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 for the Multimodal Translation Task of WAT 2021 from English to Hindi. We propose to use mBART, a pretrained multilingual sequence-to-sequence model, for the textual-only translations. Further, we bring the visual information to a textual domain by extracting object tags from the image and enhance the input for the multimodal task. 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 task.
Memes are one of the most popular types of content used to spread information online. They can influence a large number of people through rhetorical and psychological techniques. The task, Detection of Persuasion Techniques in Texts and Images, is to detect these persuasive techniques in memes. It consists of three subtasks: (A) Multi-label classification using textual content, (B) Multi-label classification and span identification using textual content, and (C) Multi-label classification using visual and textual content. In this paper, we propose a transfer learning approach to fine-tune BERT-based models in different modalities. We also explore the effectiveness of ensembles of models trained in different modalities. We achieve an F1-score of 57.0, 48.2, and 52.1 in the corresponding subtasks.
Social Media Platforms (SMPs) like Facebook, Twitter, Instagram etc. have large user base all around the world that generates huge amount of data every second. This includes a lot of posts by fake and spam users, typically used by many organisations around the globe to have competitive edge over others. In this work, we aim at detecting such user accounts in Twitter using a novel approach. We show how to distinguish between Genuine and Spam accounts in Twitter using a combination of Graph Representation Learning and Natural Language Processing techniques.
While Curriculum Learning (CL) has recently gained traction in Natural language Processing Tasks, it is still not adequately analyzed. Previous works only show their effectiveness but fail short to explain and interpret the internal workings fully. In this paper, we analyze curriculum learning in sentiment analysis along multiple axes. Some of these axes have been proposed by earlier works that need more in-depth study. Such analysis requires understanding where curriculum learning works and where it does not. Our axes of analysis include Task difficulty on CL, comparing CL pacing techniques, and qualitative analysis by visualizing the movement of attention scores in the model as curriculum phases progress. We find that curriculum learning works best for difficult tasks and may even lead to a decrement in performance for tasks with higher performance without curriculum learning. We see that One-Pass curriculum strategies suffer from catastrophic forgetting and attention movement visualization within curriculum pacing. This shows that curriculum learning breaks down the challenging main task into easier sub-tasks solved sequentially.
Well-defined jokes can be divided neatly into a setup and a punchline. While most works on humor today talk about a joke as a whole, the idea of generating punchlines to a setup has applications in conversational humor, where funny remarks usually occur with a non-funny context. Thus, this paper is based around two core concepts: Classification and the Generation of a punchline from a particular setup based on the Incongruity Theory. We first implement a feature-based machine learning model to classify humor. For humor generation, we use a neural model, and then merge the classical rule-based approaches with the neural approach to create a hybrid model. The idea behind being: combining insights gained from other tasks with the setup-punchline model and thus applying it to existing text generation approaches. We then use and compare our model with human written jokes with the help of human evaluators in a double-blind study.
This paper aims to describe the approach we used to detect hope speech in the HopeEDI dataset. We experimented with two approaches. In the first approach, we used contextual embeddings to train classifiers using logistic regression, random forest, SVM, and LSTM based models.The second approach involved using a majority voting ensemble of 11 models which were obtained by fine-tuning pre-trained transformer models (BERT, ALBERT, RoBERTa, IndicBERT) after adding an output layer. We found that the second approach was superior for English, Tamil and Malayalam. Our solution got a weighted F1 score of 0.93, 0.75 and 0.49 for English,Malayalam and Tamil respectively. Our solution ranked first in English, eighth in Malayalam and eleventh in Tamil.
With the instantaneous growth of text information, retrieving domain-oriented information from the text data has a broad range of applications in Information Retrieval and Natural language Processing. Thematic keywords give a compressed representation of the text. Usually, Domain Identification plays a significant role in Machine Translation, Text Summarization, Question Answering, Information Extraction, and Sentiment Analysis. In this paper, we proposed the Multichannel LSTM-CNN methodology for Technical Domain Identification for Telugu. This architecture was used and evaluated in the context of the ICON shared task TechDOfication 2020 (task h), and our system got 69.9% of the F1 score on the test dataset and 90.01% on the validation set.
Terminology extraction, also known as term extraction, is a subtask of information extraction. The goal of terminology extraction is to extract relevant words or phrases from a given corpus automatically. This paper focuses on the unsupervised automated domain term extraction method that considers chunking, preprocessing, and ranking domain-specific terms using relevance and cohesion functions for ICON 2020 shared task 2: TermTraction.