Papers by Emmanuele Chersoni
Generalizing over Long Tail Concepts for Medical Term Normalization (2022.emnlp-main)
Copied to clipboard
Beatrice Portelli, Simone Scaboro, Enrico Santus, Hooman Sedghamiz, Emmanuele Chersoni, Giuseppe Serra
| Challenge: | Medical term normalization is a task of mapping a text to a large number of output classes. |
| Approach: | They propose a learning strategy that leverages hierarchical information to enhance generalizability of models. |
| Outcome: | The proposed strategy produces state-of-the-art performance on seen concepts and consistent improvements on unseen ones, allowing efficient zero-shot knowledge transfer across text typologies and datasets. |
Comparing Static and Contextual Distributional Semantic Models on Intrinsic Tasks: An Evaluation on Mandarin Chinese Datasets (2024.lrec-main)
Copied to clipboard
| Challenge: | Distributional Semantics has undergone significant changes with the introduction of contextualized distributional models. |
| Approach: | They compare static and contextual distributional models for Mandarin Chinese . they find that static models are stronger for some of the classical tasks . |
| Outcome: | The proposed models perform better on some of the classical tasks that consider word meaning independent of context, while contextualized models excel in identifying semantic relations between word pairs and categorization of words into abstract semantic classes. |
Ciron: a New Benchmark Dataset for Chinese Irony Detection (2020.lrec-1)
Copied to clipboard
| Challenge: | Automatic Chinese irony detection often lacks labeled benchmark datasets . despite its pervasive nature, irony is a trope whose actual meaning differs from what is literally enunciated. |
| Approach: | They propose to use a Chinese benchmark dataset for automatic Chinese irony detection to provide a benchmark for machine learning models. |
| Outcome: | The proposed dataset includes more than 8.7K posts, collected from Weibo, a micro blogging platform. |
Automatic Learning of Modality Exclusivity Norms with Crosslingual Word Embeddings (2020.starsem-1)
Copied to clipboard
| Challenge: | Normative studies on modality for English words are relatively common . however, they are limited to a relatively small number of languages and require costly ratings. |
| Approach: | They aim to learn a mapping between word embeddings and modality norms by training on a high-resource language and testing on . monolingual and crosslingual word embeds are used to predict modality association scores . |
| Outcome: | The proposed model predicts modality associations even when trained on an English resource and tested on a completely unseen language. |
Empirical Sufficiency Lower Bounds for Language Modeling with Locally-Bootstrapped Semantic Structures (2023.starsem-1)
Copied to clipboard
| Challenge: | a recent attempt at language modeling with predicted semantic structure failed to establish empirical lower bounds on what could have made the attempt successful. |
| Approach: | They propose a concise binary vector representation of semantic structure at the lexical level and evaluate how good an incremental tagger needs to be to achieve better-than-baseline performance. |
| Outcome: | The proposed model can achieve better-than-baseline performance without losing its main advantages and lower bounds on prediction quality can't be established via a single score alone. |
Comparing Probabilistic, Distributional and Transformer-Based Models on Logical Metonymy Interpretation (2020.aacl-main)
Copied to clipboard
| Challenge: | Logical metonymies are type clashes between an event-selecting verb and an entity-denoting noun . they are typically interpreted by inferring a hidden event on the basis of contextual cues . |
| Approach: | They propose to use probabilistic and distributional models to model logical metonymy interpretation . they compare models with the best Transformer-based models and some traditional distributional ones . |
| Outcome: | The proposed models perform well on a complex scenario, but low performance on some datasets suggests that logical metonymy is still a challenging phenomenon for computational modeling. |
BERT Prescriptions to Avoid Unwanted Headaches: A Comparison of Transformer Architectures for Adverse Drug Event Detection (2021.eacl-main)
Copied to clipboard
| Challenge: | Pretrained transformer-based models are a common choice for identifying drug events from social media texts. |
| Approach: | They propose to compare transformer-based models with in-domain language pretraining to find out which one is better at ADE detection. |
| Outcome: | The proposed models outperform SpanBERT and PubMedBERT on two benchmarks. |
Did the Cat Drink the Coffee? Challenging Transformers with Generalized Event Knowledge (2021.starsem-1)
Copied to clipboard
Paolo Pedinotti, Giulia Rambelli, Emmanuele Chersoni, Enrico Santus, Alessandro Lenci, Philippe Blache
| Challenge: | Prior work has explored the ability of computational models to predict word semantic fit with a given predicate. |
| Approach: | They compare Transformers Language Models to SDM to assess their performance . they found that TLMs do not capture important aspects of event knowledge . people can discriminate between typical and atypical events, they say . |
