1 |
Jibes & Delights: A Dataset of Targeted Insults and Compliments to Tackle Online Abuse ...
|
|
|
|
BASE
|
|
Show details
|
|
2 |
ViTA: Visual-Linguistic Translation by Aligning Object Tags ...
|
|
|
|
Abstract:
Multimodal Machine Translation (MMT) enriches the source text with visual information for translation. It has gained popularity in recent years, and several pipelines have been proposed in the same direction. Yet, the task lacks quality datasets to illustrate the contribution of visual modality in the translation systems. In this paper, we propose our system under the team name Volta for the Multimodal Translation Task of WAT 2021 from English to Hindi. We also participate in the textual-only subtask of the same language pair for which we use mBART, a pretrained multilingual sequence-to-sequence model. For multimodal translation, we propose to enhance the textual input by bringing the visual information to a textual domain by extracting object tags from the image. We also explore the robustness of our system by systematically degrading the source text. Finally, we achieve a BLEU score of 44.6 and 51.6 on the test set and challenge set of the multimodal task. ... : 7 pages, accepted at WAT-2021 co-located with ACL-IJCNLP 2021 ...
|
|
Keyword:
Computation and Language cs.CL; Computer Vision and Pattern Recognition cs.CV; FOS Computer and information sciences
|
|
URL: https://arxiv.org/abs/2106.00250 https://dx.doi.org/10.48550/arxiv.2106.00250
|
|
BASE
|
|
Hide details
|
|
3 |
HASOCOne@FIRE-HASOC2020: Using BERT and Multilingual BERT models for Hate Speech Detection ...
|
|
|
|
BASE
|
|
Show details
|
|
4 |
Multilingual Pre-Trained Transformers and Convolutional NN Classification Models for Technical Domain Identification ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
gundapusunil at SemEval-2020 Task 9: Syntactic Semantic LSTM Architecture for SENTIment Analysis of Code-MIXed Data ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
A SentiWordNet Strategy for Curriculum Learning in Sentiment Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
Word Level Language Identification in English Telugu Code Mixed Data ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
A Sentiwordnet Strategy for Curriculum Learning in Sentiment Analysis
|
|
|
|
In: Natural Language Processing and Information Systems (2020)
|
|
BASE
|
|
Show details
|
|
10 |
Conversational implicatures in English dialogue: Annotated dataset ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
BCSAT : A Benchmark Corpus for Sentiment Analysis in Telugu Using Word-level Annotations ...
|
|
|
|
BASE
|
|
Show details
|
|
12 |
Automatic Target Recovery for Hindi-English Code Mixed Puns ...
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Towards Automation of Sense-type Identification of Verbs in OntoSenseNet(Telugu) ...
|
|
|
|
BASE
|
|
Show details
|
|
14 |
Towards Enhancing Lexical Resource and Using Sense-annotations of OntoSenseNet for Sentiment Analysis ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Context and Humor: Understanding Amul advertisements of India ...
|
|
|
|
BASE
|
|
Show details
|
|
|
|