Few-shot classification in named entity recognition task

Fritzler, Alexander; Logacheva, Varvara; Kretov, Maksim

doi:10.1145/3297280.3297378

Cited by 152 publications

(144 citation statements)

References 15 publications

(18 reference statements)

Supporting

Mentioning

143

Contrasting

Unclassified

Order By: Relevance

“…One way to train the NER model with low-resource is dictionary-based distantly supervision (Fries et al, 2017;Shang et al, 2018;Yang et al, 2018; which builds a dictionary of entities for creating training data without too much effort. Few-shot learning is another promising way for training the NER model under limited supervision by transferring prior knowledge of the source domain to a new domain (Fritzler et al, 2019;Hou et al, 2019). There are also some works that focus on redefining NER as a different problem for reducing the need of hand-labeled training data.…”

Section: Related Workmentioning

confidence: 99%

Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition

Zeng¹,

Li²,

Zhai³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Past progress on neural models has proven that named entity recognition is no longer a problem if we have enough labeled data. However, collecting enough data and annotating them are labor-intensive, time-consuming, and expensive. In this paper, we decompose the sentence into two parts: entity and context, and rethink the relationship between them and model performance from a causal perspective. Based on this, we propose the Counterfactual Generator, which generates counterfactual examples by the interventions on the existing observational examples to enhance the original dataset. Experiments across three datasets show that our method improves the generalization ability of models under limited observational examples. Besides, we provide a theoretical foundation by using a structural causal model to explore the spurious correlations between input features and output labels. We investigate the causal effects of entity or context on model performance under both conditions: the non-augmented and the augmented. Interestingly, we find that the non-spurious correlations are more located in entity representation rather than context representation. As a result, our method eliminates part of the spurious correlations between context representation and output labels. The code is available at https://github.com/xijiz/cfgen.

show abstract

Section: Related Workmentioning

confidence: 99%

Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition

Zeng¹,

Li²,

Zhai³

et al. 2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

show abstract

“…Prior work (Fritzler et al, 2019;Hou et al, 2020) on few-shot NER followed few-shot classification literature and adopted the episode evaluation methodology. Specifically, a NER system is evaluated with respect to multiple evaluation episodes.…”

Section: A Standard Evaluation Setupmentioning

confidence: 99%

“…In the context of NER, these fewshot classification methods can enable rapid building of NER systems for a new domain by labeling only a few examples per entity class. Several previous studies (Fritzler et al, 2019;Hou et al, 2020) propose using prototypical networks (Snell et al, 2017), a popular few-shot classification algorithm, to address the few-shot NER problem. However, these approaches only achieve 10 ∼ 30% F1 scores on average, when transferring knowledge between different NER datasets with one or five shot examples, warranting more effective methods for the problem.…”

Section: Introductionmentioning

confidence: 99%

Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning

Yang¹,

Katiyar²

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

116

113

View full text Add to dashboard Cite

We present a simple few-shot named entity recognition (NER) system based on nearest neighbor learning and structured inference. Our system uses a supervised NER model trained on the source domain, as a feature extractor. Across several test domains, we show that a nearest neighbor classifier in this featurespace is far more effective than the standard meta-learning approaches. We further propose a cheap but effective method to capture the label dependencies between entity tags without expensive CRF training. We show that our method of combining structured decoding with nearest neighbor learning achieves stateof-the-art performance on standard few-shot NER evaluation tasks, improving F1 scores by 6% to 16% absolute points over prior metalearning based systems.

show abstract

“…In one of the first works on few-shot sequence labeling, Fritzler et al (2019) apply prototypical networks to few-shot named entity recognition by training a separate prototypical network for each named entity type. This design choice makes their extension of prototypical networks more restrictive than ours, which trains a single model to classify all sequence tags.…”

Section: Few-shot Learning For Sequence Labelingmentioning

confidence: 99%

Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI

2020

View full text Add to dashboard Cite

One of the core components of voice assistants is the Natural Language Understanding (NLU) model. Its ability to accurately classify the user's request (or "intent") and recognize named entities in an utterance is pivotal to the success of these assistants. NLU models can be challenged in some languages by code-switching or morphological and orthographic variations. This work explores the possibility of improving the accuracy of NLU models for Indic languages via the use of alternate representations of input text for NLU, specifically ISO-15919 and IndicSOUNDEX, a custom SOUNDEX designed to work for Indic languages. We used a deep neural network based model to incorporate the information from alternate representations into the NLU model. We show that using alternate representations significantly improves the overall performance of NLU models when the amount of training data is limited.

show abstract

Few-shot classification in named entity recognition task

Cited by 152 publications

References 15 publications

Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition

Counterfactual Generator: A Weakly-Supervised Method for Named Entity Recognition

Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning

Proceedings of the 2nd Workshop on Natural Language Processing for Conversational AI

Contact Info

Product

Resources

About