Learning to Tag OOV Tokens by Integrating Contextual Representation and Background Knowledge

He, Keqing; Yan, Yuanmeng; Wang, Xu

doi:10.18653/v1/2020.acl-main.58

Cited by 18 publications

(14 citation statements)

References 15 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We classify the existing methods of detecting OOD intents into two main categories, supervised and unsupervised OOD detection. Supervised OOD detection (Scheirer et al, 2013;Fei and Liu, 2016;Kim and Kim, 2018;Larson et al, 2019;He et al, 2020c;Zheng et al, 2020) represents that there are extensive labeled OOD samples in the training data while unsupervised OOD detection (Breunig et al, 2000;Bendale and Boult, 2016;Hendrycks and Gimpel, 2017;Shu et al, 2017;Lee et al, 2018;Ren et al, 2019;Lin and Xu, 2019) means few or no labeled OOD samples except for labeled in-domain data. Unsupervised OOD detection makes it more complicated to identify unknown intents due to unseen and diverse semantic expressions.…”

Section: Introductionmentioning

confidence: 99%

A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space

Yan

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

Self Cite

View full text Add to dashboard Cite

Detecting out-of-domain (OOD) input intents is critical in the task-oriented dialog system. Different from most existing methods that rely heavily on manually labeled OOD samples, we focus on the unsupervised OOD detection scenario where there are no labeled OOD samples except for labeled in-domain data. In this paper, we propose a simple but strong generative distancebased classifier to detect OOD samples. We estimate the class-conditional distribution on feature spaces of DNNs via Gaussian discriminant analysis (GDA) to avoid over-confidence problems. And we use two distance functions, Euclidean and Mahalanobis distances, to measure the confidence score of whether a test sample belongs to OOD. Experiments on four benchmark datasets show that our method can consistently outperform the baselines.

show abstract

Section: Introductionmentioning

confidence: 99%

A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space

Yan

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

Self Cite

View full text Add to dashboard Cite

show abstract

“…where FFNN c is a feedforward network mapping from R 2×d → R. Then we compute an additional sentinel vector c i (Yang and Mitchell, 2017;He et al, 2020) and also compute a score α i for it:…”

Section: Final Span Graph Predictionmentioning

confidence: 99%

Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference

Lai¹,

Ji²,

Zhai³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

View full text Add to dashboard Cite

Compared to the general news domain, information extraction (IE) from biomedical text requires much broader domain knowledge. However, many previous IE methods do not utilize any external knowledge during inference. Due to the exponential growth of biomedical publications, models that do not go beyond their fixed set of parameters will likely fall behind. Inspired by how humans look up relevant information to comprehend a scientific text, we present a novel framework that utilizes external knowledge for joint entity and relation extraction named KECI (Knowledge-Enhanced Collective Inference). Given an input text, KECI first constructs an initial span graph representing its initial understanding of the text. It then uses an entity linker to form a knowledge graph containing relevant background knowledge for the the entity mentions in the text. To make the final predictions, KECI fuses the initial span graph and the knowledge graph into a more refined graph using an attention mechanism. KECI takes a collective approach to link mention spans to entities by integrating global relational information into local representations using graph convolutional networks. Our experimental results show that the framework is highly effective, achieving new state-of-theart results in two different benchmark datasets: BioRelEx (binding interaction detection) and ADE (adverse drug event extraction). For example, KECI achieves absolute improvements of 4.59% and 4.91% in F1 scores over the stateof-the-art on the BioRelEx entity and relation extraction tasks 1 .

show abstract

“…OOV Recognition OOV aims to recognize unseen slot values in training set for pre-defined slot types, using character embedding (Liang et al, 2017a), copy mechanism (Zhao and Feng, 2018), few/zeroshot learning (Hu et al, 2019;Shah et al, 2019), transfer learning (Chen and Moschitti, 2019;He et al, 2020c) and background knowledge (Yang and Mitchell, 2017;He et al, 2020d), etc. Our proposed NSD task focuses on detecting unknown slot types, not just unseen values.…”

Section: Related Workmentioning

confidence: 99%

Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System

Wu¹,

Zeng²,

He³

et al. 2021

Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Confer

Self Cite

View full text Add to dashboard Cite

Existing slot filling models can only recognize pre-defined in-domain slot types from a limited slot set. In the practical application, a reliable dialogue system should know what it does not know. In this paper, we introduce a new task, Novel Slot Detection (NSD), in the task-oriented dialogue system. NSD aims to discover unknown or out-of-domain slot types to strengthen the capability of a dialogue system based on in-domain training data. Besides, we construct two public NSD datasets, propose several strong NSD baselines, and establish a benchmark for future work. Finally, we conduct exhaustive experiments and qualitative analysis to comprehend key challenges and provide new guidance for future directions 1 .

show abstract

Learning to Tag OOV Tokens by Integrating Contextual Representation and Background Knowledge

Cited by 18 publications

References 15 publications

A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space

A Deep Generative Distance-Based Classifier for Out-of-Domain Detection with Mahalanobis Space

Joint Biomedical Entity and Relation Extraction with Knowledge-Enhanced Collective Inference

Novel Slot Detection: A Benchmark for Discovering Unknown Slot Types in the Task-Oriented Dialogue System

Contact Info

Product

Resources

About