Bibliographic record
Abstract
SpeechWeb consists of a collection of hyperlinked natural-language interfaces to applications which can be accessed through the Internet from speech browsers running on PCs. The applications contain hyperlinks which the browser uses to navigate SpeechWeb. The natural-language interfaces have been constructed as executable specifications of at-tribute grammars using a domain–specific programming lan-guage built for this purpose. The approach to natural-language processing is based on a new efficient com-positional semantics that accommodates arbitrarily-nested quantification and negation. The user-independent speech browser is grammar based, and novel techniques have been developed to improve recognition accuracy. SpeechWeb SpeechWeb currently consists of several hyperlinked appli-cations, including “solar man ” who can answer questions about the solar system, “Judy ” who knows some poems, and “Monty ” who claims to be a student at the University of Windsor in Ontario. The following is an example of the spoken user-input component of a session with SpeechWeb. can I talk to solar man? what do you know? which moons orbit earth or jupiter? was every moon that orbits mars discovered by Hall? does something orbit no planet? not every planet is orbited by phobos. does every thing that orbits no planet and is not a person or a planet spin? which moon that was discovered by hall does not orbit mars? can I talk to monty? THE BROWSER IS REDIRECTED TO MONTY hi monty who is the president of the university of windsor?
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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 teacher head, 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".