Optimizing NLU Reranking Using Entity Resolution Signals in Multi-domain Dialog Systems
In dialog systems, the Natural Language Understanding (NLU) component typically makes the interpretation decision (including domain, intent and slots) for an utterance before the mentioned entities are resolved. This may result in intent classification and slot tagging errors. In this work, we propose to leverage Entity Resolution (ER) features in NLU reranking and introduce a novel loss term based on ER signals to better learn model weights in the reranking framework. In addition, for a multi-domain dialog scenario, we propose a score distribution matching method to ensure scores generated by the NLU reranking models for different domains are properly calibrated. In offline experiments, we demonstrate our proposed approach significantly outperforms the baseline model on both single-domain and cross-domain evaluations.
Code (0)
등록된 구현이 없습니다.
Tasks
Entity Resolutionintent-classificationIntent ClassificationNatural Language UnderstandingRerankingSimilar Papers 제목 키워드 기반
Graph-boosted Active Learning for Multi-Source Entity Resolution
Supervised entity resolution methods rely on labeled record pairs for learning matching patterns between two or more data sources. Active learning minimizes the labeling effort by selecting informative pairs for labeling…
Active LearningEntity ResolutionNeural Reranking for Named Entity Recognition
We propose a neural reranking system for named entity recognition (NER). The basic idea is to leverage recurrent neural network models to learn sentence-level patterns that involve named entity mentions. In particular, g…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NER+2HLATR: Enhance Multi-stage Text Retrieval with Hybrid List Aware Transformer Reranking
Deep pre-trained language models (e,g. BERT) are effective at large-scale text retrieval task. Existing text retrieval systems with state-of-the-art performance usually adopt a retrieve-then-reranking architecture due to…
Passage RankingPassage Re-RankingRerankingRetrieval+1Dual-Rerank: Fusing Causality and Utility for Industrial Generative Reranking
Kuaishou serves over 400 million daily active users, processing hundreds of millions of search queries daily against a repository of tens of billions of short videos. As the final decision layer, the reranking stage dete…
Reinforcement LearningKnowledge DistillationAdaptive Graph Refinement and Label Propagation with LLMs for Cost-Effective Entity Resolution
Dirty entity resolution (ER), which identifies records referring to the same real-world entity from a single, messy dataset, is a fundamental task in data management and mining. However, the dominant blocking-matching-cl…
Entity Resolution