1 / 22

Threshold Setting and Performance Monitoring for Novel Text Mining

Threshold Setting and Performance Monitoring for Novel Text Mining. Wenyin Tang and Flora S. Tsai School of Electrical and Electronic Engineering Nanyang Technological University E-mail: wenyintang@ntu.edu.sg , fst1@columbia.edu. May 2, 2009. Outline. Introduction

presley
Download Presentation

Threshold Setting and Performance Monitoring for Novel Text Mining

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. Threshold Setting and Performance Monitoring for Novel Text Mining Wenyin Tang and Flora S. Tsai School of Electrical and Electronic EngineeringNanyang Technological University E-mail: wenyintang@ntu.edu.sg, fst1@columbia.edu May 2, 2009

  2. Outline • Introduction • Novel Text Mining (NTM) System • Performance Evaluation of NTM • Adaptive Threshold Setting for NTM • Motivations • Our Method: Gaussian-based Adaptive Threshold Setting (GATS) • Experimental Result • Conclusion

  3. Overview of Novel Text Mining System Interact with users: input documents, output novel info, preference setting and feedback. Prepare a clean data matrix which can be easily processed by a computer. Categorise each incoming document or sentence into its relevant topic bin. Detect novel yet relevant documents or sentences in each topic.

  4. Novel Text Mining Algorithm Unfortunately, I am “non-novel” because I am very similar to my nearest neighbor D3 D4 D3 I am “novel” because I am dissimilar with my nearest neighbor D2 D1, D2, D3, D4 … D2 D1 I am “novel” because I am dissimilar to D1 I am “novel” because I am the first document Vector space Given a set of relevant documents in a specific topic, e.g. “football games”, NTM retrieves the novel documents by: • Step 1: rank documents in the topic “football games” in a chronological order. • Step 2: assign a novelty score for each document by comparing the document with its history documents. • Step 3: predict the document as “novel” if its novelty score is greater than the predefined novelty threshold.

  5. NTM Performance Evaluation # Novel: D1, D2, D3, D4, D5, D6, D7, D8, D9, D10 System (S): 8 Assessor (A): 5 Matched (M): 4 • Precision (P) reflects how likely the system retrieved docs are truly novel. P=M/S=4/8=0.5, i.e. 50% system retrieved docs are truly novel. • Recall (R) reflects how likely the truly novel docs can be retrieved by the system. R=M/A=4/5=0.8, i.e. 80% truly novel docs can be retrieved by the system. • Fβ score: the function of P and R: novel non-novel • Given a set of documents D1, D2, to D10, relevant to some topic, for example,

  6. Threshold Setting vs. Users’ Requirements I want to read the most novel information in a short time1. I do not want to miss any novel information2. The NTM system should define the novelty threshold based on the users’ requirements adaptively. I am not sure until I can see the documents • Different users may have different performance requirements. • High-precision NTM systems are desired; • High-recall NTM systems are desired.

  7. Why Adaptive Threshold Setting Motivations: • As NTM system is a real-time system, there is little or no training information in the initial stages of NTM. Therefore, the threshold cannot be predefined with confidence. • As NTM system is an accumulating system, more training information will be available for threshold setting, based on user’s feedback given over time. • Different users may have different definitions of “novelty”: • One user: a document with 50% novel info • Another user: a document with 90% novel info

  8. Gaussian-based Adaptive Threshold Setting (GATS) Basic idea: • GATS is a score distribution-based threshold setting method. It models the score distributions of both novel and non-novel documents (based on the user feedback); • This parametric model provides the global information of data, from which we can construct an optimization criterion of desired performance to search the best threshold.

  9. Novelty Score Distributions Gaussian probability distribution approximation Non-novel Novel Empirical probability distribution and its Gaussian probability distribution approximation for TREC 2004 Novelty Track data topic N54

  10. Optimization Criterion Satisfy 2 conditions: • Criterion is a function of Threshold: J=f (θ) 2. Criterion is directly related to system performance: J=Fβ(θ)

  11. Optimization Criterion Non-novel Novel S1 S0 θ θ

  12. Flow Chart of NTM with GATS

  13. Experimental Data Sentence-level data: TREC 2004 Novelty Track data The news providers of the document set are Xinghua English (XIE) , New York Times (NYT), and Associated Press Worldstream (APW). The NIST assessors created 50 topics for this data. Each topic consists of around 25 documents. These documents were ordered chronologically and then segmented into sentences. Each sentence was given an identifier and concatenated together to form the target sentence set. In this data, the overall percentage of novel sentences is around 41.4%. The statistics of data is summarized in Table 1. Table 1 Statistics of TREC 2004 Novelty Track data

  14. Experimental Data Document-level data: APWSJ APWSJ consists of news articles from Associate Press (AP) and Wall Street Journal (WSJ), which cover the same period from 1988 to 1990 [Zhang et al., 2002]. There are 50 TREC topics from Q101 to Q150 in this data and 5 topics (Q131, Q142, Q145, Q147, Q150) that lack non-novel documents are excluded from the experiments. The statistics of this data are summarized in Table 2. Table 2 Statistics of APWSJ data

  15. Methods & Parameters • Baseline: • Fixed threshold setting θ from 0.05~0.95 with an equal step 0.05. • Our method, GATS: • Complete feedback: with β from 0.1~0.9 with an equal step 0.1. • Partial feedback: with β from 0.1~0.9 with an equal step 0.1, percentages of feedback: 10%, 20%, 50% and 80%.

  16. Experimental Result Sentence-Level NTM on TREC 2004 Data Precision Recall

  17. Experimental Result Document-Level NTM on APWSJ Data Redundancy-Precision Redundancy-Recall

  18. Comparison: GATS vs. Fixed Threshold • For precision-recall tradeoff • Fixed threshold θ cannot reflect the tradeoff of the precision and recall directly. • GATS parameter β reflects the weights ofprecision and recall directly. • Under various performance requirements, GATS is able to approximate the best fixed threshold. Table 3 Comparison of Fβ on TREC 2004 Novelty Track data

  19. Experimental Result Sentence-Level NTM on TREC 2004 Data Precision Recall PR curves of GATS (tuned for Fβ) with different percentages of the user’s feedback.

  20. Experimental Result Document-Level NTM on APWSJ Data Redundancy-Precision Redundancy-Recall R-PR curves of GATS with different percentages of the user’s feedback.

  21. Conclusion A Gaussian-based Adaptive Threshold Setting (GATS) algorithm was proposed for NTM system. GATS is a generic method, which can be tuned according to different performance requirements varying from high-precision to high-recall. By testing the proposed method on both document and sentence-level datasets, we found the experimental results showed the promising performance of GATS for a real-time NTM system.

  22. Thank You! Q & A

More Related