Marco Baroni

Prediction Hubs are Context-Informed Frequent Tokens in LLMs ACL 2025 Emergence of a High-Dimensional Abstraction Phase in Language Transformers ICLR 2025 Not a nuisance but a useful heuristic: Outlier dimensions favor frequent tokens in language models EMNLP 2025 Evil twins are not that evil: Qualitative insights into machine-generated prompts EMNLP 2025 MemoryPrompt: A Light Wrapper to Improve Context Tracking in Pre-trained Language Models COLING 2024 Bridging Information-Theoretic and Geometric Compression in Language Models EMNLP 2023 Can discrete information extraction prompts generalize across language models? ICLR 2023 Cross-Domain Image Captioning With Discriminative Finetuning CVPR 2023 Unnatural language processing: How do language models handle machine-generated prompts? EMNLP 2023 Emergent Language-Based Coordination In Deep Multi-Agent Systems EMNLP 2022 Communication breakdown: On the low mutual intelligibility between human and neural captioning EMNLP 2022 Controlled tasks for model analysis: Retrieving discrete information from sequences EMNLP 2021 A Benchmark for Systematic Generalization in Grounded Language Understanding NIPS 2020 Emergent Language Generalization and Acquisition Speed are not tied to Compositionality EMNLP 2020 Permutation Equivariant Models for Compositional Generalization in Language ICLR 2020 Compositionality and Generalization In Emergent Languages ACL 2020 Entropy Minimization In Emergent Languages ICML 2020 The emergence of number and syntax units in LSTM language models NAACL 2019 EGG: a toolkit for research on Emergence of lanGuage in Games IJCNLP 2019 Miss Tools and Mr Fruit: Emergent Communication in Agents Learning about Object Affordances ACL 2019 CNNs found to jump around more skillfully than RNNs: Compositional Generalization in Seq2seq Convolutional Networks ACL 2019 On the Distribution of Deep Clausal Embeddings: A Large Cross-linguistic Study ACL 2019 Anti-efficient encoding in emergent communication NIPS 2019 Word-order Biases in Deep-agent Emergent Communication ACL 2019 EGG: a toolkit for research on Emergence of lanGuage in Games EMNLP 2019 Rearranging the Familiar: Testing Compositional Generalization in Recurrent Networks EMNLP 2018 Jump to better conclusions: SCAN both left and right EMNLP 2018 How agents see things: On visual representations in an emergent language game EMNLP 2018 Generalization without Systematicity: On the Compositional Skills of Sequence-to-Sequence Recurrent Networks ICML 2018 Colorless Green Recurrent Networks Dream Hierarchically NAACL 2018 What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties ACL 2018 High-risk learning: acquiring new word vectors from tiny data EMNLP 2017 The red one!: On learning to refer to things based on discriminative properties ACL 2016 The LAMBADA dataset: Word prediction requiring a broad discourse context ACL 2016 Multimodal Semantic Learning from Child-Directed Input NAACL 2016 Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model IJCNLP 2015 Hubness and Pollution: Delving into Cross-Space Mapping for Zero-Shot Learning ACL 2015 Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model ACL 2015 A Multitask Objective to Inject Lexical Contrast into Distributional Semantics ACL 2015 Distributional vectors encode referential attributes EMNLP 2015 Hubness and Pollution: Delving into Cross-Space Mapping for Zero-Shot Learning IJCNLP 2015 A Multitask Objective to Inject Lexical Contrast into Distributional Semantics IJCNLP 2015 Combining Language and Vision with a Multimodal Skip-gram Model NAACL 2015 So similar and yet incompatible: Toward the automated identification of semantically compatible words NAACL 2015 SemEval-2014 Task 1: Evaluation of Compositional Distributional Semantic Models on Full Sentences through Semantic Relatedness and Textual Entailment SEMEVAL 2014 Improving the Lexical Function Composition Model with Pathwise Optimized Elastic-Net Regression EACL 2014 Is this a wampimuk? Cross-modal mapping between distributional semantics and the visual world ACL 2014 How to make words with vectors: Phrase generation in distributional semantics ACL 2014 Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors ACL 2014 A practical and linguistically-motivated approach to compositional distributional semantics ACL 2014 Of Words, Eyes and Brains: Correlating Image-Based Distributional Semantic Models with Neural Representations of Concepts EMNLP 2013 Fish Transporters and Miracle Homes: How Compositional Distributional Semantics can Help NP Parsing EMNLP 2013 DISSECT - DIStributional SEmantics Composition Toolkit ACL 2013 A relatedness benchmark to test the role of determiners in compositional distributional semantics ACL 2013 Compositional-ly Derived Representations of Morphologically Complex Words in Distributional Semantics ACL 2013 Visual Features for Linguists: Basic image analysis techniques for multimodally-curious NLPers ACL 2013 Studying the Recursive Behaviour of Adjectival Modification with Compositional Distributional Semantics EMNLP 2013 Distributional Semantics in Technicolor ACL 2012 Entailment above the word level in distributional semantics EACL 2012 Nouns are Vectors, Adjectives are Matrices: Representing Adjective-Noun Constructions in Semantic Space EMNLP 2010 EEG responds to conceptual stimuli and corpus semantics EMNLP 2009 Words and Echoes: Assessing and Mitigating the Non-Randomness Problem in Word Frequency Distribution Modeling ACL 2007 zipfR: Word Frequency Modeling in R ACL 2007 A Figure of Merit for the Evaluation of Web-Corpus Randomness EACL 2006 Large Linguistically-Processed Web Corpora for Multiple Languages EACL 2006 Wordform- and Class-based Prediction of the Components of German Nominal Compounds in an AAC System COLING 2002