikipedia (Lehmann, et al., Semantic Web 2015) [pdf]
  • YAGO2: A spatially and temporally enhanced knowledge base from Wikipedia (Hoffart et al., Artificial Intelligence 2013) [pdf]
• 3: KB population in the TAC 2016 challenge -- Nitisha Jain (Paramita)
  • TAC Challenge [link]
• 4: General common-sense KB: ConceptNet and WebChild -- Xueting Li (Paramita)
  • Representing general relational knowledge in ConceptNet 5 (Speer & Harvasi, LREC 2012) [pdf]
  • WebChild: Harvesting and Organizing Commonsense Knowledge from the Web (Tandon et al., WSDM 2014) [pdf]
• 5: Domain-specific activity KBs -- Anu Goel (Paramita)
  • HowTo KB -- Distilling task knowledge from How-To communities (Chu et al., WWW 2017) [pdf]
  • A hierarchical bayesian model for unsupervised induction of script knowledge (Frermann et al., EACL 2014) [pdf]
• 6: The Allen AI science challenge & building a science KB: Aristo -- Frederik Schmitt (Paramita)
  • Domain-targeted, high precision knowledge extraction (Mishra et al., TACL 2017) [pdf]
  • Moving beyond the Turing test with the Allen AI Science Challenge (Schoenick et al., CACM 2016) [pdf]

Area II: Learning over Knowledge Bases

• 7: KB association rule mining -- Joscha Cüppers (Simon)
  • Fast rule mining in ontological knowledge bases with AMIE+ (Galárraga et al., VLDB 2015) [pdf]
• 8: Enriching KBs with Named Events: EVIN -- Harshita Jhavar (Paramita)
  • A Fresh Look on Knowledge Bases: Distilling Named Events from News (Kuzey et al., CIKM 2014) [pdf]

Area III: Using Knowledge Bases

• 9: Exploring and profiling KBs -- Adrian Spirescu (Simon)
  • Wikidata SQID browser [link]
  • Faceted search over RDF-based knowledge graphs (Arenas et al., JWS 2016) [pdf]
  • Loupe - An Online Tool for Inspecting Datasets in the Linked Data Cloud (Mihindukulasooriya et al., ISWC 2015) [pdf]
• 10: KB question answering -- Shrestha Ghosh (Simon)
  • Automated template generation for question answering over knowledge graphs (Abujabal et al., WWW 2017) [pdf]
  • Robust question answering over the web of linked data (Yahya et al., CIKM 2013) [pdf]
• 11: Hybrid question answering using KBs and text -- Aydan Rende (Paramita)
  • Question answering on Freebase via relation extraction and textual evidence (Xu et al., ACL 2016) [pdf]
  • Open question answering over curated and extracted knowledge bases (Fader et al., KDD 2014) [pdf]
• 12: Non-encyclopedic QA in the science domain (continuation of Topic 5) -- Khansa Rekik (Simon)
  • Answering complex questions using open information extraction (Khot et al., ACL 2017) [pdf]
• 13: Biography generation - David Neisens (Simon)
  • Learning to generate one-sentence biographies from Wikidata (Chisholm et al., EACL 2017 [pdf]