1 |
Unsupervised Cross-Lingual Information Retrieval using Monolingual Data Only ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only ...
|
|
|
|
Abstract:
We propose a fully unsupervised framework for ad-hoc cross-lingual information retrieval (CLIR) which requires no bilingual data at all. The framework leverages shared cross-lingual word embedding spaces in which terms, queries, and documents can be represented, irrespective of their actual language. The shared embedding spaces are induced solely on the basis of monolingual corpora in two languages through an iterative process based on adversarial neural networks. Our experiments on the standard CLEF CLIR collections for three language pairs of varying degrees of language similarity (English-Dutch/Italian/Finnish) demonstrate the usefulness of the proposed fully unsupervised approach. Our CLIR models with unsupervised cross-lingual embeddings outperform baselines that utilize cross-lingual embeddings induced relying on word-level and document-level alignments. We then demonstrate that further improvements can be achieved by unsupervised ensemble CLIR models. We believe that the proposed framework is the ...
|
|
Keyword:
cross-lingual vector spaces; Unsupervised cross-lingual IR
|
|
URL: https://www.repository.cam.ac.uk/handle/1810/279400 https://dx.doi.org/10.17863/cam.26775
|
|
BASE
|
|
Hide details
|
|
3 |
Adversarial Propagation and Zero-Shot Cross-Lingual Transfer of Word Vector Specialization ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
A Resource-Light Method for Cross-Lingual Semantic Textual Similarity ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Post-Specialisation: Retrofitting Vectors of Words Unseen in Lexical Resources ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only
|
|
|
|
BASE
|
|
Show details
|
|
8 |
ArguminSci: a tool for analyzing argumentation and rhetorical aspects in scientific writing
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Investigating the role of argumentation in the rhetorical analysis of scientific publications with neural multi-task learning models
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Post-specialisation: Retrofitting vectors of words unseen in lexical resources
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Discriminating between lexico-semantic relations with the specialization tensor model
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Adversarial propagation and zero-shot cross-lingual transfer of word vector specialization
|
|
|
|
BASE
|
|
Show details
|
|
15 |
A resource-light method for cross-lingual semantic textual similarity
|
|
|
|
BASE
|
|
Show details
|
|
|
|