automated ontology elicitation and usage l.
Download
Skip this Video
Loading SlideShow in 5 Seconds..
Automated Ontology Elicitation and Usage PowerPoint Presentation
Download Presentation
Automated Ontology Elicitation and Usage

Loading in 2 Seconds...

play fullscreen
1 / 66

Automated Ontology Elicitation and Usage - PowerPoint PPT Presentation


  • 250 Views
  • Uploaded on

Automated Ontology Elicitation and Usage Adrian Silvescu Computer Science Dept., Iowa State University Outline Introduction, Motivation and Philosophy Abstraction Super-Structuring Ontology Usage Ontology Elicitation Framework Conclusions The Problem: Ontology Elicitation

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Automated Ontology Elicitation and Usage' - ostinmannual


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.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
automated ontology elicitation and usage

Automated Ontology Elicitation and Usage

Adrian Silvescu

Computer Science Dept.,

Iowa State University

outline
Outline
  • Introduction, Motivation and Philosophy
  • Abstraction
  • Super-Structuring
  • Ontology Usage
  • Ontology Elicitation Framework
  • Conclusions
the problem ontology elicitation
The Problem: Ontology Elicitation
  • How to get computers to figure out what an application domain (the world) is all about?
  • How to get computers to derive automatically the set of relevant concepts, entities and relations, pertaining to a certain application domain (or the world)
  • Example: Stock – News data is about: companies, units, CEOs, shares, earnings, cutting jobs, …
time warner shares idle ahead of third quarter earnings report
Time Warner Shares Idle Ahead of Third-Quarter Earnings Report
  • NEW YORK (AP) -- Shares of Media giant Time Warner Inc. were little changed Monday ahead of the company's third-quarter earnings report as investors wonder exactly what chairman Dick Parsons might say about its troubled America Online unit. There was heavy speculation this week the company -- which once had the "AOL" ticker symbol and called itself AOL Time Warner -- might announce job cuts at the online giant. A number of news organizations reported Tuesday that AOL is expected to cut about 700 jobs by the end of the year. There has also been continued speculation Time Warner might even spin off the unit
main paradigm for ontology elicitation
Main Paradigm for Ontology Elicitation
  • There are at least two essential “moves” that people make when attempting to make sense or "structure" a new application domain: Super-Structuring and Abstraction.
  • Super-Structuring is the process of grouping and subsequently naming a set of entities that occur within "proximity" of each other, into a more complex structural unit.
  • Abstraction, on the other hand, establishes that a set of entities belong to the same category, based on a certain notion of “similarity” among these entities, and subsequently names that category.
structuralism vs functionalism
Structuralism vs. Functionalism
  • Structuralism: Meaning (and “similarity” in meaning thereof) is defined in terms of structural features. [e.g., in order to define a chair we are going to say that it has four legs, a rectangular surface on top of them and a back [OOP classes]
  • Functionalism: Functionalism on the other hand asserts that the meaning of an object resides with how it is used. [e.g., a chair is something that I can sit on, and if you intentionally kill somebody with that chair, then the chair is for all practical purposes a weapon. Briefly stated the functionalist claim is that “meaning” is about ends and not about the means by which these ends are met. [OOP interfaces]
  • These are two extremes … mix.
inspirations for the main paradigm
Inspirations for the main paradigm
  • Object Oriented Programming / Software Engineering / UML – these are the main principles used:
    • Composition = Super-Structuring
    • Inheritance = Abstraction
  • Philosophy of linguistics – Words are similar in meaning if they are used in similar contexts – “distributional semantics” hypothesis
    • [Zellig Harris, [British Empiricists, (Jeremy Bentham)]].
abstractions and super structures more concrete
Abstractions and Super-Structures more concrete
  • SuperStructures – Proximal entities should be SuperStructured into a higher level unit if they occur together in the data significantly above chance levels.
  • Abstractions – Entities are similar and should be abstracted together if they occur within similar contexts
example
Example

Step1 data: Mary loves John.

Sue loves Curt.

Mary hates Curt.

Abstractions 1: A1 -> Mary | Sue because they have similar right contexts: loves.

A2 -> John | Curt because they have similar left contexts: loves.

Step 2 data: [Mary, A1] loves [John, A2].

