Combined Approach for Answer Identification with Small Sized Reading Comprehension Datasets
Bibliographic record
Abstract
In the realm of natural language understanding, machine reading and comprehension have emerged as significant areas of interest, requiring machines to extract pertinent information from textual data and understand it.This study proposes a novel method for answer identification in a multiple-choice question answering setup, utilizing science textbook and narrative text data.The proposed methodology integrates lexical semantic features at the word level and sentence-level equivalence.Initially, the strategy exploits lexical features, particularly word overlap, critical for answer identification.It extracts features such as noun phrases, verb phrases, and prepositions, accounting for their grammatical relationships.These features are then enhanced by assessing semantic similarity via a transformer model.Subsequently, answer identification is executed by mapping between answer option sentences and paragraph sentences on a one-to-one basis.The accuracy of correct answer identification was evaluated using both a feature-based approach and a BERT-based approach.Results indicated an accuracy of 66.4% and 57.5% for the science and narrative datasets, respectively, employing the combined approach.The performance evaluation of the proposed method was undertaken with a fine-tuned pre-trained language model.The evaluation analysis revealed certain challenges with the proposed methodology, outlining avenues for future 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 | 0.011 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".