Crosslingual Topic Modeling with WikiPDA

Piccardi, Tiziano; West, Robert

doi:10.1145/3442381.3449805

Cited by 6 publications

(3 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When models are trained for Wikipedia-specific tasks, however, there are many language-agnostic features that can potentially be used to boost performance in lower-resourced languages. For example, in training topic models for Wikipedia, Piccardi & West (2021) and Johnson et al (2021a) relied not on the words in an article but the links. Article links can be mapped to language-agnostic Wikidata IDs such that e.g., a link on English Wikipedia to the article for poblano peppers will be represented identically as a link to chiles poblanos 36 .…”

Section: Situated Researchersmentioning

confidence: 99%

Considerations for Multilingual Wikipedia Research

Johnson¹,

Lescak²

2022

Preprint

View full text Add to dashboard Cite

English Wikipedia has long been an important data source for much research and natural language machine learning modeling. The growth of non-English language editions of Wikipedia, greater computational resources, and calls for equity in the performance of language and multimodal models have led to the inclusion of many more language editions of Wikipedia in datasets and models. Building better multilingual and multimodal models requires more than just access to expanded datasets; it also requires a better understanding of what is in the data and how this content was generated. This paper seeks to provide some background to help researchers think about what differences might arise between different language editions of Wikipedia and how that might affect their models. It details three major ways in which content differences between language editions arise (local context, community and governance, and technology) and recommendations for good practices when using multilingual and multimodal data for research and modeling.

show abstract

Section: Situated Researchersmentioning

confidence: 99%

Considerations for Multilingual Wikipedia Research

Johnson¹,

Lescak²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…6 Examples of TM applications in digital social sciences and humanities include finding geographic themes from GPS-associated documents on social media platforms such as Flickr and Twitter, 7 selecting news articles on opposition to Euro currency from Financial Times data, 8 identifying paragraphs on epistemological concerns in English and German novels, 9 tracking research trends in different disciplines, 10 and revealing dominant themes in newspapers, 11 governance literature, 12 and Wikipedia entries. 13 Topic modeling was applied in addition to text mining to enhance access to large digital collections by providing minimal description and enriching metadata, including subject headings. 14 Also, a possibility of using topic modeling to determine the subject headings for books on Project Gutenberg was explored.…”

Section: Topic Modeling and Its Applicationsmentioning

confidence: 99%

Applying Topic Modeling for Automated Creation of Descriptive Metadata for Digital Collections

Glowacka-Musial

2022

ITAL

View full text Add to dashboard Cite

Creation of descriptive metadata for digital objects tends to be a laborious process. Specifically, subject analysis that seeks to classify the intellectual content of digitized documents typically requires considerable time and effort to determine subject headings that best represent the substance of these documents. This project examines the use of topic modeling to streamline the workflow for assigning subject headings to the digital collection of New Mexico State University news releases issued between 1958 and 2020. The optimization of the workflow enables timely scholarly access to unique primary source documentation.

show abstract

“…Some approaches use the word-aligned corpus where the topic model is achieved by optimizing the semantic distribution of words [ 22 , 23 ]. The disadvantage is that it is limited by multilingual vocabulary alignment resources [ 24 ]. Other studies are focusing on the document alignment corpus, which utilize large aligned corpora effectively and map multilingual documents to corresponding topic distributions through training [ 25 , 26 , 27 , 28 ].…”

Section: Related Workmentioning

confidence: 99%

Deep Multilabel Multilingual Document Learning for Cross-Lingual Document Retrieval

Feng

Huang

et al. 2022

Entropy

View full text Add to dashboard Cite

Cross-lingual document retrieval, which aims to take a query in one language to retrieve relevant documents in another, has attracted strong research interest in the last decades. Most studies on this task start with cross-lingual comparisons at the word level and then represent documents via word embeddings, which leads to insufficient structure information. In this work, the cross-lingual comparison at the document level is achieved through the cross-lingual semantic space. Our method, MDL (deep multilabel multilingual document learning), leverages a six-layer fully connected network to project cross-lingual documents into a shared semantic space. The semantic distances can be calculated when the cross-lingual documents are transformed into embeddings in semantic space. The supervision signals are automatically extracted from the data and then used to construct the semantic space via a linear classifier. The ambiguity of manual labels could be avoided and the multilabel supervision signals can be acquired instead of a single label. The representation of the semantic space is enriched by multilabel supervision signals, which improves the discriminative ability of the embeddings. The MDL is easy to extend to other fields since it does not depend on specific data. Furthermore, MDL is more efficient than the models training all languages jointly, since each language is trained individually. Experiments on Wikipedia data showed that the proposed method outperforms the state-of-the-art cross-lingual document retrieval methods.

show abstract

Crosslingual Topic Modeling with WikiPDA

Cited by 6 publications

References 37 publications

Considerations for Multilingual Wikipedia Research

Considerations for Multilingual Wikipedia Research

Applying Topic Modeling for Automated Creation of Descriptive Metadata for Digital Collections

Deep Multilabel Multilingual Document Learning for Cross-Lingual Document Retrieval

Contact Info

Product

Resources

About