Related papers: Cross-lingual Dataless Classification for Language…
Large Language Model (LLM) pre-training exhausts an ever growing compute budget, yet recent research has demonstrated that careful document selection enables comparable model quality with only a fraction of the FLOPs. Inspired by efforts…
Web-scale visual entity recognition, the task of associating images with their corresponding entities within vast knowledge bases like Wikipedia, presents significant challenges due to the lack of clean, large-scale training data. In this…
Publication databases rely on accurate metadata extraction from diverse web sources, yet variations in web layouts and data formats present challenges for metadata providers. This paper introduces CRAWLDoc, a new method for contextual…
Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the…
Cross-lingual Text Classification (CLC) consists of automatically classifying, according to a common set C of classes, documents each written in one of a set of languages L, and doing so more accurately than when naively classifying each…
Large Language Models (LLMs) have significantly impacted many facets of natural language processing and information retrieval. Unlike previous encoder-based approaches, the enlarged context window of these generative models allows for…
In this paper we present a novel method for retrieving information in languages other than that of the query. We use this technique in combination with existing traditional Cross Language Information Retrieval (CLIR) techniques to improve…
Wikipedia's perceived high quality and broad language coverage have established it as a fundamental resource in NLP. However, in recent years, such assumptions of high quality have become the subject of scrutiny in low-resource and…
With over 60M articles, Wikipedia has become the largest platform for open and freely accessible knowledge. While it has more than 15B monthly visits, its content is believed to be inaccessible to many readers due to the lack of readability…
Many applications require categorization of text documents using predefined categories. The main approach to performing text categorization is learning from labeled examples. For many tasks, it may be difficult to find examples in one…
We present Wikipedia-based Polyglot Dirichlet Allocation (WikiPDA), a crosslingual topic model that learns to represent Wikipedia articles written in any language as distributions over a common set of language-independent topics. It…
This paper explores the system of categories that is used to classify articles in Wikipedia. It is compared to collaborative tagging systems like del.icio.us and to hierarchical classification like the Dewey Decimal Classification (DDC).…
The scarcity of labeled training data often prohibits the internationalization of NLP models to multiple languages. Recent developments in cross-lingual understanding (XLU) has made progress in this area, trying to bridge the language…
Much of human knowledge sits in large databases of unstructured text. Leveraging this knowledge requires algorithms that extract and record metadata on unstructured text documents. Assigning topics to documents will enable intelligent…
We propose KDSL, a new word sense disambiguation (WSD) framework that utilizes knowledge to automatically generate sense-labeled data for supervised learning. First, from WordNet, we automatically construct a semantic knowledge base called…
Classifying scanned documents is a challenging problem that involves image, layout, and text analysis for document understanding. Nevertheless, for certain benchmark datasets, notably RVL-CDIP, the state of the art is closing in to…
Large Language Models (LLMs) are capable of successfully performing many language processing tasks zero-shot (without training data). If zero-shot LLMs can also reliably classify and explain social phenomena like persuasiveness and…
Multilingual large language models (LLMs) often demonstrate a performance gap between English and non-English languages, particularly in low-resource settings. Aligning these models to low-resource languages is essential yet challenging due…
Pretrained Language Models (PLMs) learn rich cross-lingual knowledge and can be finetuned to perform well on diverse tasks such as translation and multilingual word sense disambiguation (WSD). However, they often struggle at disambiguating…
Emerging digital technologies are exacerbating the existing divide in Open Access Data (OAD) between high-and low-resource languages, excluding many communities from participating in the global digital transformation. In this PhD proposal,…