| Outcome: | The proposed models can achieve comparable performance to SDM, but they lack important aspects of event knowledge. |
Can Large Language Models Interpret Noun-Noun Compounds? A Linguistically-Motivated Study on Lexicalized and Novel Compounds (2024.acl-long)
Copied to clipboard
| Challenge: | Noun-noun compounds represent an important challenge for Natural Language Understanding . correct interpretation of noun-nomin compounds is essential for many applications . |
| Approach: | They test whether Large Language Models can interpret the semantic relation between nouns . they also test whether they can abstract from such knowledge to predict the relation . |
| Outcome: | The proposed models can interpret the semantic relation between nouns and compounds using analogical comparisons. |
Modeling the Influence of Verb Aspect on the Activation of Typical Event Locations with BERT (2021.findings-acl)
Copied to clipboard
| Challenge: | Prior studies have shown that aspect of the main verb plays an important role in non-core semantic roles such as locations. |
| Approach: | They tested the popular language model BERT to determine whether its predictions of prototypical locations were influenced by aspect. |
| Outcome: | The language model BERT modelled the typicality of locations independently of the verb aspect. |
We Understand Elliptical Sentences, and Language Models should Too: A New Dataset for Studying Ellipsis and its Interaction with Thematic Fit (2023.acl-long)
Copied to clipboard
| Challenge: | ellipsis is a linguistic phenomenon characterized by the omission of one or more sentence elements. |
| Approach: | They investigated how prototypicality affects the ability of Language Models to handle elliptical sentences . they found that models were better suited to evaluating argument thematic fit . |
| Outcome: | The proposed dataset shows that the models perform better for typical events than for atypical ones in different elliptical contexts. |
Investigating Aspect Features in Contextualized Embeddings with Semantic Scales and Distributional Similarity (2024.starsem-1)
Copied to clipboard
| Challenge: | Aspect is a linguistic category describing how actions and events unfold over time. |
| Approach: | They propose to use semantic projections to examine whether the vector dimensions of annotated verbs reflect human linguistic distinctions. |
| Outcome: | The proposed models encode the aspects of stativity, durativity and telicity in most of their layers, while durativité is the most challenging feature. |
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines (2025.naacl-long)
Copied to clipboard
Genta Indra Winata, Frederikus Hudi, Patrick Amadeus Irawan, David Anugraha, Rifki Afina Putri, Wang Yutong, Adam Nohejl, Ubaidillah Ariq Prathama, Nedjma Ousidhoum, Afifa Amriani, Anar Rzayev, Anirban Das, Ashmari Pramodya, Aulia Adila, Bryan Wilie, Candy Olivia Mawalim, Cheng Ching Lam, Daud Abolade, Emmanuele Chersoni, Enrico Santus, Fariz Ikhwantri, Garry Kuwanto, Hanyang Zhao, Haryo Akbarianto Wibowo, Holy Lovenia, Jan Christian Blaise Cruz, Jan Wira Gotama Putra, Junho Myung, Lucky Susanto, Maria Angelica Riera Machin, Marina Zhukova, Michael Anugraha, Muhammad Farid Adilazuarda, Natasha Christabelle Santosa, Peerat Limkonchotiwat, Raj Dabre, Rio Alexander Audino, Samuel Cahyawijaya, Shi-Xiong Zhang, Stephanie Yulia Salim, Yi Zhou, Yinxuan Gui, David Ifeoluwa Adelani, En-Shiun Annie Lee, Shogo Okada, Ayu Purwarianti, Alham Fikri Aji, Taro Watanabe, Derry Tanti Wijaya, Alice Oh, Chong-Wah Ngo
| Challenge: | Vision Language Models struggle with cultural-specific knowledge, especially in languages other than English and in underrepresented cultural contexts. |
| Approach: | They propose a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects and a training dataset. |
| Outcome: | The proposed model performs better with correct location context, but struggles with adversarial contexts and predicting specific regional cuisines and languages. |
Sparse Brains are Also Adaptive Brains: Cognitive-Load-Aware Dynamic Activation for LLMs (2026.findings-eacl)
Copied to clipboard
| Challenge: | Existing sparsity methods lack adaptivity to contextual or model structural demands or incur prohibitive computational overhead. |
| Approach: | They propose a Cognitive-Load-Aware Dynamic Activation framework that synergizes statistical sparsity with semantic adaptability. |
| Outcome: | The proposed framework achieves 20% average speedup with less than 2% accuracy degradation outperforming Griffin and TT. |
Do LLMs Capture Embodied Cognition and Cultural Variation? Cross-Linguistic Evidence from Demonstratives (2026.acl-long)
Copied to clipboard
| Challenge: | a new study examines whether large language models acquire embodied cognition and cultural conventions from training data . demonstratives are a natural lens for evaluating linguistic phenomena that reflect cultural variation . aaron e. duan and j. nà: "the complexity of the language model is a major challenge for LLMs" |
| Approach: | They introduce demonstratives as a probe for grounded knowledge by analyzing 6,400 responses from 320 native speakers. |
