Related papers: Assessing Wikipedia-Based Cross-Language Retrieval…

Multilingual Large Language Models (LLMs) struggle with cross-lingual tasks due to data imbalances between high-resource and low-resource languages, as well as monolingual bias in pre-training. Existing methods, such as bilingual…

Latent Dirichlet Allocation (LDA) is a prominent generative probabilistic model used for uncovering abstract topics within document collections. In this paper, we explore the effectiveness of augmenting topic models with Large Language…

One of the first steps in many text-based social science studies is to retrieve documents that are relevant for the analysis from large corpora of otherwise irrelevant documents. The conventional approach in social science to address this…

Pretrained multilingual language models (LMs) can be successfully transformed into multilingual sentence encoders (SEs; e.g., LaBSE, xMPNet) via additional fine-tuning or model distillation with parallel data. However, it remains unclear…

A recent research line has obtained strong results on bilingual lexicon induction by aligning independently trained word embeddings in two languages and using the resulting cross-lingual embeddings to induce word translation pairs through…

Traditional information retrieval systems rely on keywords to index documents and queries. In such systems, documents are retrieved based on the number of shared keywords with the query. This lexical-focused retrieval leads to inaccurate…

Words have been represented in a high-dimensional vector space that encodes their semantic similarities, enabling downstream applications such as retrieving synonyms, antonyms, and relevant contexts. However, despite recent advances in…

The classical, vector space model for text retrieval is shown to give better results (up to 29% better in our experiments) if WordNet synsets are chosen as the indexing space, instead of word forms. This result is obtained for a manually…

Crosslingual word embeddings represent lexical items from different languages in the same vector space, enabling transfer of NLP tools. However, previous attempts had expensive resource requirements, difficulty incorporating monolingual…

Text retrieval is a long-standing research topic on information seeking, where a system is required to return relevant information resources to user's queries in natural language. From classic retrieval methods to learning-based ranking…

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…

Recent advances in AI have catalyzed the adoption of intelligent educational tools, yet many semantic retrieval systems remain ill-suited to the unique linguistic and structural characteristics of academic content. This study presents two…

Dense vector representations for textual data are crucial in modern NLP. Word embeddings and sentence embeddings estimated from raw texts are key in achieving state-of-the-art results in various tasks requiring semantic understanding.…

English-centric large language models (LLMs) often show strong multilingual capabilities. However, their multilingual performance remains unclear and is under-evaluated for many other languages. Most benchmarks for multilinguality focus on…

Neural approaches to learning term embeddings have led to improved computation of similarity and ranking in information retrieval (IR). So far neural representation learning has not been extended to meta-textual information that is readily…

We explore ways of incorporating bilingual dictionaries to enable semi-supervised neural machine translation. Conventional back-translation methods have shown success in leveraging target side monolingual data. However, since the quality of…

In this paper we present a model for unsupervised topic discovery in texts corpora. The proposed model uses documents, words, and topics lookup table embedding as neural network model parameters to build probabilities of words given topics,…

Pre-trained language models (PLMs) have proven to be effective for document re-ranking task. However, they lack the ability to fully interpret the semantics of biomedical and health-care queries and often rely on simplistic patterns for…

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…

Multilingual pretraining typically lacks explicit alignment signals, leading to suboptimal cross-lingual alignment in the representation space. In this work, we show that training standard pretrained models for cross-lingual alignment with…