1 |
OpenFraming: open-sourced tool for computational framing analysis of multilingual data
|
|
|
|
BASE
|
|
Show details
|
|
2 |
"Wikily" Supervised Neural Translation Tailored to Cross-Lingual Tasks ...
|
|
|
|
BASE
|
|
Show details
|
|
3 |
Majority Voting with Bidirectional Pre-translation For Bitext Retrieval ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Wikily Supervised Neural Translation Tailored to Cross-Lingual Tasks ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Detecting Frames in News Headlines and Lead Images in U.S. Gun Violence Coverage ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
OpenFraming: Open-sourced Tool for Computational Framing Analysis of Multilingual Data ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
IndoCollex: A Testbed for Morphological Transformation of Indonesian Word Colloquialism ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
LAL: linguistically aware learning for scene text recognition
|
|
|
|
BASE
|
|
Show details
|
|
10 |
Learning to scale multilingual representations for vision-language tasks
|
|
|
|
Abstract:
Current multilingual vision-language models either require a large number of additional parameters for each supported language, or suffer performance degradation as languages are added. In this paper, we propose a Scalable Multilingual Aligned Language Representation (SMALR) that supports many languages with few model parameters without sacrificing downstream task performance. SMALR learns a fixed size language-agnostic representation for most words in a multilingual vocabulary, keeping language-specific features for just a few. We use a masked cross-language modeling loss to align features with context from other languages. Additionally, we propose a cross-lingual consistency module that ensures predictions made for a query and its machine translation are comparable. The effectiveness of SMALR is demonstrated with ten diverse languages, over twice the number supported in vision-language tasks to date. We evaluate on multilingual image-sentence retrieval and outperform prior work by 3-4% with less than 1/5th the training parameters compared to other word embedding methods. ; Published version
|
|
Keyword:
Computation and language; Computer vision and pattern recognition; Scalable Multilingual Aligned Language Representation
|
|
URL: https://hdl.handle.net/2144/43499
|
|
BASE
|
|
Hide details
|
|
12 |
Learning to scale multilingual representations for vision-language tasks
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Learning to Scale Multilingual Representations for Vision-Language Tasks ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Resolving Pronouns in Twitter Streams: Context can Help! ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Winter is here: summarizing Twitter streams related to pre-scheduled events
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Detecting frames in news headlines and its application to analyzing news framing trends surrounding U.S. gun violence
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Learning translations via images with a massively multilingual image dataset
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Learning Translations via Matrix Completion
|
|
|
|
In: Conference on Empirical Methods in Natural Language Processing ; https://hal.archives-ouvertes.fr/hal-01838532 ; Conference on Empirical Methods in Natural Language Processing, Sep 2017, Copenhagen, Denmark (2017)
|
|
BASE
|
|
Show details
|
|
|
|