INSTITUTO POLITCNICO NACIONAL Centro de Investigacin en Computacin - - PowerPoint PPT Presentation

INSTITUTO POLITÉCNICO NACIONAL

Centro de Investigación en Computación

Tuesday, 16 September 2014

1

Miguel A. Sanchez- Miguel A. Sanchez-Pere Perez, Grig z, Grigori

• ri Sidorov, Alexander Gelbukh

idorov, Alexander Gelbukh

1.

Task

2.

Methodology

3.

Adaptative behavior

4.

Results

5.

Conclusions

6.

Future Work

Source Source Retrieval trieval Coll Collecti ection of

• n of

documents documents Source Source documents documents Text Align xt Alignmen ent Suspicious spicious document document Suspicious spicious passag passages

Text Alignment: Given a pair of pair of documen documents, the task is to identify all contiguous maximal-length ntiguous maximal-length passages of reus reused text ed text between them.

 Preprocessing  Seeding  Extension  Filtering

 Sentence splitting (Kiss pretrained punkt model)  Tokenizing (Treebank word tokenizer)  Keeping tokens starting with a letter or digit  Reducing to lowercase  Stemming (Porter algorithm)  Joining small sentences (1-2 words) with the next one

PAN 2014 training corpus Sentences length histogram (words)

Vector representation of sentences: TF-IDF TF-IDF, where sentences sentences are “documents,” thus called TF-ISF: inverse sentence sentence freq. “Documents”: union of sentences of both docs Vector similarity: Cosine similarity threshold th1 AND Dice similarity threshold th2

Seeds Seeds: pairs of similar similar sentences

Group left left Groupin Grouping

Group left left Groupin Grouping

Group right right Groupin Grouping

Group right right Groupin Grouping

Group left left Groupin Grouping

Example: maxGap maxGap = 1 1 Group left left Groupin Grouping

Example: maxGap maxGap = 1 1 Group left left Groupin Grouping

Example: maxGap maxGap = 1 1 Group right right Groupin Grouping

Example: maxGap maxGap = 1 1 Group right right Groupin Grouping

Example: maxGap maxGap = 1 1 Group left left Groupin Grouping

Example: maxGap maxGap = 1 1 Group left left Groupin Grouping

Iteration No plagiarism None Random Translation Summary 1 674 6803 6436 7637 3074 2 3 278 180 246 294 3 7 7 3 3 4 1

Groupin Grouping

Example: maxGap maxGap = 2 2 Validati Validation

• n

Example: maxGap maxGap = 2 2

Cosine similarity If cosine similarity < th3 th3 Regroup with maxGap - maxGap - 1

Validati Validation

• n

Validati Validation

• n

1 ,

A B

If n° n° charact characters rs in left side OR OR rigth side < minPlagLen minPlagLength gth then the case is removed

• 1. Resolving overlapping
• 2. Removing small cases

Source documents Suspicious documents Cumulative histogram of plagiarism cases passages

Text alignment task: best result of all 11 participating systems, thanks to:

1.

TF-ISF (inverse sentence frequency) measure for “soft” removal of stopwords.

2.

Recursive extension algorithm: dynamic adjustment of tolerance to gaps

3.

Algorithm for resolution of overlapping cases by comparison of competing cases

4.

Dynamic adjustment of parameters by type of

• bfuscation (summary vs. other types)

 Text reuse focused on paraphrase  Soft cosine to measure similarity between features  New strategy to resolve overlapping

Thanks!

http://www.gelbukh.com/plag http://www.gelbukh.com/plagiarism-detection/PAN-2014 iarism-detection/PAN-2014