Language Identification Strategies for Cross Language Information Retrieval.
Bibliographic record
Abstract
Abstract. In our participation to the 2010 LogCLEF track we focused on the analysis of the European Library (TEL) logs and in particular we experimented with the identification of the natural language used in the queries. Language identification is in fact a key task within Cross Language Information Retrieval systems and the challenge is particularly difficult in the case of search queries where the contextual information available is scarce; function words (grammar particles highly connotative of a specific language like prepositions, pronouns, conjunctions, etc) are usually missing and the relevant presence of Named Entities can be misleading for the correct identification of the language used in the query. In order to face this challenge with acceptable performances the techniques applied should be different form the ones adopted for language guessing with more extensive and syntactically richer text fragments, like metadata or textual documents. In particular we experimented combining together different strategies: corpus based, character model based and a priori hypothesis. Since no official evaluation of the task is available we manually evaluated a sample of 100 queries and the results obtained are quite promising. Keywords: Cross-Language Information Retrieval, Language Identification, Log Analysis.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.010 | 0.035 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.010 | 0.006 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.005 | 0.011 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.024 | 0.015 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".