LADy: A System for Latent Aspect Detection via Back-translation Augmentation
Bibliographic record
Abstract
Aspects are the features or properties of products and services about which a customer expresses opinions and sentiments. Aspect detection helps business owners identify demands and shortcomings to improve customer experience. In informal settings, like social media platforms, aspects tend to be latent (implicit) because of word limits and the expectation of context awareness henceforth. Existing methods fall short of accurate aspect detection in such scenarios. To bridge the gap, we propose data augmentation via natural language back-translation to extract latent occurrences of aspects using machine learning techniques. Specifically, we presume that back-translation can reveal latent aspects by uncovering social knowledge between languages, generating context-sensitive synonymous aspects, and clarify semantic contexts of terms and sentences. Through our experiments on well-known aspect detection methods across SemEval benchmark datasets of reviews, we demonstrate that review augmentation via back-translation yields a steady performance boost in baselines in all datasets. We further contribute LADy, a benchmark library under CC-BY-NC-SA-4.0 license at https://anonymous.4open.science/r/LADy/ to support the reproducibility of our research.
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 | 0.003 | 0.015 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.007 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.005 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.010 |
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".