Heterogeneous document embeddings for cross-lingual text classification

Moreo, Alejandro; Pedrotti, Andrea; Sebastiani, Fabrizio

doi:10.1145/3412841.3442093

Cited by 5 publications

(3 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another issue is the development of community question answering systems for low-resource languages, such as Arabic and Semitic languages, which have in general lower performances than systems developed for rich-resource languages such as English and Chinese. Cross-lingual text classification and retrieval methods exploiting correlations on distinct language-dependent feature spaces can be a promising research direction to design more effective systems in different languages [115]. Not forgetting the contributions to the field of NLP by leading search engine companies such as Google (just think at the language models based on BERT).…”

Section: Emerging Flexible Query Answering Topicsmentioning

confidence: 99%

The Power and Potentials of Flexible Query Answering Systems: A Critical and Comprehensive Analysis

Andreasen¹,

Bordogna²,

Tré³

et al. 2022

SSRN Journal

View full text Add to dashboard Cite

Section: Emerging Flexible Query Answering Topicsmentioning

confidence: 99%

The Power and Potentials of Flexible Query Answering Systems: A Critical and Comprehensive Analysis

Andreasen¹,

Bordogna²,

Tré³

et al. 2022

SSRN Journal

View full text Add to dashboard Cite

“…In an earlier, shorter version of this paper[45] we report different results for the very same datasets. The reason of the difference is that in[45] we use concatenation as the aggregation policy while we here use averaging.…”

mentioning

confidence: 99%

Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification

Moreo

Pedrotti

Sebastiani

2022

ACM Trans. Inf. Syst.

Self Cite

View full text Add to dashboard Cite

Funnelling ( Fun ) is a recently proposed method for cross-lingual text classification (CLTC) based on a two-tier learning ensemble for heterogeneous transfer learning (HTL). In this ensemble method, 1st-tier classifiers, each working on a different and language-dependent feature space, return a vector of calibrated posterior probabilities (with one dimension for each class) for each document, and the final classification decision is taken by a meta-classifier that uses this vector as its input. The meta-classifier can thus exploit class-class correlations, and this (among other things) gives Fun an edge over CLTC systems in which these correlations cannot be brought to bear. In this paper we describe Generalized Funnelling ( gFun ), a generalisation of Fun consisting of an HTL architecture in which 1st-tier components can be arbitrary view-generating functions , i.e., language-dependent functions that each produce a language-independent representation (“view”) of the (monolingual) document. We describe an instance of gFun in which the meta-classifier receives as input a vector of calibrated posterior probabilities (as in Fun ) aggregated to other embedded representations that embody other types of correlations, such as word-class correlations (as encoded by Word-Class Embeddings ), word-word correlations (as encoded by Multilingual Unsupervised or Supervised Embeddings ), and word-context correlations (as encoded by multilingual BERT ). We show that this instance of gFun substantially improves over Fun and over state-of-the-art baselines, by reporting experimental results obtained on two large, standard datasets for multilingual multilabel text classification. Our code that implements gFun is publicly available.

show abstract

mentioning

confidence: 99%

Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification

Moreo¹,

Pedrotti²,

Sebastiani³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Funnelling (Fun) is a recently proposed method for cross-lingual text classification (CLTC) based on a two-tier learning ensemble for heterogeneous transfer learning (HTL). In this ensemble method, 1st-tier classifiers, each working on a different and language-dependent feature space, return a vector of calibrated posterior probabilities (with one dimension for each class) for each document, and the final classification decision is taken by a metaclassifier that uses this vector as its input. The metaclassifier can thus exploit class-class correlations, and this (among other things) gives Fun an edge over CLTC systems in which these correlations cannot be brought to bear. In this paper we describe Generalized Funnelling (gFun), a generalization of Fun consisting of an HTL architecture in which 1st-tier components can be arbitrary view-generating functions, i.e., language-dependent functions that each produce a language-independent representation ("view") of the document. We describe an instance of gFun in which the metaclassifier receives as input a vector of calibrated posterior probabilities (as in Fun) aggregated to other embedded representations that embody other types of correlations, such as word-class correlations (as encoded by Word-Class Embeddings), wordword correlations (as encoded by Multilingual Unsupervised or Supervised Embeddings), and word-context correlations (as encoded by multilingual BERT ). We show that this instance of gFun substantially improves over Fun and over state-of-the-art baselines, by reporting experimental results obtained on two large, standard datasets for multilingual multilabel text classification. Our code that implements gFun is publicly available. CCS Concepts: • Computing methodologies → Ensemble methods; Supervised learning by classification.

show abstract

Heterogeneous document embeddings for cross-lingual text classification

Cited by 5 publications

References 6 publications

The Power and Potentials of Flexible Query Answering Systems: A Critical and Comprehensive Analysis

The Power and Potentials of Flexible Query Answering Systems: A Critical and Comprehensive Analysis

Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification

Generalized Funnelling: Ensemble Learning and Heterogeneous Document Embeddings for Cross-Lingual Text Classification

Contact Info

Product

Resources

About