[Sue, A1] loves [Curt, A2].

[Mary, A1] hates [Curt, A2].

Abstractions 2: A3 -> loves | hates because of high similarity between their left and right contexts:

This illustrates how abstraction begets more abstraction (A3 not possible on the raw data).

Step 3 data: [Mary, A1] [loves, A3] [John, A2].

[Sue, A1] [loves, A3] [Curt, A2].

[Mary, A1] [hates, A3][Curt, A2].

Structures 3: S1 -> A1 A3 because it occurs three times

S2 -> A3 A2 because it occurs three times

This illustrates how abstraction begets structuring (S1 and S2 not possible on the raw data)

Structures 4: S3 -> S1 A2

S4 -> A1 S2

algorithm silvescu and honavar 2003
Algorithm [Silvescu and Honavar, 2003]

until a limit criteria has been reached

top_ka_abstractions = Abstract(sequence_data)

top_ks_structures = SuperStructure(sequence_data)

new_sequence_data = Annotate sequence_data with the new abstractions and structures

repeat

SuperStructure(S->AB) - returns the topmost ks structures made out of two components according to an (independence) measure of whether A and B occur together by chance

(e.g., KL(P(AB)||P(A)P(B) )

Abstraction(S-> A | B) - returns the topmost ka abstractions (clusters) of two entities ranked according to the similarity between the probability distributions of their left and right contexts

(e.g., JensenShannon(context(A),context(B)))

validation usefulness for predictive tasks within the application domain
Validation: “Usefulness for Predictive tasks within the application domain”
  • Application domains examples: text data from news and protein sequences
  • Validation: use the structures and abstractions as additional features for learning predictive tasks within the domain:
    • Text categorization – for text data
    • Function prediction – for protein sequences
  • Experiments aimed at assessing the contribution of the new features vs. the basic ones (words for text and amino-acids for protein sequences respectively )
summary
Summary
  • An algorithm that
    • puts together Super-Structuring and Abstraction
    • Re-annotate the data set after deriving a set Abstractions and Super-Structures and allowing further ontology elicitation that would not possible on the raw data.
outline13
Outline
  • Introduction, Motivation and Philosophy
  • Abstraction
  • Super-Structuring
  • Ontology Usage
  • Ontology Elicitation
  • Conclusions
abstraction
Abstraction
  • Entities that occur in similar contexts should be abstracted together
  • We will explore next, one way to “operationalize” this intuition in a class conditional scenario
  • More exactly suppose we have set of mushrooms that are either edible or poisonous and each mushroom is represented as by a set of values associated with nominal attributes such as:
  • odor (9), gill attachment (4), gill spacing (3),… where the numbers in parenthesis are the number of values that each attribute can take
  • Then we can ask how “similar” are the odor values in the context of the associated mushrooms being poisonous or edible
class context distributions
Class Context Distributions

y ~ P(Class|Odor=y)=(.7,.3)

s ~ P(Class|Odor=s)=(.68,.32)

Distance(y,s) =

JS(P(Class|Odor=y), P(Class|Odor=s)

avt learner abstractions kang silvescu zhang and honavar 2004
AVT-Learner (Abstractions)[Kang, Silvescu, Zhang and Honavar, 2004]

Odor

{m,s,y,f,c,p}

{s,y,f,c,p}

Most similar!

{s,y,f}

{a,l,n}

{s,y}

{c,p}

{a,l}

{m}

{y}

{s}

{f}

{c}

{p}

{a}

{l}

{n}

using abstractions
Using Abstractions
  • Annotate the data with the set of features given by abstractions and feed it to a classifier (Propositionalization).
    • For each abstraction add a binary feature that indicates whether a value from that abstraction is present in the current example
  • Use algorithms that are especially designed to handle abstractions
using ontologies
Using Ontologies
  • Propositionalization
  • Specially designed algorithms
na ve bayes classifiers
Naïve Bayes classifiers

Edibility

Gill spacing

Gill attachement

Odor

C={c1,…,ck} be the set of all possible classes x=<a1,…,an> a new example to be classified.

