Related papers: Hierarchical Meta-Embeddings for Code-Switching Na…

Knowledge bases such as Wikidata amass vast amounts of named entity information, such as multilingual labels, which can be extremely useful for various multilingual and cross-lingual applications. However, such labels are not guaranteed to…

State of the art Named Entity Recognition (NER) models have achieved an impressive ability to extract common phrases from text that belong to labels such as location, organization, time, and person. However, typical NER systems that rely on…

This paper proposes a structure-aware decoding method based on large language models to address the difficulty of traditional approaches in maintaining both semantic integrity and structural consistency in nested and overlapping entity…

Entity linking -- the task of identifying references in free text to relevant knowledge base representations -- often focuses on single languages. We consider multilingual entity linking, where a single model is trained to link references…

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…

Human languages differ widely in their forms, each having distinct sounds, scripts, and syntax. Yet, they can all convey similar meaning. Do different languages converge on a shared neural substrate for conceptual meaning? We used language…

Code-mixing is increasingly prevalent in interactions between humans and large language models, yet existing work often reduces it to a translation or convertibility problem, making it difficult to assess whether a model's switching…

Contextual embeddings represent a new generation of semantic representations learned from Neural Language Modelling (NLM) that addresses the issue of meaning conflation hampering traditional word embeddings. In this work, we show that…

Social media messages' brevity and unconventional spelling pose a challenge to language identification. We introduce a hierarchical model that learns character and contextualized word-level representations for language identification. Our…

Most state-of-the-art models in natural language processing (NLP) are neural models built on top of large, pre-trained, contextual language models that generate representations of words in context and are fine-tuned for the task at hand.…

Contextual embeddings, such as ELMo and BERT, move beyond global word representations like Word2Vec and achieve ground-breaking performance on a wide range of natural language processing tasks. Contextual embeddings assign each word a…

We propose a novel model architecture and training algorithm to learn bilingual sentence embeddings from a combination of parallel and monolingual data. Our method connects autoencoding and neural machine translation to force the source and…

Very low-resource languages, having only a few million tokens worth of data, are not well-supported by multilingual NLP approaches due to poor quality cross-lingual word representations. Recent work showed that good cross-lingual…

There has been significant interest recently in learning multilingual word embeddings -- in which semantically similar words across languages have similar embeddings. State-of-the-art approaches have relied on expensive labeled data, which…

We computed both Word and Sub-word Embeddings using FastText. For Sub-word embeddings we selected Byte Pair Encoding (BPE) algorithm to represent the sub-words. We evaluated the Biomedical Word Embeddings obtaining better results than…

Due to the inherent difficulty in modeling phonetic similarities across different languages, code-switching speech recognition presents a formidable challenge. This study proposes a Collaborative-MoE, a Mixture of Experts (MoE) model that…

Word embedding, a high-dimensional (HD) numerical representation of words generated by machine learning models, has been used for different natural language processing tasks, e.g., translation between two languages. Recently, there has been…

Code-switching (CS) is common in daily conversations where more than one language is used within a sentence. The difficulties of CS speech recognition lie in alternating languages and the lack of transcribed data. Therefore, this paper uses…

Handwritten word retrieval is vital for digital archives but remains challenging due to large handwriting variability and cross-lingual semantic gaps. While large vision-language models offer potential solutions, their prohibitive…

Most state of the art approaches for Named Entity Recognition rely on hand crafted features and annotated corpora. Recently Neural network based models have been proposed which do not require handcrafted features but still require annotated…