Knowledge-Based Short Text Categorization Using Entity and Category Embedding

Türker, Rima; Zhang, Lei; Koutraki, Maria; Sack, Harald

doi:10.1007/978-3-030-21348-0_23

Cited by 11 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…On a high level, to represent text, these approaches either use: 1) explicit, hand-engineered features or 2) neural networks to model the dependencies within text (implicit features). Very often, conceptual information (entities and their categories) from tweets is captured using a knowledge base (KB) [2]which is then either 1) embedded in a common vector space [31] or 2) further enriched with word and sub-word information from the tweets [34]. While the knowledge-powered approach helps in enriching the semantics, it fails when the entity in the text is not correctly disambiguated or is simply not found in the KB.…”

Section: Short Text Classificationmentioning

confidence: 99%

I-AID: Identifying Actionable Information from Disaster-related Tweets

Zahera¹,

Jalota²,

Sherif³

et al. 2020

Preprint

View full text Add to dashboard Cite

Social media data plays a significant role in modern disaster management by providing valuable data about affected people, donations, help requests and advice. Recent studies highlight the need to filter information on social media into fine-grained content categories. However, identifying useful information from massive amounts of social media posts during a crisis is a challenging task. Automatically categorizing the information (e.g., reports on affected individuals, donations and volunteers) contained in these posts is vital for their efficient handling and consumption by the communities affected and organisations concerned. In this paper, we propose a system, dubbed I-AID, to automatically filter tweets with critical or actionable information from the enormous volume of social media data. Our system combines state-of-the art approaches to process and represent textual data in order to capture its underlying semantics. In particular, we use 1) Bidirectional Encoder Representations from Transformers (commonly known as, BERT) to learn a contextualized vector representation of a tweet, and 2) a graph-based architecture to compute semantic correlations between the entities and hashtags in tweets and their corresponding labels. We conducted our experiments on a real-world dataset of disaster-related tweets. Our experimental results indicate that our model outperforms baselines in terms of F1-score by +11%.

show abstract

Section: Short Text Classificationmentioning

confidence: 99%

I-AID: Identifying Actionable Information from Disaster-related Tweets

Zahera¹,

Jalota²,

Sherif³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…In this paper, keyword selection is a problem with the classification that some suitable keywords for advertisers can be selected from many recommended keywords. Because the number of words in a keyword is small, many experts use short text classification methods to solve this problem [6], [10]- [13].…”

Section: Related Work a Abstractelection On Google Adsmentioning

confidence: 99%

“…4) The performances of traditional classifiers are not satisfactory. Many experts have studied and elaborated on the classification of short texts [6], [10]- [13], but few experts have studied how to choose keywords. In practical applications, it is very difficult to extract the correct characteristics of the keywords and quickly make the classification of the keywords high.…”

mentioning

confidence: 99%

MOPSO-Based CNN for Keyword Selection on Google Ads

et al. 2019

View full text Add to dashboard Cite

Automatically selecting keywords that are satisfactory to advertisers from a large number of keywords provided by Google Ads is the main task of this paper. But there is not too much time for the model to judge whether keywords are selected, choosing correct keywords in the shortest time is another task of this paper. Therefore, a structure of the model that can get some useful keywords for advertisers is designed and an improved multi-objective particle swarm optimization algorithm is proposed to achieve this multiobjective task. These are also the main contributions of this paper. To accomplish this multi-objective task, many technical issues need to be overcome, such as the mixed language problem, the imbalance problem, the problem of extracting features from corpora and so on. This paper proposes a corpus selection method to solve the mixed problem of Chinese and English in keywords, word embedding method to solve the representation of keywords, re-sampling to solve data imbalance problem, improved convolutional neural network (CNN) to solve classification problem, and a multi-objective particle swarm optimization algorithm (MOPSO) to achieve neural structure search of CNN so that the effect of the classification is improved and the training time is reduced. The keyword selection problem is solved with the combination of evolutionary computing, deep learning, machine learning, and text processing techniques. Experimental results show that the proposed algorithm greatly improved the accuracy of keyword selection and shortened the time of selecting keywords. Therefore, this algorithm has a good application value.INDEX TERMS Google Ads, corpus selection, word embedding, re-sampling, CNN, MOPSO, keyword selection, neural structure search. I. INTRODUCTIONGoogle Ads is the advertising agency of Google that provides advertising services to advertisers. The previous name was Google Adwords. Google Ads can push advertisers' ads to Google and Google-related sites and some social media. Such as Google, Facebook, and so on. It is profitable through the advertising of advertisers. The form of the advertisement includes text, pictures, and videos. After advertisersThe associate editor coordinating the review of this article and approving it for publication was Alberto Cano.

show abstract

“…Data sparsity and class imbalance are common problems in text classification tasks (Türker et al, 2019;Zhang and Wu, 2015;Shams, 2014;Kumar et al, 2020), especially when the text to be labelled is from a highly-specialised domain where only scarce domain experts can perform the labelling task (Türker et al, 2019;Ali, 2019). Data Augmentation (DA) is a widely used method for tackling such issues (Anaby-Tavor et al, 2020;Kumar et al, 2020;Papanikolaou and Pierleoni, 2019).…”

Section: Introductionmentioning

confidence: 99%

Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification

Edwards¹,

Ushio²,

Camacho-Collados³

et al. 2021

Preprint

View full text Add to dashboard Cite

Data augmentation techniques are widely used for enhancing the performance of machine learning models by tackling class imbalance issues and data sparsity. State-of-the-art generative language models have been shown to provide significant gains across different NLP tasks. However, their applicability to data augmentation for text classification tasks in fewshot settings have not been fully explored, especially for specialised domains. In this paper, we leverage GPT-2 (Radford et al., 2019) for generating artificial training instances in order to improve classification performance. Our aim is to analyse the impact the selection process of seed training examples have over the quality of GPT-generated samples and consequently the classifier performance. We perform experiments with several seed selection strategies that, among others, exploit class hierarchical structures and domain expert selection. Our results show that fine-tuning GPT-2 in a handful of label instances leads to consistent classification improvements and outperform competitive baselines. Finally, we show that guiding this process through domain expert selection can lead to further improvements, which opens up interesting research avenues for combining generative models and active learning.

show abstract

Knowledge-Based Short Text Categorization Using Entity and Category Embedding

Cited by 11 publications

References 14 publications

I-AID: Identifying Actionable Information from Disaster-related Tweets

I-AID: Identifying Actionable Information from Disaster-related Tweets

MOPSO-Based CNN for Keyword Selection on Google Ads

Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification

Contact Info

Product

Resources

About