Related papers: Which Are the Low-Resource Languages of the Semant…
The rise of generative chat-based Large Language Models (LLMs) over the past two years has spurred a race to develop systems that promise near-human conversational and reasoning experiences. However, recent studies indicate that the…
It is a well-known fact that current AI-based language technology -- language models, machine translation systems, multilingual dictionaries and corpora -- focuses on the world's 2-3% most widely spoken languages. Recent research efforts…
This paper examines approaches to generate lexical resources for endangered languages. Our algorithms construct bilingual dictionaries and multilingual thesauruses using public Wordnets and a machine translator (MT). Since our work relies…
Probing techniques for large language models (LLMs) have primarily focused on English, overlooking the vast majority of the world's languages. In this paper, we extend these probing methods to a multilingual context, investigating the…
Large language models (LLMs) demonstrate unprecedented capabilities and define the state of the art for almost all natural language processing (NLP) tasks and also for essentially all Language Technology (LT) applications. LLMs can only be…
Low-resource languages serve as invaluable repositories of human history, embodying cultural evolution and intellectual diversity. Despite their significance, these languages face critical challenges, including data scarcity and…
This tutorial (https://tum-nlp.github.io/low-resource-tutorial) is designed for NLP practitioners, researchers, and developers working with multilingual and low-resource languages who seek to create more equitable and socially impactful…
Since the Simple Knowledge Organization System (SKOS) specification and its SKOS eXtension for Labels (SKOS-XL) became formal W3C recommendations in 2009 a significant number of conventional knowledge organization systems (KOS) (including…
The ability to have the same experience for different user groups (i.e., accessibility) is one of the most important characteristics of Web-based systems. The same is true for Knowledge Graph Question Answering (KGQA) systems that provide…
Recent studies show that large language models (LLMs) are powerful tools for working with natural language, bringing advances in many areas of computational linguistics. However, these models face challenges when applied to low-resource…
In low-resource multilingual speech-to-text translation, uniform architectural sharing across languages frequently introduces representation conflicts that impede convergence. This work proposes a principled methodology to automatically…
We introduce DsDs: a cross-lingual neural part-of-speech tagger that learns from disparate sources of distant supervision, and realistically scales to hundreds of low-resource languages. The model exploits annotation projection, instance…
Most Knowledge Graphs (KGs) contain textual descriptions of entities in various natural languages. These descriptions of entities provide valuable information that may not be explicitly represented in the structured part of the KG. Based on…
Several recent papers have published good solutions for language identification (LID) for about 300 high-resource and medium-resource languages. However, there is no LID available that (i) covers a wide range of low-resource languages, (ii)…
Sustainable Development Goals (SDGs) bring together the diverse development community and provide a clear set of development targets for 2030. Given a large number of actors and initiatives related to these goals, there is a need to have a…
Meta-learning has achieved great success in leveraging the historical learned knowledge to facilitate the learning process of the new task. However, merely learning the knowledge from the historical tasks, adopted by current meta-learning…
Neural machine translation has become the state-of-the-art for language pairs with large parallel corpora. However, the quality of machine translation for low-resource languages leaves much to be desired. There are several approaches to…
Parsers are available for only a handful of the world's languages, since they require lots of training data. How far can we get with just a small amount of training data? We systematically compare a set of simple strategies for improving…
Hierarchical attention networks have recently achieved remarkable performance for document classification in a given language. However, when multilingual document collections are considered, training such models separately for each language…
Relation Extraction (RE) serves as a crucial technology for transforming unstructured text into structured information, especially within the framework of Knowledge Graph development. Its importance is emphasized by its essential role in…