| 1 |
Homepage2Vec: Language-Agnostic Website Embedding and Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Classifying Dyads for Militarized Conflict Analysis
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Cognitive Network Topology and Optimization of the Mental Lexicon ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 6 |
Linguistic effects on news headline success: Evidence from thousands of online field experiments (Registered Report Protocol)
|
|
|
|
In: PLoS One (2021)
|
|
BASE
|
|
Show details
|
|
|
| 7 |
On the Limitations of Cross-lingual Encoders as Exposed by Reference-Free Machine Translation Evaluation ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 8 |
On the limitations of cross-lingual encoders as exposed by reference-free machine translation evaluation
|
|
|
|
BASE
|
|
Show details
|
|
|
| 10 |
Crosslingual Document Embedding as Reduced-Rank Ridge Regression ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 14 |
Causal Effects of Brevity on Style and Success in Social Media ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 15 |
Message Distortion in Information Cascades
|
|
|
|
In: http://infoscience.epfl.ch/record/270657 (2019)
|
|
BASE
|
|
Show details
|
|
|
| 17 |
Reverse-Engineering Satire, or "Paper on Computational Humor Accepted despite Making Serious Advances"
|
|
|
|
In: http://infoscience.epfl.ch/record/271147 (2019)
|
|
BASE
|
|
Show details
|
|
|
| 18 |
Why the World Reads Wikipedia: Beyond English Speakers
|
|
|
|
In: http://infoscience.epfl.ch/record/270302 (2019)
|
|
BASE
|
|
Show details
|
|
|
| 19 |
Crosslingual Document Embedding as Reduced-Rank Ridge Regression
|
|
|
|
In: http://infoscience.epfl.ch/record/263893 (2019)
|
|
Abstract:
There has recently been much interest in extending vector-based word representations to multiple languages, such that words can be compared across languages. In this paper, we shift the focus from words to documents and introduce a method for embedding documents written in any language into a single, language-independent vector space. For training, our approach leverages a multilingual corpus where the same concept is covered in multiple languages (but not necessarily via exact translations), such as Wikipedia. Our method, Cr5 (Crosslingual reduced-rank ridge regression), starts by training a ridge-regression-based classifier that uses language-specific bag-of-word features in order to predict the concept that a given document is about. We show that, when constraining the learned weight matrix to be of low rank, it can be factored to obtain the desired mappings from language-specific bags-of-words to language-independent embeddings. As opposed to most prior methods, which use pretrained monolingual word vectors, postprocess them to make them crosslingual, and finally average word vectors to obtain document vectors, Cr5 is trained end-to-end and is thus natively crosslingual as well as document-level. Moreover, since our algorithm uses the singular value decomposition as its core operation, it is highly scalable. Experiments show that our method achieves state-of-the-art performance on a crosslingual document retrieval task. Finally, although not trained for embedding sentences and words, it also achieves competitive performance on crosslingual sentence and word retrieval tasks.
|
|
URL: http://infoscience.epfl.ch/record/263893
https://doi.org/10.1145/3289600.3291023
http://infoscience.epfl.ch/record/263893/files/cr5%20paper.pdf
|
|
BASE
|
|
Hide details
|
|
|
| 20 |
Churn Intent Detection in Multilingual Chatbot Conversations and Social Media ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|
|
