1 / 21

Computational Implicatures for Advanced Question Answering

Computational Implicatures for Advanced Question Answering. Sanda Harabagiu, Alessandro Moschitti, Adrian Atanasiu, Paul Morarescu. Question Processing. There are many reasons for which current QA systems cannot accurately produce answers:

theo
Download Presentation

Computational Implicatures for Advanced Question Answering

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. Computational Implicatures for Advanced Question Answering Sanda Harabagiu, Alessandro Moschitti, Adrian Atanasiu, Paul Morarescu

  2. Question Processing • There are many reasons for which current QA systems cannot accurately produce answers: • Questions are too complex – need translations in sets of simpler questions • Sometimes implicit knowledge is presupposed • Pragmatic knowledge of the domain • Recognition of non-literal expressions, followed by coercion into intended knowledge

  3. Implicit Knowledge • Such knowledge is not directly derivable from the context of question • It belongs either to world knowledge or to knowledge reported/posted in media articles • It belongs to the context of the search • It belongs to the domain knowledge accessible to anyone with expertise in the domain of interest

  4. Two Forms of Question Implicatures • Form 1: Background description Question literal, but there are implicatures between the background description and the question • Example: Q1(Analyst): Recent events in Afhganistan. How have they affected efforts to curb production on opium in that country? Implication +translation into simpler question: How have recent events affected opium production in Afghanistan?

  5. The answers How have recent events affected opium production in Afghanistan? • A1: Last fall, as the United States launched its bombing campaign against the Taliban regime, cash-stripped farmers and warlords eager to make a profit sowed the country’s fields with poppies once again (Source: The Boston Globe; Method: automatic QA) • A2: Since the Taliban regime was ousted and the US-backed regime of Hamid Karzai was installed in Kabul, opium production has risen by one thousand, five hundred tonnes. (Source: Altavista; Method: automatic QA)

  6. Why is it difficult to process Q1? • The question does not state which are the recent events in Afghnistan it implies them. Need to generate several intermediary questions for creating the background: Q1(1):How have recent events affected opium production in Afghanistan? Q1(2):How have recent events affected counternarcotics operations? • Q1 has two anaphors: they referring to recent eventsand that country referring to Aghanistan. Position. • Expected answer type: MANNER (action: curb production of opium)

  7. Source for Semantics • WordNet: synset (control, hold in, hold, contain, check, curb, moderate) - Paraphrases: production of opium = opium production What is being done to control opium production in Afghanistan? A1: The UN drug control programme on Friday welcomed a decision by Afghanistan’s interim government to offer opium farmers US$250 per destroyed field. Recent events

  8. Processing background questions • Generate background information • Series of questions • Generate context for processing simpler questions. • Recognize expected answer from the context of the background

  9. Case 2: Interpretation relying on Pragmatic Knowledge Example of Y/N question: Q2: Will George W. Bush survive the Democrats attacks? 1. But they are scaring the Democrats , who are demonstrating palpable fear that in a swing state such as Oregon , where the race between Al Gore and George W. Bush is too close to call , the outsize support for Nader is going to hand the White House to the Republicans...[view] 2. Of all the talented people in the Clinton administration , Bush saw fit to keep only two on the job : Dick Clarke , who ran counterterrorism for the National Security Council , and George Tenet , director of the CIA...[view] 3. Though there have been plenty of policy disagreements , the Democrats have stood behind their commander in chief , whatever their doubts about his fitness for office or how he attained it...[view] 4. " George H.W. Bush attacked Michael Dukakis 's patriotism throughout the 1988 presidential - election campaign...[view] 5. In his speech before hundreds of students , Bradley implored the audience not to vote for Nader...[view]

  10. What is the implication Selectional constraints Survive Dangerous situation George W. Bush Democrat’s attacks Semantic dependency derivable from the parse

  11. Two Solutions for Pragmatic Knowledge • Rapidly Formatted Knowledge Bases  “rapidly” is still time consuming • Ad-hoc knowledge on-demand  Generate questions when knowledge is needed • Knowledge validation - redundancy on the web - redundancy in categorized text Support Vector Machines for learning features of ad-hoc categories • Generate Bayesian Networks (probabilistic reasoning) • Use Auto-epistemic logic

