Approaches to automated metadata extraction : FixRep Project

UKOLN is supported by: Approaches to automated metadata extraction : FixRep Project Emma Tonkin [email_address] www.bath.ac.uk

Wouldn't it be nice if... ...computers could author our metadata for us, thus saving a lot of hassle? Mechanical metadata extraction vs manual metadata input

But... Automated tools are fallible There's never quite enough information available Templates change, different domains have different standards In short, computers are often wrong and so are people

Hybrid approach: Get what metadata you can Ask the user to check and clean it if necessary Philosophy: If the computer gets it wrong, we can fix it later The 'half a loaf' hypothesis

Wouldn’t it be nice if… … computers could fix our metadata for us? Or, more realistically, help us do this work for ourselves.

All about ‘fixing it later’, doing what we can with what we have Automated metadata extraction + metadata consistency assessment Metadata generation, evaluation, characterisation: enabling metadata triage

Challenges in automated metadata extraction Manual metadata generation Metadata extraction in brief Practical use as part of a repository deposit workflow A user study comparing manual and hybrid input Towards metadata triage

Whatever can go wrong... PDFs can be: Encrypted Corrupted Oddly encoded An image file without embedded text Occurrence: ~3-6%

Character sets Ligatures, Accents, Symbols - may not always be extractable from PDFs Image © Daniel Ullrich

Document formats/layouts Many possible formats Some formats not widely supported Document layouts vary widely, esp. by discipline

Challenges in metadata extraction Manual metadata generation Metadata extraction in brief Practical use as part of a repository deposit workflow A user study comparing manual and hybrid input Towards metadata triage

Whatever can go wrong... (II) Function following form – interface Model adapted to suit unique user needs Data model incompletely supported Input validation issues Systematic error; typos; localisation; encoding; etc. Lots of past work in characterising manual input errors

Challenges in metadata extraction Manual metadata generation Metadata extraction in brief Practical use as part of a repository deposit workflow A user study comparing manual and hybrid input

Image segmentation, templating & OCR

Working from text There are a number of possible states (ie. title, author, email, affiliation, abstract) Directed graph with probabilities Markov chain: for example, Title Author Email Affil.

Hidden Markov Model We cannot directly see these states – only the words But we can gather statistics on the correlation between the words and the underlying states, to inform guesses as to how the data should be segmented This may be expressed in terms of an HMM Bayesian statistics used across term appearance

Example parse Confirmation-Guided Discovery of First-Order Rules, PETER A. FLACH, NICOLAS LACHICHE Confirmation-Guided Discovery of First-Order Rules, PETER A. FLACH, NICOLAS LACHICHE ... Confirmation-Guided Discovery of First-Order Rules , PETER A. FLACH, NICOLAS LACHICHE Self-correcting, to the extent that the knowledge base grows as new papers are added to the collection

Aims Adaption of existing interfaces Enhancing rather than rewriting Cross-platform, accessible interface Simple reusable REST API, metadata as DC/XML

Question: “ Do people accept ‘hybrid’ interfaces?” Here’s one we did earlier…

Hypotheses Correcting extracted metadata is faster than entering or cutting-and-pasting metadata. The resulting metadata has fewer errors when the user is provided with already extracted metadata to correct. User satisfaction with a system is higher if it 'tries' to extract metadata, even if it fails. Measured: speed and accuracy of entering information manually versus hybrid entry, and qualitatively, the user-satisfaction

Results: Timing Hybrid faster under both conditions (Summary of median times)‏

Results: Accuracy Tested against ground-truth Keyword accuracy: First keyword listed was relevant for 46% of the publications. The top two were relevant in 66%; the top-5 cover 81% of all desired keywords. Manual metadata accuracy: Few users use cut and paste Capitalisation, punctuation frequently differs Synonyms are accidentally substituted Hybrid closer to ground-truth, and more complete, but results not clear-cut.

Qualitative results Most users preferred the hybrid mode Most perceived it to be faster than manual data entry Few believed the hybrid approach to be more accurate; in practice, there was no significant difference in quality between hybrid and manual approach Both were good - quality

Discussion Results support hypotheses People prefer the hybrid interface, and found it more satisfying to use Accessibility issues exist, but can be overcome The punchline: one subject actually preferred manual entry because the hybrid system filled in metadata fields that he preferred to leave empty – ie. it did more than the subject wanted!

MetRe prototype (2008) Characteristic classes of individual/systematic error highlighted Nb. local and general best practice. Uses: ranking, browsing, correcting systematic error Uses info from intra-/inter-repository harvested metadata to identify patterns, rank occurrences and co-occurrences

Issues Discipline/domain-specific issues Lots of information required to do this right (see metadata schema/terminology registry) Some APs present particular difficulties, such as SWAP (FRBR structure, linking objects by ‘Scholarly Work’)

Approach Generally dependent on heuristics over available data Powered by very specific functions (classifiers, validation, etc…) Potentially expensive, not always domain-independent

Future work More! Data Filters (input/output formats) Methods Evaluation Service availability (mail me for announcements!)

Conclusion Metadata creation can be supported through software Specific problem sets in metadata triage Work continues in the FixRep project

Conclusion (II) Formal Metadata Extraction/evaluation Metadata review process Accessibility metadata Entity extraction (named entities, geographical, temporal [k-int!]) Repository integration

Thanks! Comments/Questions? www.ukoln.ac.uk/projects/fixrep

Approaches to automated metadata extraction : FixRep Project

More Related Content

Similar to Approaches to automated metadata extraction : FixRep Project (20)

More from UKOLN (dev), University of Bath (9)

Recently uploaded (20)

Approaches to automated metadata extraction : FixRep Project