Papers by Enrico Santus

12 papers
Generalizing over Long Tail Concepts for Medical Term Normalization (2022.emnlp-main)

Copied to clipboard

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.
Towards Debiasing Fact Verification Models (D19-1)

Copied to clipboard

Challenge: Prior research has shown that data collection methods that use crowdsourcing introduce idiosyncratic biases that impact performance in unexpected ways.
Approach: They propose a method to regularize the training data to avoid idiosyncrasies in the datasets that are used for fact verification.
Outcome: The proposed model outperforms the existing model on the FEVER dataset, achieving 61.7% of the baseline.
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

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.
SupCL-Seq: Supervised Contrastive Learning for Downstream Optimized Sequence Representations (2021.findings-emnlp)

Copied to clipboard

Challenge: SupCL-Seq extends contrastive learning from computer vision to sequence classification tasks.
Approach: They propose a supervised alternative to Masked Language Modeling (MLM) that extends contrastive learning to sequence optimization in NLP by altering the dropout mask probability in standard Transformer architectures.
Outcome: The proposed method leads to large gains on the GLUE benchmark, including 6% absolute improvement on CoLA, 5.4% on MRPC, 4.7% on RTE and 2.6% on STS-B.
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines (2025.naacl-long)

Copied to clipboard

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.
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.
Deciphering Undersegmented Ancient Scripts Using Phonetic Prior (2021.tacl-1)

Copied to clipboard

Challenge: a number of undeciphered languages are still undecipherated, igniting fierce scientific debate . a recent study shows that NLP methods can successfully decipher lost languages .
Approach: They propose a decipherment model that incorporates phonetic geometry into word segmentation and cognate alignment . they use the International Phonetic Alphabet to learn character embeddings based on historical sound change .
Outcome: The proposed model shows that it can decipher both deciphered and undeciphered languages.
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.
IMaT: Unsupervised Text Attribute Transfer via Iterative Matching and Translation (D19-1)

Copied to clipboard

Challenge: Existing approaches to rewrite sentences with certain attributes are difficult and often result in poor content-preservation and ungrammaticality.
Approach: They propose a method that uses a sequence-to-sequence model to learn attribute transfer . existing approaches try to explicitly disentangle content and attribute information .
Outcome: The proposed method outperforms complex state-of-the-art systems by a large margin in sentiment modification and formality transfer tasks.
GraphIE: A Graph-Based Framework for Information Extraction (N19-1)

Copied to clipboard

Challenge: Most modern Information Extraction (IE) systems are implemented as sequential taggers and model local dependencies.
Approach: They propose a framework that operates over a graph representing a broad set of dependencies between textual units.
Outcome: The proposed framework outperforms the state-of-the-art sequence tagging model on three different tasks.
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.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations