1 / 61

Relational Inference for Wikification

Relational Inference for Wikification. Xiao Cheng and Dan Roth University of Illinois at Urbana-Champaign. Wikification.

sondra
Download Presentation

Relational Inference for Wikification

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Relational Inference for Wikification Xiao Cheng and Dan Roth University of Illinois at Urbana-Champaign

  2. Wikification Blumenthal (D) is a candidate for the U.S. Senate seat now held by Christopher Dodd (D), and he has held a commanding lead in the race since he entered it. But the Times report has the potential to fundamentally reshape the contest in the Nutmeg State. Blumenthal (D) is a candidate for the U.S. Senate seat now held by Christopher Dodd(D), and he has held a commanding lead in the race since he entered it. But the Times report has the potential to fundamentally reshape the contest in the Nutmeg State.

  3. Applications • Knowledge Acquisition via Grounding • Coreference Resolution • Learning-based multi-sieve co-reference resolution with knowledge (Ratinov et al. 2012) • Information Extraction • Unsupervised relation discovery with sense disambiguation (Yao et al. 2012) • Automatic Event Extraction with Structured Preference Modeling (Lu and Roth, 2012 ) • Text Classification • Gabrilovichand Markovitch, 2007; Chang et al., 2008 • Entity Linking

  4. Challenges • Ambiguity • Concepts outside of Wikipedia (NIL) • Blumenthal? • Variability • Scale • Millions of labels Blumenthal (D) is a candidate for the U.S. Senate seat now held by Christopher Dodd(D), and he has held a commanding lead in the race since he entered it. But the Times report has the potential to fundamentally reshape the contest in the Nutmeg State. The New York Times The Times Times CT The Nutmeg State Connecticut

  5. Challenges • State-of-the-art systems (Ratinov et al. 2011) can achieve the above with local and global statistical features • Reaches bottleneck around 70%~ 85% F1 on non-wiki datasets • What is missing? Blumenthal (D) is a candidate for the U.S. Senate seat now held by Christopher Dodd(D), and he has held a commanding lead in the race since he entered it. But the Times report has the potential to fundamentally reshape the contest in the Nutmeg State.

  6. Motivating Example Mubarak, the wife of deposed Egyptian President Hosni Mubarak, … Egyptian President Hosni Mubarak , the of deposed , … Mubarak wife • What are we missing with Bag of Words (BOW) models? • Who is Mubarak? • Constraining interaction between concepts • (Mubarak, wife, Hosni Mubarak)

  7. Relational Inference for Wikification Mubarak, the wife of deposed Egyptian President Hosni Mubarak, … • (Mubarak, wife, Hosni Mubarak) • Our contribution • Identify key textual relations for Wikification • A global inference framework to incorporate relational knowledge • Significant improvement over state-of-the-art systems

  8. Talk Outline • Why Wikification? • Introduction • Motivation • Approach • Wikification Pipeline • Formulation • Relational Analysis • Evaluation • Result • Entity Linking

  9. Wikification Pipeline 1 - Mention Segmentation ...ousted long time Yugoslav President Slobodan Milošević in October. Mr. Milošević's Socialist Party… sub-NP (Noun Phrase) chunks NER Regular expressions

  10. Wikification Pipeline 1 - Mention Segmentation ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party…

  11. Wikification Pipeline 2 - Candidate Generation ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party…

  12. Wikification Pipeline 3 - Candidate Ranking ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party… Local and global statistical features

  13. Wikification Pipeline 4 – Determine NILs ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party… Is the top candidate really what the text referred to?

  14. Talk Outline • Why Wikification? • Introduction • Motivation • Approach • Wikification Pipeline • Formulation • Relational Analysis • Evaluation • Result • Entity Linking

  15. Formulation (0) Mubarak, the wife of deposed Egyptian President Hosni Mubarak, … • (Mubarak, wife, Hosni Mubarak) • Intuition • Promote pairs of concepts coherent with textual relations

  16. Formulation (1) weight to output Whether to output th candidate of the th mention weight of a relation Whether a relation exists between and Formulate as an Integer Linear Program (ILP): If no relation exists, collapse to the non-structured decision

  17. Formulation (2) ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party… r(1,2)34 r(4,3)34 • eki: whether a concept is chosen • ski : score of a concept • r(k,l)ij: whether a relation is present • w(k,l)ij: score of a relation

  18. Overall Approach

  19. Relation Identification • ACE style in-document coreference • Extract named entity-only coreference relations with high precision • Syntactico-Semantic relations (Chan & Roth ‘10) • Easy to extract with high precision • Aim for high recall, as false-positives will be verified and discarded • Sparse, but covers ~80% relation instances in ACE2004

  20. Relation Identification ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party…

  21. Overall Approach

  22. Relation Retrieval ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party… • Current approach • Collect known mappings from Wikipedia page titles, hyperlinks… • Limit to top-K candidates based on frequency of links (Ratinov et al. 2011) • What concepts can “Socialist Party” refer to?

