11 papers
Relational Abstractions for Spatial Reasoning with Diffusion Models
Ana Ezquerro, Ozan Özdenizci
Diffusion models excel at image synthesis, but they remain limited in their ability to reliably satisfy structured spatial reasoning constraints. In conditional data distribution m…
Synthetic Data Characterization via Training Dynamics
Irene Lago, Ana Ezquerro, David Vilares
Interpreting properties of LLM-generated data is important for understanding its utility and limitations across learning tasks. In this work, we characterize synthetic data through…
Hierarchical Bracketing Encodings Work for Dependency Graphs
Ana Ezquerro, Carlos Gómez-Rodríguez, David Vilares
We revisit hierarchical bracketing encodings from a practical perspective in the context of dependency graph parsing. The approach encodes graphs as sequences, enabling linear-time…
Bringing Emerging Architectures to Sequence Labeling in NLP
Ana Ezquerro, Carlos Gómez-Rodríguez, David Vilares
Pretrained Transformer encoders are the dominant approach to sequence labeling. While some alternative architectures-such as xLSTMs, structured state-space models, diffusion models…
LyS at SemEval 2025 Task 8: Zero-Shot Code Generation for Tabular QA
Adrián Gude, Roi Santos-Ríos, Francisco Prado-Valiño +2
This paper describes our participation in SemEval 2025 Task 8, focused on Tabular Question Answering. We developed a zero-shot pipeline that leverages an Large Language Model to ge…
Hierarchical Bracketing Encodings for Dependency Parsing as Tagging
Ana Ezquerro, David Vilares, Anssi Yli-Jyrä +1
We present a family of encodings for sequence labeling dependency parsing, based on the concept of hierarchical bracketing. We prove that the existing 4-bit projective encoding bel…
Better Benchmarking LLMs for Zero-Shot Dependency Parsing
Ana Ezquerro, Carlos Gómez-Rodríguez, David Vilares
While LLMs excel in zero-shot tasks, their performance in linguistic challenges like syntactic parsing has been less scrutinized. This paper studies state-of-the-art open-weight LL…
Dependency Graph Parsing as Sequence Labeling
Ana Ezquerro, David Vilares, Carlos Gómez-Rodríguez
Various linearizations have been proposed to cast syntactic dependency parsing as sequence labeling. However, these approaches do not support more complex graph-based representatio…
LyS at SemEval-2024 Task 3: An Early Prototype for End-to-End Multimodal Emotion Linking as Graph-Based Parsing
Ana Ezquerro, David Vilares
This paper describes our participation in SemEval 2024 Task 3, which focused on Multimodal Emotion Cause Analysis in Conversations. We developed an early prototype for an end-to-en…
From Partial to Strictly Incremental Constituent Parsing
Ana Ezquerro, Carlos Gómez-Rodríguez, David Vilares
We study incremental constituent parsers to assess their capacity to output trees based on prefix representations alone. Guided by strictly left-to-right generative language models…
On the Challenges of Fully Incremental Neural Dependency Parsing
Ana Ezquerro, Carlos Gómez-Rodríguez, David Vilares
Since the popularization of BiLSTMs and Transformer-based bidirectional encoders, state-of-the-art syntactic parsers have lacked incrementality, requiring access to the whole sente…