Where the probabilities are estimated from the data

outline22
Outline
  • Introduction, Motivation and Philosophy
  • Abstraction
  • Super-Structuring
  • Ontology Elicitation Framework
  • Ontology Usage
  • Conclusions
superstructuring
SuperStructuring
  • SuperStructures – Proximal entities should be SuperStructured into a higher level unit if they occur together in the data significantly above chance levels.
    • Proximity , Topology
    • Independence tests KL( P(AB)||P(A)P(B) )
    • Compression
experimental setup
Experimental setup
  • Sequence data => natural topology: left,right
  • We have run Super-Structuring 10 times and selected each time the 100 best scoring double according to the KL score – a total of 1000 new features
  • Then we fed the resulting dataset annotated with these new 1000 features to a Naïve Bayes Classifier
experimental results
Experimental Results
  • On protein sequences – function prediction:
    • Selected ~ 1000 functional classes from SWISSPROT that contain more that 10 proteins in each class
    • Super-Structuring improves prediction by 6.54 % (10 fold cross validation) vs. Naïve Bayes
  • On text data – text classification:
    • Reuters 21578 news documents
    • ~12000 of them are assigned to classes based on the type of news they report (e.g., earn, corn, grain, …)
    • Super-Structuring improves 1.43 % (10 fold cross validation) vs. Naïve Bayes
generative models for sequence classification
Generative Models for Sequence Classification

MFDLSKFLPVITPLMIDTAKLCMSSAVSAY … -> Ligase

MGLGWLLYQMGYVKKDFIANQTEGFEDWLA … -> Kinase

Naïve Bayes Case:

na ve bayes kgrams ontology usage
Naïve Bayes-kgrams – Ontology usage

Naïve Bayes

S1

S2

S2

S3

S3

S4

S4

S5

S5

S6

S1

S2

S3

S4

S5

S6

na ve bayes k nbk silvescu andorf dobbs and honavar 2004 andorf silvescu dobbs and honavar 2004
Naïve Bayes ^ k (NBk)[Silvescu, Andorf, Dobbs and Honavar 2004] [Andorf, Silvescu, Dobbs and Honavar 2004]

Naïve Bayes

NBk

S2

S3

S4

S5

S1

S2

S2

S3

S3

S4

S4

S5

S5

S6

S1

S2

S3

S4

S5

S6

JTT

markov models of size k

S1

S1

S2

S2

S3

S3

S4

S4

S5

S5

S6

S6

Markov Models of size k
experimental results protein function classification i
Experimental Results – Protein function classification (I)

Results for the Kinase (GO0004672) dataset. There were a total of 396 proteins and five classes. Species refers to what species the sequences came from. K refers to the number of dependencies used in each algorithm.

experimental results protein function classification ii
Experimental Results – Protein function classification (II)

Results for the Kinase (GO0004672) dataset. There were a total of 396 proteins and five classes. Species refers to what species the sequences came from. K refers to the number of dependencies used in each algorithm.

experimental results protein function classification iii
Experimental Results – Protein function classification (III)

Results for the Kinase(GO0004672) / Ligase(GO001684) dataset. There was a total of 396 proteins and two classes. Species refers to what species the sequences came from. K refers to the number of dependencies used in each algorithm.

outline34
Outline
  • Introduction, Motivation and Philosophy
  • Abstraction
  • Super-Structuring
  • Ontology Usage
  • Ontology Elicitation Framework
  • Conclusions
avt mmk
AVT-MMk

Stopping criterion for Cut Pushing:

MDL Score

Si-k

Si-1

Si

the mdl score
The MDL Score
  • Where M is the model and D is the data
  • In the classification scenario we will use CMDL which replaces the Log Likelihood LL with the Conditional Log Likelihood and the penalty factor is also only on the part of the model that contains class dependencies
taxonomies over k grams
Taxonomies over k-grams

