RETRONLU: Retrieval Augmented Task-Oriented Semantic Parsing

2021-09-21 · NLP4ConvAI (ACL) 2022 5 · Vivek Gupta, Akshat Shrivastava, Adithya Sagar, Armen Aghajanyan, Denis Savenkov

While large pre-trained language models accumulate a lot of knowledge in their parameters, it has been demonstrated that augmenting it with non-parametric retrieval-based memory has a number of benefits from accuracy improvements to data efficiency for knowledge-focused tasks, such as question answering. In this paper, we are applying retrieval-based modeling ideas to the problem of multi-domain task-oriented semantic parsing for conversational assistants. Our approach, RetroNLU, extends a sequence-to-sequence model architecture with a retrieval component, used to fetch existing similar examples and provide them as an additional input to the model. In particular, we analyze two settings, where we augment an input with (a) retrieved nearest neighbor utterances (utterance-nn), and (b) ground-truth semantic parses of nearest neighbor utterances (semparse-nn). Our technique outperforms the baseline method by 1.5% absolute macro-F1, especially at the low resource setting, matching the baseline model accuracy with only 40% of the data. Furthermore, we analyze the nearest neighbor retrieval component's quality, model sensitivity and break down the performance for semantic parses of different utterance complexity.

📄 PDF Abstract BibTeX arXiv:2109.10410

Code (0)

등록된 구현이 없습니다.

Tasks

Question Answering Retrieval Semantic Parsing

LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding

2026-04-18 · Yifan Zhu, Yu Mi, Yue Lu, Yanchu Guan 외 arxiv

Multimodal Retrieval-Augmented Generation (RAG) has emerged as an effective paradigm for enhancing Large Language Models (LLMs) with external knowledge. However, existing multimodal RAG systems predominantly rely on coar…

Question Answering

Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts

2024-05-30 · Chunjing Gan, Dan Yang, Binbin Hu, Hanxiao Zhang 외

In recent years, large language models (LLMs) have made remarkable achievements in various domains. However, the untimeliness and cost of knowledge updates coupled with hallucination issues of LLMs have curtailed their a…

All Hallucination RAG Retrieval+1

MME-RAG: Multi-Manager-Expert Retrieval-Augmented Generation for Fine-Grained Entity Recognition in Task-Oriented Dialogues

2025-11-15 · Liang Xue, Haoyu Liu, Yajun Tian, Xinyu Zhong 외 arxiv

Fine-grained entity recognition is crucial for reasoning and decision-making in task-oriented dialogues, yet current large language models (LLMs) continue to face challenges in domain adaptation and retrieval controllabi…

Domain Generalization Domain Adaptation

QuOTE: Question-Oriented Text Embeddings

2025-02-16 · Andrew Neeser, Kaylen Latimer, Aadyant Khatri, Chris Latimer 외

We present QuOTE (Question-Oriented Text Embeddings), a novel enhancement to retrieval-augmented generation (RAG) systems, aimed at improving document representation for accurate and nuanced retrieval. Unlike traditional…

Multi-hop Question Answering Question Answering Question Generation Question-Generation+3

Synchronous Faithfulness Monitoring for Trustworthy Retrieval-Augmented Generation

2024-06-19 · Di wu, Jia-Chen Gu, Fan Yin, Nanyun Peng 외

Retrieval-augmented language models (RALMs) have shown strong performance and wide applicability in knowledge-intensive tasks. However, there are significant trustworthiness concerns as RALMs are prone to generating unfa…

Reranking Retrieval Retrieval-augmented Generation Uncertainty Quantification