Training Effective Neural CLIR by Bridging the Translation Gap

@article{Bonab2020TrainingEN,
  title={Training Effective Neural CLIR by Bridging the Translation Gap},
  author={Hamed Bonab and S. Sarwar and J. Allan},
  journal={Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval},
  year={2020}
}
  • Hamed Bonab, S. Sarwar, J. Allan
  • Published 2020
  • Computer Science
  • Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
  • We introduce Smart Shuffling, a cross-lingual embedding (CLE) method that draws from statistical word alignment approaches to leverage dictionaries, producing dense representations that are significantly more effective for cross-language information retrieval (CLIR) than prior CLE methods. This work is motivated by the observation that although neural approaches are successful for monolingual IR, they are less effective in the cross-lingual setting. We hypothesize that neural CLIR fails because… CONTINUE READING

    References

    SHOWING 1-10 OF 12 REFERENCES
    Unsupervised Cross-Lingual Information Retrieval Using Monolingual Data Only
    • 36
    • Highly Influential
    • PDF
    Monolingual and Cross-Lingual Information Retrieval Models Based on (Bilingual) Word Embeddings
    • 215
    • Highly Influential
    • PDF
    How to (Properly) Evaluate Cross-Lingual Word Embeddings: On Strong Baselines, Comparative Analyses, and Some Misconceptions
    • 90
    • Highly Influential
    • PDF
    A Survey of Cross-lingual Word Embedding Models
    • 215
    • Highly Influential
    • PDF
    Simple task-specific bilingual word embeddings
    • 108
    • Highly Influential
    • PDF
    Linguistic Regularities in Continuous Space Word Representations
    • 2,663
    • Highly Influential
    • PDF
    Cross-Language Information Retrieval
    • G. Grefenstette
    • Computer Science
    • The Springer International Series on Information Retrieval
    • 1998
    • 427
    • Highly Influential
    Translation techniques in cross-language information retrieval
    • 519
    • Highly Influential
    • PDF
    A Deep Relevance Matching Model for Ad-hoc Retrieval
    • 478
    • Highly Influential
    • PDF
    Distributed Representations of Words and Phrases and their Compositionality
    • 20,872
    • Highly Influential
    • PDF