Multi-input CNN for Text Classification in Commercial Scenarios

Parcheta, Zuzanna; Sanchis-Trilles, Germán; Casacuberta, Francisco; Redahl, Robin

doi:10.1007/978-3-030-20521-8_49

Cited by 5 publications

(5 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Due to its characteristics, it is difficult to draw any conclusions about the combination of text encoding techniques. What was already confirmed in [24] is that BPE tokenisation has a very positive effect, especially on agglutinative and inflected languages such as Swedish, where the difference in scores over other techniques was significant. However, in this work, the techniques applied at the BPE level always appear in the final combination of embeddings.…”

Section: Results Analysismentioning

confidence: 60%

“…In this work, the multi-input Convolutional Neural Network from [24] was expanded to make it possible to train the network with any text encoding technique as input. We included experiments using four different text encoding techniques such as the Keras embedding layer, GloVe, BERT embeddings, and ParagraphVector.…”

Section: Results Analysismentioning

confidence: 99%

“…In this work, the extension of multi-input CNN for text classification already presented in [24] is described. The new classification model provides the possibility of combining several types of embedding vectors implemented for text that are tokenised at different levels and using different encoding techniques.…”

Section: Approachmentioning

confidence: 99%

See 2 more Smart Citations

Combining Embeddings of Input Data for Text Classification

Parcheta¹,

Sanchis-Trilles²,

Casacuberta³

et al. 2020

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

The problem of automatic text classification is an essential part of text analysis. The improvement of text classification can be done at different levels such as a preprocessing step, network implementation, etc. In this paper, we focus on how the combination of different methods of text encoding may affect classification accuracy. To do this, we implemented a multi-input neural network that is able to encode input text using several text encoding techniques such as BERT, neural embedding layer, GloVe, skip-thoughts and ParagraphVector. The text can be represented at different levels of tokenised input text such as the sentence level, word level, byte pair encoding level and character level. Experiments were conducted on seven datasets from different language families: English, German, Swedish and Czech. Some of those languages contain agglutinations and grammatical cases. Two out of seven datasets originated from real commercial scenarios: 1) classifying ingredients into their corresponding classes by means of a corpus provided by Northfork ; and 2) classifying texts according to the English level of their corresponding writers by means of a corpus provided by ProvenWord. The developed architecture achieves an improvement with different combinations of text encoding techniques depending on the different characteristics of the datasets. Once the best combination of embeddings at different levels was determined, different architectures of multi-input neural networks were compared. The results obtained with the best embedding

show abstract

Section: Results Analysismentioning

confidence: 60%

Section: Results Analysismentioning

confidence: 99%

See 1 more Smart Citation

Combining Embeddings of Input Data for Text Classification

Parcheta¹,

Sanchis-Trilles²,

Casacuberta³

et al. 2020

Neural Process Lett

Self Cite

View full text Add to dashboard Cite

show abstract

“…To address the scarcity problem of MT parallel data in specific-domain, data selection methods utilise an initial in-domain training data to select relevant additional sentences from a generic parallel corpus. Previous research has used n-gram language model (Moore and Lewis, 2010; Axelrod et al, 2011;Duh et al, 2013), count-based methods Parcheta et al, 2018), similarity score of sentence embeddings (Wang et al, 2017;Junczys-Dowmunt, 2018;Dou et al, 2020) to rank the generic corpus. The ranking and selection process often operate in the same language, either source or target language, and take advantage of the parallel corpus to retrieve the paired translation (Farajian et al, 2017).…”

Section: Unsupervised Domain Adaptation Of Nmtmentioning

confidence: 99%

Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection

Vu¹,

Phung

et al. 2021

Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

This paper considers the unsupervised domain adaptation problem for neural machine translation (NMT), where we assume the access to only monolingual text in either the source or target language in the new domain. We propose a cross-lingual data selection method to extract in-domain sentences in the missing language side from a large generic monolingual corpus. Our proposed method trains an adaptive layer on top of multilingual BERT by contrastive learning to align the representation between the source and target language. This then enables the transferability of the domain classifier between the languages in a zero-shot manner. Once the in-domain data is detected by the classifier, the NMT model is then adapted to the new domain by jointly learning translation and domain discrimination tasks. We evaluate our cross-lingual data selection method on NMT across five diverse domains in three language pairs, as well as a real-world scenario of translation for COVID-19. The results show that our proposed method outperforms other selection baselines up to +1.5 BLEU score.

show abstract

“…A text classification using a Multi-input convolutional neural network is proposed [10]. In this paper, the author executed pre-processing at two levels i.e.…”

Section: Introductionmentioning

confidence: 99%

Sense understanding of text conversation using temporal convolution neural network

Rathor

Agrawal

2022

Multimed Tools Appl

View full text Add to dashboard Cite

This paper proposes a model which uses Spatio Temporal features for real-time sense understanding of a text conversation. The proposed model uses CNN along with the concept of LSTM to create a new Spatio temporal cell. Furthermore, the proposed model is used to classify the sentences into eight senses. The model achieved an F-Score around 0.984 on sense classification. Additionally, the efficiency and capabilities of the model are also tested on a standard IMDB sentiment classification dataset. On the IMDB dataset, the model gave an accuracy of 89.27. The experimental results show that the proposed model works better than a CNN model, a Bi-LSTM model, and a combination of CNN & LSTM model in terms of a number of parameters and execution time.

show abstract

Multi-input CNN for Text Classification in Commercial Scenarios

Cited by 5 publications

References 12 publications

Combining Embeddings of Input Data for Text Classification

Combining Embeddings of Input Data for Text Classification

Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection

Sense understanding of text conversation using temporal convolution neural network

Contact Info

Product

Resources

About