  23. Uninformative Mentions

  24. Relation Retrieval ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party… • What concepts can “Socialist Party” refer to? • More robust candidate generation • Identified relations are verified against a knowledge base (DBPedia) • Retrieve relation arguments matching “(Milošević ,?,Socialist Party)” as our new candidates

  25. Relation Retrieval ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party… q1=(Socialist Party of France,?, *Milošević*) q2=(Slobodan Milošević,?,*Socialist Party*) • Query Pruning • Only 2 queries per pair necessary due to strong baseline.

  26. Relation Retrieval

  27. Relation Retrieval ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party…

  28. Overall Approach

  29. Relational Inference ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party…

  30. Relation scoring Relation query Retrieved relation tuple Query scoring as a tie-breaker between multiple relations Explicit relations are stronger than a hyperlink relations Normalize score for each pair of mention to

  31. Relational Inference ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party… 1

  32. Relational Inference - coreference ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party…

  33. Overall Approach

  34. Determine unknown concepts (NILs) Dorothy Byrne, a state coordinator for the Florida Green Party,… nominal mention • How to capture the fact: • “Dorothy Byrne” does not refer to any concept in Wikipedia • Identify coreferent nominal mention relations • Generate better features for NIL classifier

  35. Determine unknown concepts (NILs) Dorothy Byrne, a state coordinator for the Florida Green Party,… nominal mention Create NIL candidate for propagation

  36. Talk Outline • Why Wikification? • Introduction • Motivation • Approach • Wikification Pipeline • Formulation • Relational Analysis • Evaluation • Result • Entity Linking

  37. Wikification Performance Result

  38. Evaluation – TAC KBP Entity Linking • Task Definition • Links a named entity in a document to either a TAC Knowledge Base (TAC KB) node or NIL • Cluster NIL entities • Relevant Tasks • Wikification • Cross-document coreference

  39. Evaluation – TAC KBP Entity Linking *Median of top 14 systems • Run Relational Inference (RI) Wikifier “as-is”: • No retraining using TAC data

  40. Conclusion Thank you! *Demo will be updated in a week at: http://cogcomp.cs.illinois.edu/demo/wikify Download at: http://cogcomp.cs.illinois.edu/page/download_view/Wikifier • Importance of linguistic and world knowledge • Identification of relational information benefits Wikification • Introduced an inference framework to leverage better language understandings • Future work • Accumulate what we know about NIL concepts • Joint entity typing, coreference and disambiguation • Incorporate more relations

  41. Back up slides BACK UP slides

  42. Massive Textual Information How can we know more from large volumes of possibly unfamiliar raw texts?

  43. Massive Textual Information We naturally “look up” concepts and accumulate knowledge.

  44. Challenges Tuesday marks the 142nd anniversary of an event that forever altered the course ofChicago's development as a then-young American city ? It’s a version of Chicago – the standard classic Macintosh menu font… By the time the New Orleans Saints kicked off at Soldier Field on Sunday afternoon, their woeful history in the Windy City was fully understood.

  45. Challenges Tuesday marks the 142nd anniversary of an event that forever altered the course ofChicago's development as a then-young American city • Ambiguity • Variety • Concepts outside of Wikipedia (NIL) Chicago Chicago font Chicago ? Chicago The Windy City It’s a version of Chicago – the standard classic Macintosh menu font… Chicago By the time the New Orleans Saints kicked off at Soldier Field on Sunday afternoon, their woeful history in the Windy City was fully understood.

  46. Organizing knowledge Estimated size of a printed version of Wikipedia as of August 2010. *Picture courtesy of Wikipedia • Wikipedia as a source of “common sense” knowledge • Naturally bridges rich structured knowledge and text data • Comprehensive for most purposes • ~4.3 million English articles as of today • Cross-lingual

  47. Motivating Example Mubarak, the wife of deposed Egyptian President Hosni Mubarak, … Mubarak Egyptian President wife Hosni Mubarak • Relatively sparse, but act as hard constraints • Intuitively, we need to “de-coreference” this pair of mention • Opens a new dimension in text understanding • helps all stages of Wikification

  48. Wikification Approach ...ousted long time Yugoslav PresidentSlobodan Milošević in October. Mr. Milošević'sSocialist Party… • Mention Segmentation • Use Shallow Parsing, NER and regular expression to generate likely mentions of concepts. • Match nested mentions using dictionary. • Discard unknown mentions.

  49. Ranking Mubarak Egyptian President wife Hosni Mubarak • Features • Local features from Bag of Words (BOW) representation, such as various TFIDF windows. • Global features from Bag of Concepts (BOC) representation. • What are we losing?

More Related