| Outcome: | The proposed model fails to understand proximal–distal contrast and shows no cultural differences . the proposed model is a new probe for evaluating embodied cognition and cultural conventions . |
Good Arguments Against the People Pleasers: How Reasoning Mitigates (Yet Masks) LLM Sycophancy (2026.acl-long)
Copied to clipboard
| Challenge: | Recent studies have identified a critical drawback of aligning models with human judgments and outputs that are flawed or incorrect. |
| Approach: | They evaluate a range of LLMs to examine whether CoT reasoning mitigates sycophancy . they find that reasoning masks a tendency to scophage in some cases . |
| Outcome: | The proposed model models show that CoT reasoning reduces sycophancy but masks it in some cases. |
Are Word Embeddings Really a Bad Fit for the Estimation of Thematic Fit? (2020.lrec-1)
Copied to clipboard
| Challenge: | In recent years, vectors derived from neural network training have replaced count-based distributional semantic models as a de facto standard for word representation in NLP. |
| Approach: | They propose to evaluate count models and word embeddings on thematic fit estimation by taking into account a larger number of parameters and verb roles and introducing dependency-based embedders in the comparison. |
| Outcome: | The proposed model outperforms count models and word embeddings in thematic fit estimation tasks while introducing dependency-based embedders. |
PhonoThink: Improving Large Language Models’ Reasoning on Chinese Phonological Ambiguities (2025.emnlp-main)
Copied to clipboard
| Challenge: | Effectively resolving phonological ambiguities is crucial for robust natural language processing, as these ambiguity are pervasive in tasks ranging from speech-to-text, spelling correction, to offensive language detection. |
| Approach: | They propose a framework to enhance LLMs’ phonological capability through a multiple-stage training approach. |
| Outcome: | The proposed framework enables the base model to achieve comparable performance to a much larger model. |
ExpliCa: Evaluating Explicit Causal Reasoning in Large Language Models (2025.findings-acl)
Copied to clipboard
Martina Miliani, Serena Auriemma, Alessandro Bondielli, Emmanuele Chersoni, Lucia Passaro, Irene Sucameli, Alessandro Lenci
| Challenge: | Large Language Models (LLMs) are increasingly used in tasks requiring interpretive and inferential accuracy. |
| Approach: | They propose a dataset for evaluating Large Language Models in explicit causal reasoning that integrates causal and temporal relations presented in different linguistic orders and explicitly expressed by linguistic connectives. |
| Outcome: | The proposed model performs better than existing models in the domain of causal reasoning. |
A Rank-Based Similarity Metric for Word Embeddings (P18-2)
Copied to clipboard
| Challenge: | Word Embeddings have become a standard for word representations, with vector cosine being the only similarity metric. |
| Approach: | They propose to use rank-based similarity estimation metrics to measure word similarity . they find WE outperforms vector cosine in the recent outlier detection task . |
| Outcome: | The proposed rank-based measure outperforms vector cosine in the recent outlier detection task. |
Are Language Models Sensitive to Semantic Attraction? A Study on Surprisal (2023.starsem-1)
Copied to clipboard
| Challenge: | In psycholinguistics, semantic attraction is a sentence processing phenomenon in which a given argument violates the selectional requirements of a verb but is not perceived by comprehenders due to its attraction to another noun in the same sentence. |
| Approach: | They used autoregressive language models to compute the sentence-level and target phrase-level Surprisal scores of a psycholinguistic dataset on semantic attraction. |
| Outcome: | The proposed models are sensitive to semantic attraction, leading to reduced Surprisal scores, although none perfectly matches the human behavioral pattern. |
Exploring a Unified Sequence-To-Sequence Transformer for Medical Product Safety Monitoring in Social Media (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Adverse Events (AEs) are harmful events resulting from the use of medical products. |
| Approach: | They propose a model that combines sequence-to-sequence learning with language transfer capabilities to improve model robustness. |
| Outcome: | The proposed approach achieves strong performance over baselines on English benchmarks. |
Learning to Look at the Other Side: A Semantic Probing Study of Word Embeddings in LLMs with Enabled Bidirectional Attention (2025.acl-long)
Copied to clipboard
| Challenge: | Autoregressive Large Language Models (LLMs) demonstrate exceptional performance in language understanding and generation tasks, but their application in text embedding tasks has been relatively slow due to the constraints of the unidirectional attention mechanism. |
| Approach: | They propose to enable bidirectional attention in LLMs to improve their ability to represent subsequent context but weaken their utilization of preceding context. |
| Outcome: | The proposed model improves the LLMs’ ability to represent subsequent context but weakens their utilization of preceding context, while contrastive learning training can help to maintain both abilities. |