Using Domain Knowledge for Low Resource Named Entity Recognition
- URL: http://arxiv.org/abs/2203.14738v1
- Date: Mon, 28 Mar 2022 13:26:47 GMT
- Title: Using Domain Knowledge for Low Resource Named Entity Recognition
- Authors: Yuan Shi
- Abstract summary: We propose to use domain knowledge to improve the performance of named entity recognition in areas with low resources.
The proposed model avoids large-scale data adjustments in different domains while handling named entities recognition with low resources.
- Score: 2.749726993052939
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In recent years, named entity recognition has always been a popular research
in the field of natural language processing, while traditional deep learning
methods require a large amount of labeled data for model training, which makes
them not suitable for areas where labeling resources are scarce. In addition,
the existing cross-domain knowledge transfer methods need to adjust the entity
labels for different fields, so as to increase the training cost. To solve
these problems, enlightened by a processing method of Chinese named entity
recognition, we propose to use domain knowledge to improve the performance of
named entity recognition in areas with low resources. The domain knowledge
mainly applied by us is domain dictionary and domain labeled data. We use
dictionary information for each word to strengthen its word embedding and
domain labeled data to reinforce the recognition effect. The proposed model
avoids large-scale data adjustments in different domains while handling named
entities recognition with low resources. Experiments demonstrate the
effectiveness of our method, which has achieved impressive results on the data
set in the field of scientific and technological equipment, and the F1 score
has been significantly improved compared with many other baseline methods.
Related papers
- An Experimental Study on Data Augmentation Techniques for Named Entity Recognition on Low-Resource Domains [0.9903198600681908]
We evaluate the effectiveness of two prominent text augmentation techniques, Mention Replacement and Contextual Word Replacement, on two widely-used NER models, Bi-LSTM+CRF and BERT.
We conduct experiments on four datasets from low-resource domains, and we explore the impact of various combinations of training subset sizes and number of augmented examples.
arXiv Detail & Related papers (2024-11-21T19:45:48Z) - Adapting to Distribution Shift by Visual Domain Prompt Generation [34.19066857066073]
We adapt a model at test-time using a few unlabeled data to address distribution shifts.
We build a knowledge bank to learn the transferable knowledge from source domains.
The proposed method outperforms previous work on 5 large-scale benchmarks including WILDS and DomainNet.
arXiv Detail & Related papers (2024-05-05T02:44:04Z) - Query of CC: Unearthing Large Scale Domain-Specific Knowledge from
Public Corpora [104.16648246740543]
We propose an efficient data collection method based on large language models.
The method bootstraps seed information through a large language model and retrieves related data from public corpora.
It not only collects knowledge-related data for specific domains but unearths the data with potential reasoning procedures.
arXiv Detail & Related papers (2024-01-26T03:38:23Z) - Named Entity Recognition Under Domain Shift via Metric Learning for Life Sciences [55.185456382328674]
We investigate the applicability of transfer learning for enhancing a named entity recognition model.
Our model consists of two stages: 1) entity grouping in the source domain, which incorporates knowledge from annotated events to establish relations between entities, and 2) entity discrimination in the target domain, which relies on pseudo labeling and contrastive learning to enhance discrimination between the entities in the two domains.
arXiv Detail & Related papers (2024-01-19T03:49:28Z) - Style Transfer as Data Augmentation: A Case Study on Named Entity
Recognition [17.892385961143173]
We propose a new method to transform the text from a high-resource domain to a low-resource domain by changing its style-related attributes.
We design a constrained decoding algorithm along with a set of key ingredients for data selection to guarantee the generation of valid and coherent data.
Our approach is a practical solution to data scarcity, and we expect it to be applicable to other NLP tasks.
arXiv Detail & Related papers (2022-10-14T16:02:03Z) - Investigation on Data Adaptation Techniques for Neural Named Entity
Recognition [51.88382864759973]
A common practice is to utilize large monolingual unlabeled corpora.
Another popular technique is to create synthetic data from the original labeled data.
In this work, we investigate the impact of these two methods on the performance of three different named entity recognition tasks.
arXiv Detail & Related papers (2021-10-12T11:06:03Z) - A Review of Single-Source Deep Unsupervised Visual Domain Adaptation [81.07994783143533]
Large-scale labeled training datasets have enabled deep neural networks to excel across a wide range of benchmark vision tasks.
In many applications, it is prohibitively expensive and time-consuming to obtain large quantities of labeled data.
To cope with limited labeled training data, many have attempted to directly apply models trained on a large-scale labeled source domain to another sparsely labeled or unlabeled target domain.
arXiv Detail & Related papers (2020-09-01T00:06:50Z) - Adversarial Knowledge Transfer from Unlabeled Data [62.97253639100014]
We present a novel Adversarial Knowledge Transfer framework for transferring knowledge from internet-scale unlabeled data to improve the performance of a classifier.
An important novel aspect of our method is that the unlabeled source data can be of different classes from those of the labeled target data, and there is no need to define a separate pretext task.
arXiv Detail & Related papers (2020-08-13T08:04:27Z) - Domain Adaption for Knowledge Tracing [65.86619804954283]
We propose a novel adaptable framework, namely knowledge tracing (AKT) to address the DAKT problem.
For the first aspect, we incorporate the educational characteristics (e.g., slip, guess, question texts) based on the deep knowledge tracing (DKT) to obtain a good performed knowledge tracing model.
For the second aspect, we propose and adopt three domain adaptation processes. First, we pre-train an auto-encoder to select useful source instances for target model training.
arXiv Detail & Related papers (2020-01-14T15:04:48Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.