Related papers: A Data Bootstrapping Recipe for Low Resource Multi…
Transformers are the most eminent architectures used for a vast range of Natural Language Processing tasks. These models are pre-trained over a large text corpus and are meant to serve state-of-the-art results over tasks like text…
Sentiment analysis is the most basic NLP task to determine the polarity of text data. There has been a significant amount of work in the area of multilingual text as well. Still hate and offensive speech detection faces a challenge due to…
Document-level Relation Extraction (DocRE), which aims to extract relations from a long context, is a critical challenge in achieving fine-grained structural comprehension and generating interpretable document representations. Inspired by…
Cross-lingual document classification aims at training a document classifier on resources in one language and transferring it to a different language without any additional resources. Several approaches have been proposed in the literature…
Pre-trained multilingual language models have become an important building block in multilingual natural language processing. In the present paper, we investigate a range of such models to find out how well they transfer discourse-level…
This paper addresses the challenge of integrating low-resource languages into multilingual automatic speech recognition (ASR) systems. We introduce a novel application of weighted cross-entropy, typically used for unbalanced datasets, to…
Transliteration is very common on social media, but transliterated text is not adequately handled by modern neural models for various NLP tasks. In this work, we combine data augmentation approaches with a Teacher-Student training scheme to…
Transliteration is a task in the domain of NLP where the output word is a similar-sounding word written using the letters of any foreign language. Today this system has been developed for several language pairs that involve English as…
Information extraction is an important task in NLP, enabling the automatic extraction of data for relational database filling. Historically, research and data was produced for English text, followed in subsequent years by datasets in…
We propose a new formulation for multilingual entity linking, where language-specific mentions resolve to a language-agnostic Knowledge Base. We train a dual encoder in this new setting, building on prior work with improved feature…
Since their inception, embeddings have become a primary ingredient in many flavours of Natural Language Processing (NLP) tasks supplanting earlier types of representation. Even though multilingual embeddings have been used for the…
This paper describes our submission to the constrained track of WMT21 shared news translation task. We focus on the three relatively low resource language pairs Bengali to and from Hindi, English to and from Hausa, and Xhosa to and from…
The advent of neural-networks in NLP brought with it substantial improvements in supervised relation extraction. However, obtaining a sufficient quantity of training data remains a key challenge. In this work we propose a process for…
Video retrieval using natural language queries requires learning semantically meaningful joint embeddings between the text and the audio-visual input. Often, such joint embeddings are learnt using pairwise (or triplet) contrastive loss…
Prompting pre-trained language models has achieved impressive performance on various NLP tasks, especially in low data regimes. Despite the success of prompting in monolingual settings, applying prompt-based methods in multilingual…
Although the Indonesian language is spoken by almost 200 million people and the 10th most spoken language in the world, it is under-represented in NLP research. Previous work on Indonesian has been hampered by a lack of annotated datasets,…
We propose an efficient modeling framework for cross-lingual named entity recognition in semi-structured text data. Our approach relies on both knowledge distillation and consistency training. The modeling framework leverages knowledge from…
Plagiarism involves using another person's work or concepts without proper attribution, presenting them as original creations. With the growing amount of data communicated in regional languages such as Marathi -- one of India's regional…
Speech Relation Extraction (SpeechRE) aims to extract relation triplets directly from speech. However, existing benchmark datasets rely heavily on synthetic data, lacking sufficient quantity and diversity of real human speech. Moreover,…
Enterprise relation extraction aims to detect pairs of enterprise entities and identify the business relations between them from unstructured or semi-structured text data, and it is crucial for several real-world applications such as risk…