{"total":34,"rows":[{"id":"2210.03050","title":"State-of-the-art generalisation research in NLP: A taxonomy and review","created":"2022-10-06","cited_by_count":98,"area":null},{"id":"2201.05176","title":"Neural Approaches to Conversational Information Retrieval","created":"2022-01-13","cited_by_count":42,"area":null},{"id":"2305.09067","title":"SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting","created":"2023-05-15","cited_by_count":39,"area":null},{"id":"2109.13489","title":"\"How Robust r u?\": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations","created":"2021-09-28","cited_by_count":30,"area":null},{"id":"2310.06504","title":"Revisit Input Perturbation Problems for LLMs: A Unified Robustness Evaluation Framework for Noisy Slot Filling Task","created":"2023-10-10","cited_by_count":23,"area":null},{"id":"2207.14627","title":"\"Do you follow me?\": A Survey of Recent Approaches in Dialogue State Tracking","created":"2022-07-29","cited_by_count":22,"area":null},{"id":"2106.04016","title":"Disfl-QA: A Benchmark Dataset for Understanding Disfluencies in Question Answering","created":"2021-06-08","cited_by_count":20,"area":null},{"id":"2210.07448","title":"Evaluating Out-of-Distribution Performance on Document Image Classifiers","created":"2022-10-14","cited_by_count":16,"area":null},{"id":"2112.05842","title":"Revisiting the Boundary between ASR and NLU in the Age of Conversational Dialog Systems","created":"2021-12-10","cited_by_count":15,"area":null},{"id":"2207.13211","title":"A Survey of Intent Classification and Slot-Filling Datasets for Task-Oriented Dialog","created":"2022-07-26","cited_by_count":14,"area":null},{"id":"2205.06262","title":"FETA: A Benchmark for Few-Sample Task Transfer in Open-Domain Dialogue","created":"2022-05-12","cited_by_count":11,"area":null},{"id":"2403.14659","title":"Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future","created":"2024-02-28","cited_by_count":11,"area":null},{"id":"2108.13048","title":"ASR-GLUE: A New Multi-task Benchmark for ASR-Robust Natural Language Understanding","created":"2021-08-30","cited_by_count":9,"area":null},{"id":"2112.08321","title":"Know Thy Strengths: Comprehensive Dialogue State Tracking Diagnostics","created":"2021-12-15","cited_by_count":9,"area":null},{"id":"2201.06849","title":"Toward Self-learning End-to-End Task-Oriented Dialog Systems","created":"2022-01-18","cited_by_count":9,"area":null},{"id":"2208.11508","title":"PSSAT: A Perturbed Semantic Structure Awareness Transferring Method for Perturbation-Robust Slot Filling","created":"2022-08-24","cited_by_count":9,"area":null},{"id":"2210.04782","title":"Robustification of Multilingual Language Models to Real-world Noise in Crosslingual Zero-shot Settings with Robust Contrastive Pretraining","created":"2022-10-10","cited_by_count":9,"area":null},{"id":"2211.11617","title":"CGoDial: A Large-Scale Benchmark for Chinese Goal-oriented Dialog Evaluation","created":"2022-11-21","cited_by_count":9,"area":null},{"id":"2312.13871","title":"Evaluating Task-oriented Dialogue Systems: A Systematic Review of Measures, Constructs and their Operationalisations","created":"2023-12-21","cited_by_count":9,"area":null},{"id":"2209.03632","title":"AARGH! End-to-end Retrieval-Generation for Task-Oriented Dialog","created":"2022-09-08","cited_by_count":8,"area":null},{"id":"2302.04618","title":"Robust Question Answering against Distribution Shifts with Test-Time Adaptation: An Empirical Study","created":"2023-02-09","cited_by_count":8,"area":null},{"id":"2310.16609","title":"Back Transcription as a Method for Evaluating Robustness of Natural Language Understanding Models to Speech Recognition Errors","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2310.03518","title":"Towards Robust and Generalizable Training: An Empirical Study of Noisy Slot Filling for Input Perturbations","created":"2023-10-05","cited_by_count":5,"area":null},{"id":"2310.10169","title":"DemoNSF: A Multi-task Demonstration-based Generative Framework for Noisy Slot Filling Task","created":"2023-10-16","cited_by_count":5,"area":null},{"id":"2205.10363","title":"Robust Task-Oriented Dialogue Generation with Contrastive Pre-training and Adversarial Filtering","created":"2022-05-20","cited_by_count":4,"area":null},{"id":"2402.02078","title":"Exploring the Robustness of Task-oriented Dialogue Systems for Colloquial German Varieties","created":"2024-02-03","cited_by_count":4,"area":null},{"id":"2110.11514","title":"SYNERGY: Building Task Bots at Scale Using Symbolic Knowledge and Machine Teaching","created":"2021-10-21","cited_by_count":3,"area":null},{"id":"2210.12942","title":"Are Current Task-oriented Dialogue Systems Able to Satisfy Impolite Users?","created":"2022-10-24","cited_by_count":3,"area":null},{"id":"2403.05640","title":"Generating Hard-Negative Out-of-Scope Data with ChatGPT for Intent Classification","created":"2024-03-08","cited_by_count":2,"area":null},{"id":"2406.10950","title":"E-Bench: Towards Evaluating the Ease-of-Use of Large Language Models","created":"2024-06-16","cited_by_count":2,"area":null},{"id":"2205.09934","title":"Towards Explanation for Unsupervised Graph-Level Representation Learning","created":"2022-05-20","cited_by_count":1,"area":null},{"id":"2212.02745","title":"Sources of Noise in Dialogue and How to Deal with Them","created":"2022-12-06","cited_by_count":1,"area":null},{"id":"2402.14494","title":"Noise-BERT: A Unified Perturbation-Robust Framework with Noise Alignment Pre-training for Noisy Slot Filling Task","created":"2024-02-22","cited_by_count":1,"area":null},{"id":"2311.08705","title":"Evaluating Robustness of Dialogue Summarization Models in the Presence of Naturally Occurring Variations","created":"2023-11-15","cited_by_count":0,"area":null}],"next_cursor":null}