Interpretation of Natural Language Rules in Conversational Machine\n Reading
Bibliographic record
Abstract
Most work in machine reading focuses on question answering problems where the\nanswer is directly expressed in the text to read. However, many real-world\nquestion answering problems require the reading of text not because it contains\nthe literal answer, but because it contains a recipe to derive an answer\ntogether with the reader's background knowledge. One example is the task of\ninterpreting regulations to answer "Can I...?" or "Do I have to...?" questions\nsuch as "I am working in Canada. Do I have to carry on paying UK National\nInsurance?" after reading a UK government website about this topic. This task\nrequires both the interpretation of rules and the application of background\nknowledge. It is further complicated due to the fact that, in practice, most\nquestions are underspecified, and a human assistant will regularly have to ask\nclarification questions such as "How long have you been working abroad?" when\nthe answer cannot be directly derived from the question and text. In this\npaper, we formalise this task and develop a crowd-sourcing strategy to collect\n32k task instances based on real-world rules and crowd-generated questions and\nscenarios. We analyse the challenges of this task and assess its difficulty by\nevaluating the performance of rule-based and machine-learning baselines. We\nobserve promising results when no background knowledge is necessary, and\nsubstantial room for improvement whenever background knowledge is needed.\n
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 | 0.047 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.003 | 0.002 |
| Science and technology studies | 0.002 | 0.003 |
| Scholarly communication | 0.007 | 0.010 |
| Open science | 0.004 | 0.004 |
| Research integrity | 0.003 | 0.004 |
| Insufficient payload (model declined to judge) | 0.005 | 0.003 |
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".