Papers by Fausto Giunchiglia
Toward Robust In-Context Learning: Leveraging Out-of-distribution Proxies for Target Inaccessible Demonstration Retrieval (2026.acl-long)
Copied to clipboard
| Challenge: | Large language models (LLMs) perform well on Out-of-Distribution tasks, but performance degrades as distribution shift becomes more severe. |
| Approach: | They propose a demonstration search framework that incorporates an OOD proxy to approximate the inaccessible target domain and guide the retrieval process. |
| Outcome: | The proposed framework enhances robustness in out-of-distribution tasks by incorporating an OOD proxy to approximate the inaccessible target domain and guide the retrieval process. |
Deep Attention Diffusion Graph Neural Networks for Text Classification (2021.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods for text classification based on graph neural networks (GNNs) consider only one-hop neighborhoods and low-frequency information within texts, which suffer from over-smoothing issues if many graph layers are stacked. |
| Approach: | They propose a deep attention diffusion Graph Neural Network model to learn text representations by bridging the chasm of interaction difficulties between a word and its distant neighbors. |
| Outcome: | The proposed model outperforms existing methods on standard benchmark datasets on a set of textual features. |
Language Diversity: Visible to Humans, Exploitable by Machines (2022.acl-demo)
Copied to clipboard
Gábor Bella, Erdenebileg Byambadorj, Yamini Chandrashekar, Khuyagbaatar Batsuren, Danish Cheema, Fausto Giunchiglia
| Challenge: | Universal Knowledge Core (UKC) is a large multilingual lexical database with a focus on language diversity and covering over two thousand languages. |
| Approach: | Universal Knowledge Core is a large multilingual lexical database with a focus on language diversity and covering over two thousand languages. |
| Outcome: | the database lets users explore millions of individual words and their meanings, but also phenomena of cross-lingual convergence and divergence, such as shared interlingual meanings and lexicon similarities. |
Ancient Chinese Glyph Identification Powered by Radical Semantics (2024.findings-acl)
Copied to clipboard
| Challenge: | Currently, about half of ancient Chinese glyphs have not been deciphered yet. |
| Approach: | They propose to use a Chinese glyph knowledge graph to infer the Chinese character label for the unknown ancient Chinese . they propose to combine the visual, textual, and the graph data to create a multimodal Chinese morph identification framework. |
| Outcome: | The proposed method can identify ancient Chinese characters from 1300 BC to 200 BC based on image and radical semantics on a 1000-year-old Chinese glyph dataset. |
Using Linguistic Typology to Enrich Multilingual Lexicons: the Case of Lexical Gaps in Kinship (2022.lrec-1)
Copied to clipboard
Temuulen Khishigsuren, Gábor Bella, Khuyagbaatar Batsuren, Abed Alhakim Freihat, Nandu Chandran Nair, Amarsanaa Ganbold, Hadi Khalilia, Yamini Chandrashekar, Fausto Giunchiglia
| Challenge: | a method to enrich lexical resources with content relating to linguistic diversity is proposed . Typology-based approaches are being used to improve cross-lingual NLP tasks . |
| Approach: | They propose a method to enrich lexical resources with content relating to linguistic diversity based on lexica. |
| Outcome: | The proposed method can be used to improve cross-lingual NLP tasks by removing the need for parallel textual corpora or cross-linguistic transfer from high-to-low-resourced languages. |
From Fake to Real: Mitigating Out-of-Distribution Bias in In-Context Learning via Feedback Supervision from Large Language Models (2026.findings-acl)
Copied to clipboard
| Challenge: | In-Context Learning (ICL) is one of the most common methods for complex Natural Language Understanding tasks. |
| Approach: | They propose a method that uses model confidence and perturbation perplexity to enhance the quality of pseudo-labels. |
| Outcome: | The proposed method reduces OOD biases by avoiding direct use of source data. |
A Simple Contrastive Learning Framework for Interactive Argument Pair Identification via Argument-Context Extraction (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on argument mining uses context-based methods to identify whether two arguments are interactively related. |
| Approach: | They propose a contrastive learning framework to extract valuable information from the context. |
| Outcome: | The proposed framework achieves state-of-the-art performance on the benchmark dataset and visually displays more compact representations. |
ZiNet: Linking Chinese Characters Spanning Three Thousand Years (2022.findings-acl)
Copied to clipboard
| Challenge: | tens of thousands of ancient characters must be deciphered by experts to interpret unearthed documents. |
| Approach: | They propose a diachronic Chinese knowledge base to help researchers discover glyph similar characters by measuring glyph similarities between ancient Chinese characters. |
