A Deep Learning Approach for Semantic Similarity Prediction Between Question Pairs Using Siamese Network and Word Embedding Techniques
Bibliographic record
Abstract
Question-answering platforms, such as Quora, Red-dit, and StackOverflow, have become immensely popular in the virtual community. Among these platforms, Quora stands out as a widely utilized and resourceful repository with over 300 million monthly visitors. However, the prevalence of similar questions with paraphrased content poses challenges for users in finding relevant answers. This paper proposes a deep learning approach for predicting the semantic similarity of question pairs to address the issue of duplicate questions. The proposed model employs a Siamese network-based Long Short-Term Memory (LSTM) architecture, utilizing word embedding vectors from various algorithms such as Glo Ve, Word2Vec, and FastText. Previous research on duplicate question identification is reviewed, with our approach overcoming drawbacks such as low-level semantic connections and text type incompatibility. After pre-processing the Siamese LSTM network compares the embeddings using L1 distance to determine question pair similarity. The model is trained and evaluated on the Quora Question Pair Classification dataset, and outperformed other state-of-the-art methods with an accuracy of 84.77% with the FastText word embedding.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".