Papers with Code 아카이브
Slot Filling
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 2
- 평가표
- 14
- 보존된 평가 기록
- 110
The goal of Slot Filling is to identify from a running dialog different slots, which correspond to different parameters of the user’s query. For instance, when a user queries for nearby restaurants, key slots for location and preferred food are required for a dialog system to retrieve the appropriate information. Thus, the main challenge in the slot-filling task is to extract the target entity.
Source: Real-time On-Demand Crowd-powered Entity Extraction
Image credit: Robust Retrieval Augmented Generation for Zero-shot Slot Filling
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
Generalized Multiple Intent Conditioned Slot Filling
Search-in-the-Chain: Interactively Enhancing Large Language Models with Search for Knowledge-intensive Tasks
Zero-Shot Slot and Intent Detection in Low-Resource Languages
Efficient Sequence Transduction by Jointly Predicting Tokens and Durations
A Preliminary Evaluation of ChatGPT for Zero-shot Dialogue Understanding
Efficiently Aligned Cross-Lingual Transfer Learning for Conversational Tasks using Prompt-Tuning
Toward Open-domain Slot Filling via Self-supervised Co-training
CTRAN: CNN-Transformer-based Network for Natural Language Understanding
Matching-based Term Semantics Pre-training for Spoken Patient Query Understanding
A Persian Benchmark for Joint Intent Detection and Slot Filling
Revisit Out-Of-Vocabulary Problem for Slot Filling: A Unified Contrastive Frameword with Multi-level Data Augmentations
Can discrete information extraction prompts generalize across language models?
Uncertainty-aware Self-training for Low-resource Neural Sequence Labeling
HIT-SCIR at MMNLU-22: Consistency Regularization for Multilingual Spoken Language Understanding
Spoken Language Understanding for Conversational AI: Recent Advances and Future Direction
How Does Beam Search improve Span-Level Confidence Estimation in Generative Sequence Labeling?
Can Current Task-oriented Dialogue Models Automate Real-world Scenarios in the Wild?
The Massively Multilingual Natural Language Understanding 2022 (MMNLU-22) Workshop and Competition
Punctuation Restoration for Singaporean Spoken Languages: English, Malay, and Mandarin
ESIE-BERT: Enriching Sub-words Information Explicitly with BERT for Joint Intent Classification and SlotFilling
A Scope Sensitive and Result Attentive Model for Multi-Intent Spoken Language Understanding
Introducing Semantics into Speech Encoders
In-game Toxic Language Detection: Shared Task and Attention Residuals
A Dynamic Graph Interactive Framework with Label-Semantic Injection for Spoken Language Understanding
End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator
Augmenting Task-Oriented Dialogue Systems with Relation Extraction
Shift-Reduce Task-Oriented Semantic Parsing with Stack-Transformers
Explainable Slot Type Attentions to Improve Joint Intent Detection and Slot Filling
Group is better than individual: Exploiting Label Topologies and Label Relations for Joint Multiple Intent Detection and Slot Filling
Co-guiding Net: Achieving Mutual Guidances between Multiple Intent Detection and Slot Filling via Heterogeneous Semantics-Label Graphs
A Unified Framework for Multi-intent Spoken Language Understanding with prompting
Explainable Abuse Detection as Intent Classification and Slot Filling
From Disfluency Detection to Intent Detection and Slot Filling
Multi-grained Label Refinement Network with Dependency Structures for Joint Intent Detection and Slot Filling
Entity Aware Syntax Tree Based Data Augmentation for Natural Language Understanding
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.