Class Notes
Sofia University "St. Kliment Ohridski" Faculty of Mathematics and Informatics

Information Retrieval

course @ Sofia University

Lab notes by Elitsa Yotkova

Labs

TopicDescriptionNotesQuizSlides
00Introduction Team, course content, SemEval-2027, top AI conferences Learn → Coming soon Coming soon
01Inverted Index and Boolean Queries Postings lists, Boolean and phrase queries Learn → Quiz → Present →
02Text Preprocessing Tokenization, normalization, stemming, lemmatization Learn → Coming soon Present →
03Tolerant Retrieval and Spelling Correction Wild-cards, edit distance, spelling correction Learn → Coming soon Coming soon
04Ranked Retrieval: TF-IDF and BM25 TF-IDF, cosine similarity, BM25 Learn → Coming soon Coming soon
05Evaluating IR Systems Precision, recall, MRR, MAP, nDCG Learn → Coming soon Coming soon
06Web Crawling and PageRank Crawlers, robots.txt, PageRank Learn → Coming soon Coming soon
07Query Expansion and Language Models Rocchio, pseudo-relevance feedback, query likelihood Learn → Coming soon Coming soon
08Neural Text Representations Tokens and embeddings, self-attention, Transformers Learn → Coming soon Coming soon
09Sentence Embeddings and Semantic Search Encoders, pooling, semantic search, bi-encoders Learn → Coming soon Coming soon
10Dense Retrieval and Vector Databases Bi-encoders, ANN search (IVF, HNSW), FAISS Learn → Coming soon Coming soon
11Hybrid Retrieval and Reranking Rank fusion (RRF), cross-encoder reranking Learn → Coming soon Coming soon
12Retrieval-Augmented Generation Chunking, grounded prompts, citations Learn → Coming soon Coming soon
13Evaluating RAG Systems Evidence recall, faithfulness, LLM judges Learn → Coming soon Coming soon

Recommended projects: take part in SemEval-2027

SemEval is the yearly international workshop on semantic evaluation: organisers publish a task with data and a metric, teams build systems, and all systems are scored on the same hidden test set.

The 11 tasks

1RETECO: Reasoning-Oriented Retrievalclosest to this course 2Directional-Consistent Fine-Grained NLI (DiCo-NLI) 3Semantic Change Across Multiple Time Periods 4Par-PARSEME: Paraphrasing of Idioms 5ComPartMENT: Compound and Particle Verb Compositionality 6Culturally Grounded Spoken and Visual Question Answering 7CLaS: Cross-Lingual Alignment and Steering of LLMs 8StereoQueerEval: Stereotypes and Hate Speech towards LGBTQIA+ 9Analysis of Multimodal Framing in the Newsorganised by us 10AgentRisk: Risk in Agentic Multi-Turn Interactions 11VAKRA-Advanced: Multi-Hop Multi-Source Tool Calling

Task 9: Analysis of Multimodal Framing in the News

We are among the organisers of Task 9: Dr. Dimitar Dimitrov, Elitsa Yotkova and Prof. Ivan Koychev, together with Giovanni Da San Martino, Preslav Nakov, Jakub Piskorski and colleagues from Padova, MBZUAI, Helsinki, Porto, Beira Interior and ETH Zurich. It builds on the SemEval-2023 task on persuasion techniques, framing and news genre.

Framing is choosing which aspects of an issue to make salient, so that a reader takes away a particular meaning. Images can reinforce, complement or contradict the framing of the text.

Task 9 page → All SemEval-2027 tasks →

Led by

Labs · Teaching Assistant · Author of these notes

Elitsa Yotkova

Master's student in Information Retrieval and Knowledge Discovery @ Sofia University, ex-Google, Uber

Website GitHub Google Scholar LinkedIn

Previously at

Labs · Teaching Assistant

Dr. Dimitar Dimitrov

Sofia University "St. Kliment Ohridski", Faculty of Mathematics and Informatics

Google Scholar

Lectures

Prof. Ivan Koychev

Sofia University "St. Kliment Ohridski", Faculty of Mathematics and Informatics

Google Scholar