End-to-end optimization of goal-driven and visually grounded dialogue systems Harm de Vries
Bibliographic record
Abstract
End-to-end design of dialogue systems has recently become a popular research\ntopic thanks to powerful tools such as encoder-decoder architectures for\nsequence-to-sequence learning. Yet, most current approaches cast human-machine\ndialogue management as a supervised learning problem, aiming at predicting the\nnext utterance of a participant given the full history of the dialogue. This\nvision is too simplistic to render the intrinsic planning problem inherent to\ndialogue as well as its grounded nature, making the context of a dialogue\nlarger than the sole history. This is why only chit-chat and question answering\ntasks have been addressed so far using end-to-end architectures. In this paper,\nwe introduce a Deep Reinforcement Learning method to optimize visually grounded\ntask-oriented dialogues, based on the policy gradient algorithm. This approach\nis tested on a dataset of 120k dialogues collected through Mechanical Turk and\nprovides encouraging results at solving both the problem of generating natural\ndialogues and the task of discovering a specific object in a complex picture.\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 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) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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".