Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs
| العنوان: | Constraint based Knowledge Base Distillation in End-to-End Task Oriented Dialogs |
|---|---|
| المؤلفون: | Dinesh Raghu, Atishya Jain, null Mausam, Sachindra Joshi |
| المصدر: | ACL/IJCNLP (Findings) |
| بيانات النشر: | Association for Computational Linguistics, 2021. |
| سنة النشر: | 2021 |
| مصطلحات موضوعية: | FOS: Computer and information sciences, Structure (mathematical logic), Computer Science - Machine Learning, Multiset, Computer Science - Computation and Language, Correctness, business.industry, Computer science, Filter (signal processing), computer.software_genre, Machine Learning (cs.LG), Constraint (information theory), Knowledge base, Metric (mathematics), Artificial intelligence, Dialog box, business, Computation and Language (cs.CL), computer, Natural language processing |
| الوصف: | End-to-End task-oriented dialogue systems generate responses based on dialog history and an accompanying knowledge base (KB). Inferring those KB entities that are most relevant for an utterance is crucial for response generation. Existing state of the art scales to large KBs by softly filtering over irrelevant KB information. In this paper, we propose a novel filtering technique that consists of (1) a pairwise similarity based filter that identifies relevant information by respecting the n-ary structure in a KB record. and, (2) an auxiliary loss that helps in separating contextually unrelated KB information. We also propose a new metric -- multiset entity F1 which fixes a correctness issue in the existing entity F1 metric. Experimental results on three publicly available task-oriented dialog datasets show that our proposed approach outperforms existing state-of-the-art models. D. Raghu and A. Jain contributed equally to this work |
| الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_dedup___::e2108d754838609b60a93c538cff5cceTest https://doi.org/10.18653/v1/2021.findings-acl.448Test |
| حقوق: | OPEN |
| رقم الانضمام: | edsair.doi.dedup.....e2108d754838609b60a93c538cff5cce |
| قاعدة البيانات: | OpenAIRE |
| الوصف غير متاح. |