1 / 24

QuASI: Question Answering using Statistics, Semantics, and Inference

QuASI: Question Answering using Statistics, Semantics, and Inference. Marti Hearst, Jerry Feldman, Chris Manning, Srini Narayanan Univ. of California-Berkeley / ICSI / Stanford University. Dynamic Probabilistic Inference for event structure. Srini Narayanan Jerry Feldman

hewitt
Download Presentation

QuASI: Question Answering using Statistics, Semantics, and Inference

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. QuASI:Question Answering using Statistics, Semantics, and Inference Marti Hearst, Jerry Feldman, Chris Manning, Srini Narayanan Univ. of California-Berkeley / ICSI / Stanford University

  2. Dynamic Probabilistic Inference for event structure Srini Narayanan Jerry Feldman ICSI and UC Berkeley Jan-June 2003

  3. Scenario Question (CNS data) • How has Al-Qaida conducted its efforts to acquire WMD capability and what are the results of this endeavor? • Even with perfect parsing, to answer this question, we have to go beyond words in the input in at least the following ways: • Multiple sources (reports, evidence, news) • Fusing information from unreliable sources (P(Information = true | source)) • Non-monotonicity. Previous assertions or predictions may have to be retracted in the light of new evidence. • Modeling complex events • Evolving events with complex dynamics including sequence, concurrency, coordination, interruptions and resources.

  4. Reasoning about Events for QA • Reasoning about dynamics • Complex event structure • Multiple stages, interruptions, resources • Evolving events • Conditional events, presuppositions. • Nested temporal and aspectual references • Past, future event references • Metaphoric references • Use of motion domain to describe complex events. • Reasoning with Uncertainty • Combining Evidence from Multiple, unreliable sources • Non-monotonic inference • Retracting previous assertions • Conditioning on partial evidence

  5. Previous work • Models of event structure that are able to deal with the temporal and aspectual structure of events • Based on an active semantics of events and a factorized graphical model of complex states. • Models event stages, embedding, multi-level perspectives and coordination. • Event model based on a Stochastic Petri Net representation with extensions allowing hierarchical decomposition. • State is represented as a Temporal Bayes Net (T(D)BN).

  6. Factorized Inference

  7. Quantifying the model

  8. Pilot System Results • Captures fine grained distinctions needed for interpretation • Frame-based Inferences (COLING02) • Aspectual Inferences (Cogsci98, IJCAI 99, COLING02) • Metaphoric Inferences (AAAI 99) • Sufficient Inductive bias for verb learning (Bailey97, CogSci99), construction learning (Chang02, to Appear) • Model for DAML-S (WWW02, Computer Networks 03)

  9. Extensions to Pilot System • Scalable Data Resources • Language Resources/Ontology • Lexicon (Open Source, WordNet, FrameNet) • Conceptual Relations: • Schemas, Maps, Frames, Mental Space • General Principle: Use Semantic Web resources • (DAML, DAML-S, OpenCYC, IEEE SUMO) • Language Analyzer • Construction Parser (ICSI/EML) • Statistical techniques (UCB/Stanford, CU,UTD) • Scalable Domain Representation • Coordinated Probabilistic Relational Models

  10. Problems with DBN • Scaling up to relational structures • Supports linear (sequence) but not branching (concurrency, coordination) dynamics

  11. Structured Probabilistic Inference

  12. Probabilistic inference for QA • Filtering • P(X_t | o_1…t,X_1…t) • Update the state based on the observation sequence and state set • MAP Estimation • Argmaxh1…hnP(X_t | o_1…t, X_1…t) • Return the best assignment of values to the hypothesis variables given the observation and states • Smoothing • P(X_t-k | o_1…t, X_1…t) • modify assumptions about previous states, given observation sequence and state set • Projection/Prediction/Reachability • P(X_t+k | o_1..t, X_1..t) • Predict future states based on observation sequence and state set

  13. PRM (and DBN) inference is hard • Exact Inference Techniques (NP): • Variable Elimination (VE) • Junction-Tree Methods • Approximate inference (NP): • Variational Approximations • Loopy propagation (loses information)

  14. Tractable inference and net topology • Polytree-inference is tractable (Pearl 1990) • Proportional to Network Size • SCFG-inference can be modeled as extended Polytree inference (Narayanan 99) • For more complicated models, exploit relational structure (Pfeffer 99, Kohler et al 00, 02).

  15. Probabilistic Relation Inference • Scalable Representation of • States, domain knowledge, ontologies • (Pfeffer 2000, Koller et al. 2001) • Merges relational database technology with Probabilistic reasoning based on Graphical Models. • Domain entities and relations. • Inter-entity relations are probabilistic functions • Can capture complex dependencies with both simple and composite slot (chains). • Inference exploits structure of the domain

  16. Inference With PRMs SVE inference for a PRM P with q query variables and N attributes is O(Nkbk(m+2)bq) (Pfeffer 2000) • k is the maximum number of interface variables • q is the number of query variables • m is the maximum tree width for any object in P (related to the markov blanket).

  17. Controlling PRM inference • The number of interface variables, k, is related to the number of relations that a variable participates in as well as the number of slot chains that the variable participates in • Careful selection of relations (only part-of) can make inference tractable. • The tree width m depends on the markov blanket of an attribute. • Control of network topology can reduce this.

  18. Adding Time to PRM’s • Since time is another relation, doesn’t increase expressive power. • Significant impact of inference tractability since both k and m may become quite large. • New Algorithm: Exploit the structure of time using the interface and frontier algorithm (Murphy 2002). • Variables at slice t with links to variables at t+1 form the interface • Interface variables d-separate the past (< t) from the future slices (> t). • Allows for on-line inference algorithms similar to inside-outside algorithm for SCFG’s.

  19. The CPRM algorithm • Combines insights from • the SVE algorithm for PRMs (Pfeffer 2000) • the frontier algorithms for temporal models (Murphy 2002) and • Inference algorithms for complex, coordinated events (Narayanan 1999) • Expressive Probabilistic Modeling paradigm with relations and branching dynamics. • Offers principled methods to bound inferential complexity.

  20. Status of CPRM inference • Spring-Summer 2003 • Design Dynamic Probabilistic Relational Models (DPRM) • Initial Design of CPRM inference algorithm • Integrate Parser with existing Pilot System • Steve Sinha • Summer/Fall 2003 • Implement CPRM to replace Pilot System • Nathaniel Smith, Eva Mok • Test CPRM for QA (UTD) • Related Work • Probabilistic OWL (PrOWL) • Probabilistic FrameNet

  21. Conclusion • QA with complex scenarios (such as the CNS scenario/data) needs complex inference that deals with • Relational Structure • Uncertain source and domain knowledge • Complex dynamics and evolving events • We have developed a representation and inference algorithm that is capable of tractable inference for a variety of domains. • We are collaborating with UTD (Sanda Harabagiu) to apply these techniques to QA systems.

More Related