Si-k

Si

Si+1

outline41
Outline
  • Introduction, Motivation and Philosophy
  • Abstraction
  • Super-Structuring
  • Ontology Usage
  • Ontology Elicitation Framework
  • Conclusions
ontology elicitation framework
Ontology elicitation framework
  • Repeat
    • 1. Propose New Concepts - Using the Data
      • e.g., by using Abstraction and SuperStructuring
    • 2. Evaluate the desirability of the proposed New Concepts according to a Scoring Function
    • 3. Select Posited Concepts according to the ranking of the New Concepts by the Scoring Function
    • 4. Annotate Data with Posited Concepts
  • until a termination criterion reached
issues
Issues
  • Controlling the Ontology Elicitation process
    • 1. Mixing of Abstractions and Superstructuring at each step - base case
    • 2. Use Superstructures in order to improve modeling accuracy and abstractions in order to decrease model size and gain generalization accuracy [i.e., associated with better statistical significance due to larger sample size]
types of ontology elicitation
Types of Ontology elicitation
  • Model Free vs. Model Based
    • Model free Scores: such as KL and JS
    • Likelihood / MDL Score
  • Conditional vs. Unconditional
    • The KL and JS [Model Free] and MDL [Model Based] become class conditional
other topics under exploration
Other Topics under exploration
  • Probabilistic Model for Shallow parsing
  • Conditional Probabilistic Models & Regularization
  • Relational Learning
current and future work
Current and Future work
  • Concept formation - Identifying the extensions of well separated concepts from the given structures and abstractions derived by the proposed method and further generalizing these concept extensions by learning corresponding intentional definitions and thus truly completing the ontology elicitation process.
  • Other operations - generalizing the approach in order to incorporate more operations (such as sub-structuring, maybe causality)
  • More tasks - validation on more predictive tasks (interaction site prediction and information extraction respectively) and on more than one task at a time (~ multitask learning) + incorporation of the task(s) bias into the feature / ontology derivation loop.
  • Arbitrary Topologies - exploring the method from sequences to arbitrary topologies (e.g., graphs in order to accommodate relational models)
  • More Domains - Exploring other application domains such as Metabolic Pathways, reinforcement learning, …
  • More ways to use ontologies
summary48
Summary
  • A framework for Ontology Elicitation
  • Learning Algorithms that use ontologies
  • Ontologies
    • improve classification accuracy
    • contribute to the comprehensibility of the model / domain
timeline
Timeline
  • 1. [Nov04-Dec04] Experiments with Model free ontology Elicitation
  • 2. [Nov04-Jan05] Experiments with AVT-NBk and AVT-BN
  • 3. [Nov04-Feb05] Experiments with the Probabilistic model for Shallow Parsing
  • 4. [Jan05-Feb05] Write paper on Model free ontology Elicitation
  • 5. [Jan05-Mar05] Write paper on AVT-NBk and AVT-BN
  • 6. [Feb05-Apr05] Write paper on the Probabilistic model for Shallow Parsing
  • 7. [Summer05, Fall05] Write thesis
  • 8. [Fall05] Defend
publications on ontology elicitation and usage
Publications [On Ontology Elicitation and usage]
  • [Silvescu and Honavar, 2004b] Silvescu, A. and Honavar, V. (2004) A Graphical Model for ShallowParsing Sequences. In Proceedings of the AAAI-04 Workshop on Text Extraction and Mining, San Jose, California.
  • [Silvescu et al., 2004a] Silvescu, A., Andorf, C., Dobbs, D., and Honavar, V. (2004) Learning NBk. To be submitted to SIGMOD/PODS, Baltimore, Maryland.
  • [Andorf et al., 2004] Andorf, C., Silvescu, A., Dobbs, D. and Honavar, V. (2004). Learning Classifiers for Assigning Protein Sequences to Gene Ontology Functional Families. In: Fifth International Conference on Knowledge Based Computer Systems (KBCS 2004). India.
  • [Kang et al., 2004] Kang, D-K., Silvescu, A., Zhang, J. and Honavar, V. (2004). Generation of Attribute Value Taxonomies from Data for Accurate and Compact Classifier Construction. In: IEEE International Conference on Data Mining.
  • Silvescu and Honavar, 2003] Silvescu, A. and Honavar, V. (2003) Ontology elicitation: Structural Abstraction = Structuring + Abstraction + Multiple Ontologies. Learning@Snowbird Workshop, Snowbird, Utah, 2003.
