7 papers
Lexical Redefinition Reveals Context-Sensitive Instruction Following
Roksana Goworek, Haim Dubossarsky
How do language models reconcile conflicting contextual evidence within a prompt? We study this question using lexical redefinition, where an explicit instruction specifies how a w…
Rethinking Metrics for Lexical Semantic Change Detection
Roksana Goworek, Haim Dubossarsky
Lexical semantic change detection (LSCD) increasingly relies on contextualised language model embeddings, yet most approaches still quantify change using a small set of semantic ch…
Generative Query Expansion with Multilingual LLMs for Cross-Lingual Information Retrieval
Olivia Macmillan-Scott, Roksana Goworek, Eda B. Özyiğit
Query expansion is the reformulation of a user query by adding semantically related information, and is an essential component of monolingual and cross-lingual information retrieva…
What Drives Cross-lingual Ranking? Retrieval Approaches with Multilingual Language Models
Roksana Goworek, Olivia Macmillan-Scott, Eda B. Özyiğit
Cross-lingual information retrieval (CLIR) enables access to multilingual knowledge but remains challenging due to disparities in resources, scripts, and weak cross-lingual semanti…
Bridging Language Gaps: Advances in Cross-Lingual Information Retrieval with Multilingual LLMs
Roksana Goworek, Olivia Macmillan-Scott, Eda B. Özyiğit
Cross-lingual information retrieval (CLIR) addresses the challenge of retrieving relevant documents written in languages different from that of the original query. Research in this…
Multilinguality Does not Make Sense: Investigating Factors Behind Zero-Shot Transfer in Sense-Aware Tasks
Roksana Goworek, Haim Dubossarsky
Cross-lingual transfer is central to modern NLP, enabling models to perform tasks in languages different from those they were trained on. A common assumption is that training on mo…
SenWiCh: Sense-Annotation of Low-Resource Languages for WiC using Hybrid Methods
Roksana Goworek, Harpal Karlcut, Muhammad Shezad +10
This paper addresses the critical need for high-quality evaluation datasets in low-resource languages to advance cross-lingual transfer. While cross-lingual transfer offers a key s…