Semantic Similarity Frontiers: From Concepts to Documents
Bibliographic record
Abstract
Semantic similarity forms a central component in many NLP systems, from lexical semantics, to part of speech tagging, to social media analysis. Recent years have seen a renewed interest in developing new similarity techniques, buoyed in part by work on embeddings and by SemEval tasks in Semantic Textual Similarity and Cross-Level Semantic Similarity. The increased interest has led to hundreds of techniques for measuring semantic similarity, which makes it difficult for practitioners to identify which state-of-the-art techniques are applicable and easily integrated into projects and for researchers to identify which aspects of the problem require future research.This tutorial synthesizes the current state of the art for measuring semantic similarity for all types of conceptual or textual pairs and presents a broad overview of current techniques, what resources they use, and the particular inputs or domains to which the methods are most applicable. We survey methods ranging from corpus-based approaches operating on massive or domains-specific corpora to those leveraging structural information from expert-based or collaboratively-constructed lexical resources. Furthermore, we review work on multiple similarity tasks from sense-based comparisons to word, sentence, and document-sized comparisons and highlight general-purpose methods capable of comparing multiple types of inputs. Where possible, we also identify techniques that have been demonstrated to successfully operate in multilingual or cross-lingual settings.Our tutorial provides a clear overview of currently-available tools and their strengths for practitioners who need out of the box solutions and provides researchers with an understanding of the limitations of current state of the art and what open problems remain in the field. Given the breadth of available approaches, participants will also receive a detailed bibliography of approaches (including those not directly covered in the tutorial), annotated according to the approaches abilities, and pointers to when open-source implementations of the algorithms may be obtained.
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 | 0.007 | 0.042 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.016 | 0.016 |
| Science and technology studies | 0.002 | 0.010 |
| Scholarly communication | 0.017 | 0.044 |
| Open science | 0.003 | 0.008 |
| Research integrity | 0.003 | 0.005 |
| Insufficient payload (model declined to judge) | 0.016 | 0.004 |
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".