2023-07-05 ジョージア工科大学
◆従来の試みでは、ユーザーの意図やレシピの進行状況を正確に理解できず、質問に対する回答や調理時間の明確化などにも問題がありました。研究者はこれらの課題に取り組み、ChattyChefのモデルを改良し、ユーザーの意図を把握し、レシピの進行状況を正確に追跡することに成功しました。
◆このモデルは、料理の質問に適切な回答を生成し、混乱や余分な手順を避けるためにレシピの適切な部分を選択します。研究チームは、ChattyChefのデータセットを作成し、その有用性を実証しました。
＜関連情報＞
レシピに基づく会話における命令順序の改善
Improved Instruction Ordering in Recipe-Grounded Conversation
Duong Minh Le, Ruohao Guo, Wei Xu, Alan Ritter
arXiv Submitted on :26 May 2023
DOI:https://doi.org/10.48550/arXiv.2305.17280
In this paper, we study the task of instructional dialogue and focus on the cooking domain. Analyzing the generated output of the GPT-J model, we reveal that the primary challenge for a recipe-grounded dialog system is how to provide the instructions in the correct order. We hypothesize that this is due to the model’s lack of understanding of user intent and inability to track the instruction state (i.e., which step was last instructed). Therefore, we propose to explore two auxiliary subtasks, namely User Intent Detection and Instruction State Tracking, to support Response Generation with improved instruction grounding. Experimenting with our newly collected dataset, ChattyChef, shows that incorporating user intent and instruction state information helps the response generation model mitigate the incorrect order issue. Furthermore, to investigate whether ChatGPT has completely solved this task, we analyze its outputs and find that it also makes mistakes (10.7% of the responses), about half of which are out-of-order instructions. We will release ChattyChef to facilitate further research in this area at: https://github.com/octaviaguo/ChattyChef
Comments: Accepted at ACL 2023 main conference
Subjects: Computation and Language (cs.CL)
Cite as: arXiv:2305.17280 [cs.CL]
(or arXiv:2305.17280v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2305.17280
Focus to learn more
Submission history
From: Duong Le [view email]
[v1] Fri, 26 May 2023 21:57:11 UTC (11,954 KB)