  • [Zhang et al., 2002] Zhang, J., Silvescu, A., and Honavar, V. (2002). Ontology-Driven Induction of Decision Trees at Multiple Levels of Abstraction. In: Proceedings of Symposium on Abstraction, Reformulation, and Approximation. Berlin: Springer-Verlag.
other publications
Other Publications
  • [Reinoso et al., 2003] Reinoso J., Silvescu, A., Caragea, D., Pathak, J., and Honavar, V. (2003). A Federated Query-Centric Approach to Information Extraction and Integration from Heterogeneous, Distributed and Autonomous Data Sources. Proceedings of the 2003 IEEE International Conference on Information Reuse and Integration, October 27-29, 2003, Las Vegas, USA.
  • [Caragea et al., 2003a] Caragea, D., Reinoso, J., Silvescu, A. and Honavar, V. (2003). Statistics Gathering for Learning from Distributed, Heterogeneous and Autonomous Data Sources. In: Proceedings of the International Workshop on Information Integration on the Web, IJCAI 2003, Acapulco, Mexico.
  • [Caragea et al., 2003b] Caragea, D., Silvescu, A., and Honavar, V. (2003). Decision Tree Induction from Distributed Data Sources. In: Proceedings of the Conference on Intelligent Systems Design and Applications, Tulsa, Oklahoma.
  • [Caragea et al., 2004a] Caragea, D., Silvescu, A., and Honavar, V. (2004). A Framework for Learning from Distributed Data Using Sufficient Statistics and its Application to Learning Decision Trees. International Journal of Hybrid Intelligent Systems. Vol. 1, No. 2. Invited Paper.
  • [Caragea et al., 2004b] Caragea, D., Silvescu, A. and Honavar, V. (2004) Learning classifiers from distributed data: issues, strategy, examples. To be submitted to JMLR.
  • [Silvescu and Honavar, 2001] Silvescu, A., and Honavar, V. (2001). Temporal Boolean Network Models of Genetic Networks and Their Inference from Gene Expression Time Series. Complex Systems.
  • [Caragea et al., 2001] Caragea, D., Silvescu, A., and Honavar, V. (2001) Towards a Theoretical Framework for Analysis and Synthesis of Agents That Learn from Distributed Dynamic Data Sources. In: Emerging Neural Architectures Based on Neuroscience. Berlin: Springer-Verlag. Invited Chapter.
  • [Silvescu and Honavar, 2001] Silvescu, A. and Honavar, V. (2001). Temporal Boolean Network Models of Genetic Networks and Their Inference from Gene Expression Time Series. In: Proceedings of the Atlantic Symposium on Computational Biology, Genome Information Systems & Technology.
  • [Caragea et al., 2000a] Caragea, D., Silvescu, A., and Honavar, V. (2000). Agents that Learn from Distributed Dynamic Data Sources. In: Proceedings of the Workshop on Learning Agents, Agents 2000/ECML 2000. Stone, P. and Sen, S. (Ed.) ECML. Barcelona, Spain. pp. 53-61.
  • [Caragea et al., 2000b] Caragea, D., Silvescu, A., and Honavar, V. (2000). Towards a Theoretical Framework for Analysis and Synthesis of Distributed and Incremental Learning Agents. In: Proceedings of the Workshop on Distributed and Parallel Knowledge Discovery. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Boston, U.S.A.
  • [Silvescu, 1999] Silvescu, A. (1999) Fourier Neural Networks, Proceedings of the IJCNN'99, Washington, DC.
papers in preparation
Papers in preparation
  • [Silvescu et al., 2005 ] Silvescu, A., and Honavar, V. (2005) Sequential Ontology elicitation.
  • [Silvescu et al., 2005 ] Silvescu, A., Kang, D.K., Zhang, J., and Honavar, V. (2005) AVT-MMk and AVT-Bayesian Networks
  • [Silvescu et al., 2005b] Silvescu, A., Yakhnenko, O., and Honavar, V. (2004) Regularised Conditional Classifers.
  • [Silvescu et al., 2005 ] Silvescu, A., Kang, D.K., and Honavar, V. (2005) Relational tree learning with dynamic creation of attributes.
  • [Silvescu et al., 2005a] Silvescu, A., Caragea, D., Yakhnenko, O., Kang, D.K., Pathak, J. and Honavar, V. (2005) Data Source Independent Learning Through the Means of Sufficient Statistics and Data Source Wrappers.
  • [Caragea et al., 2005] Caragea, D., Silvescu, A. and Honavar, V. (2005) Characterization of Sufficient Statistics Using Fixed Point Equations.
introduction
Introduction
  • Probabilistic Models for sequence data can be mainly divided into two categories:
    • I. Fairly sophisticated models that are aimed at finding an all encompassing characterization of the whole sequence by the means of an interdependent generative process (such as PCFGs and HMMs [manning99foundations]); and
    • II. Relatively simple models that make an independence assumption regarding the generation process of each of the elements of the sequence (such as Unigram, Naive Bayes, Clustering, PLSA and LDA [blei03latent]).
shallow parsing
Shallow parsing