| Outcome: | The proposed method shows strong correlations between the scores obtained from the method and from human experts. |
Exploring the Language of Data (2020.coling-main)
Copied to clipboard
| Challenge: | Structured data, such as database tables or XML trees, often contain short natural language labels that describe the data structure itself or provide content (attribute values). Conventional NLP tools, such supervised sequence labellers or embeddings trained on full sentences, do not perform well on structured data. |
| Approach: | They propose to design a type of abbreviated grammar that is called the Language of Data and to investigate the grammatical properties of such labels. |
| Outcome: | The proposed model outperforms models trained on standard text on tokenisation, part-of-speech tagging, and named entity recognition over real-world structured data. |
UniMorph 4.0: Universal Morphology (2022.lrec-1)
Copied to clipboard
Khuyagbaatar Batsuren, Omer Goldman, Salam Khalifa, Nizar Habash, Witold Kieraś, Gábor Bella, Brian Leonard, Garrett Nicolai, Kyle Gorman, Yustinus Ghanggo Ate, Maria Ryskina, Sabrina Mielke, Elena Budianskaya, Charbel El-Khaissi, Tiago Pimentel, Michael Gasser, William Abbott Lane, Mohit Raj, Matt Coler, Jaime Rafael Montoya Samame, Delio Siticonatzi Camaiteri, Esaú Zumaeta Rojas, Didier López Francis, Arturo Oncevay, Juan López Bautista, Gema Celeste Silva Villegas, Lucas Torroba Hennigen, Adam Ek, David Guriel, Peter Dirix, Jean-Philippe Bernardy, Andrey Scherbakov, Aziyana Bayyr-ool, Antonios Anastasopoulos, Roberto Zariquiey, Karina Sheifer, Sofya Ganieva, Hilaria Cruz, Ritván Karahóǧa, Stella Markantonatou, George Pavlidis, Matvey Plugaryov, Elena Klyachko, Ali Salehi, Candy Angulo, Jatayu Baxi, Andrew Krizhanovsky, Natalia Krizhanovskaya, Elizabeth Salesky, Clara Vania, Sardana Ivanova, Jennifer White, Rowan Hall Maudslay, Josef Valvoda, Ran Zmigrod, Paula Czarnowska, Irene Nikkarinen, Aelita Salchak, Brijesh Bhatt, Christopher Straughn, Zoey Liu, Jonathan North Washington, Yuval Pinter, Duygu Ataman, Marcin Wolinski, Totok Suhardijanto, Anna Yablonskaya, Niklas Stoehr, Hossep Dolatian, Zahroh Nuriah, Shyam Ratan, Francis M. Tyers, Edoardo M. Ponti, Grant Aiton, Aryaman Arora, Richard J. Hatcher, Ritesh Kumar, Jeremiah Young, Daria Rodionova, Anastasia Yemelina, Taras Andrushko, Igor Marchenko, Polina Mashkovtseva, Alexandra Serova, Emily Prud’hommeaux, Maria Nepomniashchaya, Fausto Giunchiglia, Eleanor Chodroff, Mans Hulden, Miikka Silfverberg, Arya D. McCarthy, David Yarowsky, Ryan Cotterell, Reut Tsarfaty, Ekaterina Vylomova
| Challenge: | The Universal Morphology project provides broad-coverage instantiated morphological inflection tables for hundreds of diverse languages. |
| Approach: | They propose a language-independent feature schema for rich morphological annotation and a type-level resource of annotated data in diverse languages realizing that schema. |
| Outcome: | The proposed schema has added 66 new languages, including 24 endangered languages. |
A Major Wordnet for a Minority Language: Scottish Gaelic (2020.lrec-1)
Copied to clipboard
Gábor Bella, Fiona McNeill, Rody Gorman, Caoimhin O Donnaile, Kirsty MacDonald, Yamini Chandrashekar, Abed Alhakim Freihat, Fausto Giunchiglia
| Challenge: | a new wordnet resource is available for Scottish Gaelic, a minority language spoken by 60,000 speakers . weak online presence of minority languages is a problem due to lack of digital corpora, authors say . |
| Approach: | They propose a new wordnet resource for Scottish Gaelic, a Celtic minority language . the wordnet contains over 15 thousand word senses and is among the 30 largest in the world . authors hope to contribute to long-term preservation of Scottish Gaels as a living language - offline and on the Web . |
| Outcome: | The new wordnet is for Scottish Gaelic, a minority language spoken by 60,000 speakers . the wordnet contains over 15 thousand word senses and is among the 30 largest in the world . authors hope it will contribute to the long-term preservation of the language, both offline and on the Web . |
IndoUKC: A Concept-Centered Indian Multilingual Lexical Resource (2022.lrec-1)
Copied to clipboard
| Challenge: | a new multilingual lexical database for Indian languages is proposed . the database provides words and crosslingually mapped word meanings specific to Indian languages and cultures. |
| Approach: | They propose to create a multilingual lexical database for Indian languages called IndoUKC . the database is based on existing IndoWordNet resources and is available for browsing . |
| Outcome: | The proposed database is based on the existing IndoWordNet resource and is available for download through the LiveLanguage data catalogue. |
CogNet: A Large-Scale Cognate Database (P19-1)
Copied to clipboard
| Challenge: | Existing cognate databases have limited practical applications for research, despite their wide coverage and limited use in lexical tasks. |
| Approach: | They introduce a new large-scale lexical database that provides cognates across languages. |
| Outcome: | The proposed database contains 3.1 million cognate pairs across 338 languages and has an accuracy of 94%. |