Cross-language linking of news stories on the web using interlingual topic modelling

Smet, Wim De; Moens, Marie‐Francine

doi:10.1145/1651437.1651447

Cited by 39 publications

(27 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In order to tackle this issue, recent work relies on the supervision-lighter framework of multilingual probabilistic topic modeling (MuPTM) (Mimno, Wallach, Naradowsky, Smith, & McCallum, 2009;Boyd-Graber & Blei, 2009;De Smet & Moens, 2009;Ni, Sun, Hu, & Chen, 2009;Zhang, Mei, & Zhai, 2010;Fukumasu, Eguchi, & Xing, 2012) or other similar models for latent structure induction (Haghighi, Liang, Berg-Kirkpatrick, & Klein, 2008;Daumé III & Jagarlamudi, 2011).…”

Section: Bilingual Word Representations From Document-aligned Datamentioning

confidence: 99%

“…More recent work on multilingual probabilistic topic modeling (MuPTM) (Mimno et al, 2009;De Smet & Moens, 2009;Vulić et al, 2011) showed that word representations of higher quality may be built if a multilingual topic model such as bilingual LDA (BiLDA) is trained jointly on document-aligned comparable corpora by retaining the structure of the corpus intact (i.e., there is no need to construct pseudo-bilingual documents).…”

Section: Basic-muptmmentioning

confidence: 99%

See 1 more Smart Citation

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

Vulić

Moens

2016

jair

Self Cite

View full text Add to dashboard Cite

We propose a new model for learning bilingual word representations from non-parallel document-aligned data. Following the recent advances in word representation learning, our model learns dense real-valued word vectors, that is, bilingual word embeddings (BWEs). Unlike prior work on inducing BWEs which heavily relied on parallel sentence-aligned corpora and/or readily available translation resources such as dictionaries, the article reveals that BWEs may be learned solely on the basis of document-aligned comparable data without any additional lexical resources nor syntactic information. We present a comparison of our approach with previous state-of-the-art models for learning bilingual word representations from comparable data that rely on the framework of multilingual probabilistic topic modeling (MuPTM), as well as with distributional local context-counting models. We demonstrate the utility of the induced BWEs in two semantic tasks: (1) bilingual lexicon extraction, (2) suggesting word translations in context for polysemous words. Our simple yet effective BWE-based models significantly outperform the MuPTM-based and contextcounting representation models from comparable data as well as prior BWE-based models, and acquire the best reported results on both tasks for all three tested language pairs.

show abstract

Section: Bilingual Word Representations From Document-aligned Datamentioning

confidence: 99%

Section: Basic-muptmmentioning

confidence: 99%

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

Vulić

Moens

2016

jair

Self Cite

View full text Add to dashboard Cite

show abstract

“…Another potential solution to diversity is the use of topic models, such as latent Dirichlet allocation (LDA), where the similarity between two documents is measured via the similarity of the latent topics they share rather than by direct content comparison [3]. Recently, based on seminal work on multilingual topic modeling [22], multimodal extensions of LDA were proposed for cross-modal video hyperlinking [4], combining the potential for diversity offered by topic models and by multimodality. As for BiDNN, bag-of-words representations of words from automatic transcripts and of visual concepts in keyframes are used in bimodal LDA (BiLDA).…”

Section: Bidirectional Deep Neural Networkmentioning

confidence: 99%

“…As a result, documents are seen as mixtures of latent topics, while topics are probability distributions over words. The multimodal extension in [4] considers that each latent topic is defined by two probability distributions, one over each modality (or language in [22]). The BiLDA model is thus trained on parallel documents, assuming that the underlying topic distribution is common to the two modalities.…”

Section: Bidirectional Deep Neural Networkmentioning

confidence: 99%

Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity

Bois

Vukotić

Simon

et al. 2016

MultiMedia Modeling

View full text Add to dashboard Cite

Abstract. Video hyperlinking is the process of creating links within a collection of videos. Starting from a given set of video segments, called anchors, a set of related segments, called targets, must be provided. In the past years, a number of content-based approaches have been proposed with good results obtained by searching for target segments that are very similar to the anchor in terms of content and information. Unfortunately, relevance has been obtained to the expense of diversity. In this paper, we study multimodal approaches and their ability to provide a set of diverse yet relevant targets. We compare two recently introduced crossmodal approaches, namely, deep auto-encoders and bimodal LDA, and experimentally show that both provide significantly more diverse targets than a state-of-the-art baseline. Bimodal auto-encoders offer the best trade-off between relevance and diversity, with bimodal LDA exhibiting slightly more diverse targets at a lower precision.

show abstract

“…We have in-house software that implements this model. We gloss over much of the details, but more information may be found in [29], [30].…”

mentioning

confidence: 99%

Fashion Meets Computer Vision and NLP at e-Commerce Search

Zoghbi¹,

Heyman²,

Gómez³

et al. 2016

IJCEE

Self Cite

View full text Add to dashboard Cite

Abstract:In this paper, we focus on cross-modal (visual and textual) e-commerce search within the fashion domain. Particularly, we investigate two tasks: 1) given a query image, we retrieve textual descriptions that correspond to the visual attributes in the query; and 2) given a textual query that may express an interest in specific visual product characteristics, we retrieve relevant images that exhibit the required visual attributes. To this end, we introduce a new dataset that consists of 53,689 images coupled with textual descriptions. The images contain fashion garments that display a great variety of visual attributes, such as different shapes, colors and textures in natural language. Unlike previous datasets, the text provides a rough and noisy description of the item in the image. We extensively analyze this dataset in the context of cross-modal e-commerce search. We investigate two state-of-the-art latent variable models to bridge between textual and visual data: bilingual latent Dirichlet allocation and canonical correlation analysis. We use state-of-the-art visual and textual features and report promising results.

show abstract

Cross-language linking of news stories on the web using interlingual topic modelling

Cited by 39 publications

References 22 publications

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

Bilingual Distributed Word Representations from Document-Aligned Comparable Data

Exploiting Multimodality in Video Hyperlinking to Improve Target Diversity

Fashion Meets Computer Vision and NLP at e-Commerce Search

Contact Info

Product

Resources

About