Related papers: Unsupervised Bilingual Lexicon Induction for Low R…
Entity Linking is one of the essential tasks of information extraction and natural language understanding. Entity linking mainly consists of two tasks: recognition and disambiguation of named entities. Most studies address these two tasks…
Word embedding is a key component in many downstream applications in processing natural languages. Existing approaches often assume the existence of a large collection of text for learning effective word embedding. However, such a corpus…
Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However,…
Multilingual Large Language Models (LLMs) have shown remarkable performance across various languages; however, they often include significantly less data for low-resource languages such as Urdu compared to high-resource languages like…
Sign Language (SL) enables two-way communication for the deaf and hard-of-hearing community, yet many sign languages remain under-resourced in the AI space. Sign Language Instruction Generation (SLIG) produces step-by-step textual…
Transformer-based models achieve impressive performance on numerous Natural Language Inference (NLI) benchmarks when trained on respective training datasets. However, in certain cases, training samples may not be available or collecting…
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…
Bengali is an underrepresented language in NLP research. However, it remains a challenge due to its unique linguistic structure and computational constraints. In this work, we systematically investigate the challenges that hinder Bengali…
Unsupervised neural machine translation (UNMT) is beneficial especially for low resource languages such as those from the Dravidian family. However, UNMT systems tend to fail in realistic scenarios involving actual low resource languages.…
Dense retrieval methods have demonstrated promising performance in multilingual information retrieval, where queries and documents can be in different languages. However, dense retrievers typically require a substantial amount of paired…
This paper describes DBPal, a new system to translate natural language utterances into SQL statements using a neural machine translation model. While other recent approaches use neural machine translation to implement a Natural Language…
Large Language Models (LLMs) perform well on unseen tasks in English, but their abilities in non English languages are less explored due to limited benchmarks and training data. To bridge this gap, we introduce the Indic QA Benchmark, a…
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…
Despite advancements in English-dominant generative large language models, further development is needed for low-resource languages to enhance global accessibility. The primary methods for representing these languages are monolingual and…
Large language models (LLMs) can generate fluent natural language texts when given relevant documents as background context. This ability has attracted considerable interest in developing industry applications of LLMs. However, LLMs are…
Natural Language Inference (NLI) models are known to learn from biases and artefacts within their training data, impacting how well they generalise to other unseen datasets. Existing de-biasing approaches focus on preventing the models from…
Contrastive vision-language models like CLIP have shown great progress in transfer learning. In the inference stage, the proper text description, also known as prompt, needs to be carefully designed to correctly classify the given images.…
Unsupervised Bilingual Dictionary Induction methods based on the initialization and the self-learning have achieved great success in similar language pairs, e.g., English-Spanish. But they still fail and have an accuracy of 0% in many…
We evaluate cognitive impairment (CI) classification from transcripts of speech in English, Slovene, and Korean. We compare zero-shot large language models (LLMs) used as direct classifiers under three input settings -- transcript-only,…
Language Identification in textual documents is the process of automatically detecting the language contained in a document based on its content. The present Language Identification techniques presume that a document contains text in one of…