We explore the interval between these two extremes with a model that does not attempt to be a global characterization of the sequence as in the case of PCFG/HMM but yet it does not assume independence among the generative processes of the subsequent elements in the sequence: Shallow Parsing

model
Model
  • We assume that the generation process produces chunks (subsequences) of elements of variable size, which are then concatenated in order to yield the whole sequence. The elements within a chunk are dependent of each other and the dependence is quantified by the hidden macro-variable Gi denoting the current chunk generator. The chunk generators are chosen independently from a distribution whose possible values is the set of all possible chunk generators.
  • [This model can be further extended to allow dependencies, either directed or undirected among chunk generators but for the sake of simplicity we will stick to the independence assumption in this paper].
generative model silvescu and honavar 2004
Generative Model[Silvescu and Honavar, 2004]
  • The generative process, using plate notation, is depicted in the next figure. Basically, a generator Gi is first drawn from a multinomial distribution and then it is used to generate the subsequence (chunk) Si.
  • The chunk generators in our case are PCFGs (Probabilistic Context Free Grammars), hence the tree model within the hidden variable denoting the generator Gi. The generated sequence is actually a concatenation of independent samples from a mixture of (small!) PCFGs.
generation
Generation

. . .

. . .

inference
Inference
  • Inference in this model is aimed at determining for each generative model Gi and for each Non-terminal Nj from the PCFGs what is the probability that each of these hidden variables has in generating a subsequence of the output.
  • The resulting algorithm has the flavor of the Inside - Outside algorithm for reasoning in PCFGs but needs to be augmented with one two more messages aside from the traditional a and b, that we call g(t:n) and d(1:t) (thus yielding the abgd - algorithm).
  • A Most Probable Explanation (MPE) procedure (a.k.a. Viterbi for Markov models) can be derived too, by replacing sums with max in the appropriate places in our abgd algorithm.
learning parameters em
Learning – Parameters [ = EM ]
  • In order to estimate the parameters of the model we use Expectation Maximization.
  • The Expectation step computes the hidden variables probabilities outlined previously using the abgd - algorithm.
  • As for Maximization, since our model is decomposable - it has sufficient statistics. Therefore all we have to do in order to compute the maximum likelihood estimator for the parameters is to compute the expected counts by summing up the probabilities obtained during the Expectation step.
  • [Some regularization is actually also going on in the form or Dirichlet priors but for simplicity ...]
  • Note that even though the abgd algorithm is conceptually more complicated that the ab we can obtain considerable improvements in running time because the ab in our case is run on much smaller strings (chunks vs. whole sequence)
learning structure
Learning - Structure
  • All the PCFGs share the structure and parameters
  • In order to learn the structure of the PCFGs we use a Structural-EM type of approach with appropriate custom operators designed for this task.
  • We can show that every CFG can be written in an Abstraction Super-structuring Normal Form (ASNF), which restricts the productions to one of the following types:
slide64
ASNF
  • ASNF – Abstraction Super-structuring Normal Form:
    • [Atomic] A -> a and this is the only production that contains A in the left hand side.
    • [Super-structuring] A -> BC and this is the only production that contains A in the left hand side.
    • [Abstraction] A -> B .
  • As a consequence our Structural - EM operators will be of either the Abstraction or Super-structuring type and with proper randomization we can show that the procedure is complete.
  • All the Atomics are inserted in the first step by default.
experiments future work
Experiments & Future Work
  • The experiments are targeted at evaluating the performance of the proposed approach on text and protein sequences tasks.
  • Ontology elicitation
  • Features for various tasks such as
    • Sequence Classification
    • Information Extraction
outline66
Outline
  • Introduction & Model Free Ontology Elicitation
  • A Generative Model for Shallow Parsing
  • Ontology Elicitation Framework
  • Ontology Usage
  • Contributions and Further work