  12. Pragmatic Knowledge Auto-epistemic Logic Organize knowledge + belief operators World1 World2 Worldn Ad-Hoc Text Categorization based on Support Vector Machines Op1 Op2 Opn Generates predominant concepts and their featured weights Bayesian Networks Answer Mining Capture beliefs that The epistemic worlds are plausible Question Generation and Processing for Populating possible worlds

  13. Auto-epistemic logic Attack(Democrat) Opposed-attack(Republican) Attacks(x,y) actions(x,y) / positions(x,y) / statements(x,y) Three worlds in auto-epistemic logic (HAEL-style) Based on generalizations of the most Representative features in the ad-hoc Category involving George W. Bush and the Democrats Empirical method of generating Ad-hoc categories

  14. Pragmatic knowledge coercion - Where do we start? Republicans Opposition Democrats Actions w1 Positions w2 Statements w3 Organized as AutoEpistemic Logic worlds in HAEL–style (Konolidge). + two operators: Hypothesis – accounts for the best implicatures Stength– accounts for the coercion Modeled as Baysian Networks

  15. Populating possible worlds How do we populate each world? Actions: select the most general concepts and use it for answer mining U.S. President has an agenda organized, prioritized actions Pose to a Q/A system the question: What items are on the agenda of President Bush? The most redundant answer on the www (Oct 10, 2002): War and recession top President Bush’s agenda. war(a) recession(b) find the context of these items, to enrich the world of actions.

  16. Text Mining • For finding the arguments of the newly discovered concepts. 1/ Create ad-hoc category WAR a) generate topical features from WordNet for the new category b) categorize texts with the new features introduced in the SVM model 2/ Detect dominant argument of WAR a) collect windows of 10 words surrounding the most popular feature word b) find the most general semantic category of the most frequent class of words war – has country as semantic category of the dominant argument. Which country?? Q/A system IRAQ

  17. Validation of Text Mining • Study the usage of FrameNet in deriving pragmatic knowledge by combining extracted information with relational semantics from WN • To date: we have obtained a highly accurate method of classifying any sentence by FrameNet frame (Recent result f-measure = 89%)

  18. Using Pragmatic Knowledge for Deriving Implicatures Q: Are Democrats for or against war on IRAQ? The Democrats’ arguments fall closer to the State department’s, which are few and simple: 1) Bush has to “make the case” for war on Iraq. That means prove that Saddam Hussein has chemical or nuclear weapons. 2) Bush must get support for attack from other countries in the world, especially from Europe and the states surrounding Iraq (which has been a failure thus far). 3) Specify the extent of the commitment or resources, troops, money etc. this project is estimated to cost. 4) Involve the people in the decision-making, or better yet Congress. 5) and some are calling for a program of nation-building. The first point is the main one Democrats are repeating, and the rest get less airplay.

  19. Answer mining for implicatures Q21: Did Bush convince law makers/Congress that US must attack IRAQ? Q22: What is the US Congress resolution on war on IRAQ? Q23: How did George W Bush make the case on war on IRAQ? A4. the past few days. [spacer.gif] [icon0 - print.gif] PRINT [icon0 – discuss.gif] DISCUSSION [icon0 - home.gif] CHINESE [icon0 - sendmail.gif] SEND TO FRIEND [spacer.gif] A choice between war and peace has never been an easy one , but the US Congress swiftly passed a resolution granting President George W. Bush broad authority to act against Iraq after a brief debate over the past few days. This is in sharp contrast with the way the Congress behaved more than a decade ago when the majority of...[view]

  20. Plausible answers Q2: Will George W. Bush survive the Democrats attacks? A4. the past few days. [spacer.gif] [icon0 - print.gif] PRINT [icon0 – discuss.gif] DISCUSSION [icon0 - home.gif] CHINESE [icon0 - sendmail.gif] SEND TO FRIEND [spacer.gif] A choice between war and peace has never been an easy one , but the US Congress swiftly passed a resolution granting President George W. Bush broad authority to act against Iraq after a brief debate over the past few days. This is in sharp contrast with the way the Congress behaved more than a decade ago when the majority of...[view] Hypothesis(Q22) – was the highest among all possible paths from Q2 Stength(Q22)– measures the plausible quality of the coerced knowledge that enabled Q22

  21. Future Plans • Model auto-epistemic logic assertions and operators • Quantify the plausibility with Bayesian Networks • Formalize generation of implicatures • Study various ways of rejecting implicatures

More Related