Papers by Caio Corro

14 papers
Span-based discontinuous constituency parsing: a family of exact chart-based algorithms with time complexities from O(nˆ6) down to O(nˆ3) (2020.emnlp-main)

Copied to clipboard

Challenge: a novel chart-based parser for discontinuous constituency trees is proposed for span-based span parsing . it can process discontinuous constituent trees of block degree two, including ill-nested structures .
Approach: They propose a chart-based algorithm for span-based parsing of discontinuous constituency trees . they build variants with smaller search spaces and time complexities ranging from O(n6) down to O(N3) .
Outcome: The proposed algorithm can process 98% of constituents in linguistic treebanks while having the same complexity as continuous constituency parsers.
On the Rejection Criterion for Proxy-based Test-time Alignment (2026.acl-short)

Copied to clipboard

Challenge: Recent work suggests that test-time alignment methods rely on a small aligned model as a proxy that guides the generation of a larger base model.
Approach: They propose a rejection criterion based on a conservative confidence bet for test-time alignment methods that use a small aligned model as a proxy to guide the generation of a larger base model.
Outcome: The proposed approach outperforms previous work on several datasets.
Sparse Logistic Regression with High-order Features for Automatic Grammar Rule Extraction from Treebanks (2024.lrec-main)

Copied to clipboard

Challenge: Descriptive grammars are valuable, but they lack quantitative data.
Approach: They propose to extract and explore significant fine-grained grammar patterns and potential syntactic grammar rules from treebanks to create an easy-to-understand corpus-based grammar.
Outcome: The proposed model captures well-known and less well- known significant grammar rules in Spanish, French, and Wolof.
Few-shot domain adaptation for named-entity recognition via joint constrained k-means and subspace selection (2025.coling-main)

Copied to clipboard

Challenge: Named-entity recognition (NER) requires large annotated datasets, which limits its applicability across domains with varying entity definitions.
Approach: They propose a weakly-supervised algorithm that combines small labeled datasets with large amounts of unlabeled data.
Outcome: The proposed approach achieves state-of-the-art results in few-shot NER . it combines label supervision, cluster size constraints, and domain-specific discriminative subspace selection.
On Graph-based Reentrancy-free Semantic Parsing (2023.tacl-1)

Copied to clipboard

Challenge: Existing graph-based approaches for semantic parsing fail on compositional generalization tasks.
Approach: They propose a graph-based approach for semantic parsing that solves two problems . they propose two algorithms based on constraint smoothing and conditional gradient to approximate these problems.
Outcome: The proposed graph-based approach delivers state-of-the-art results on GeoQuery, Scan, and Clevr .
KAD: A Framework for Proxy-based Test-time Alignment with Knapsack Approximation Deferral (2026.eacl-long)

Copied to clipboard

Challenge: Existing studies have shown that large language models require further alignment to adhere to downstream task requirements and stylistic preferences.
Approach: They propose a proxy-based test-time alignment method to circumvent alignment costs by reducing the token-specific deferral rule to 0-1 knapsack problem.
Outcome: The proposed method improves both task performance and speculative decoding speed.
A Fast and Sound Tagging Method for Discontinuous Named-Entity Recognition (2024.emnlp-main)

Copied to clipboard

Challenge: Named-entity recognition (NER) is a fundamental natural language processing task . a tagging scheme for discontinuous named entities is proposed .
Approach: They propose a tagging scheme for discontinuous named entity recognition based on an explicit description of the inner structure of discontinuous mentions.
Outcome: The proposed method is comparable to state-of-the-art models on three English datasets in the biomedical domain.
A dynamic programming algorithm for span-based nested named-entity recognition in O(n2) (2023.acl-long)

Copied to clipboard

Challenge: Named entity recognition (NER) is a fundamental problem in information retrieval . nested NER has a cubic-time complexity, but can be realized in quadratic time using a semi-Markov model .
Approach: They propose a span-based named-entity recognition algorithm with a quadratic-time complexity . they add a constraint on the search space to reduce the complexity of the algorithm .
Outcome: The proposed algorithm covers a large part of three standard English benchmarks and delivers comparable results.
On the inconsistency of separable losses for structured prediction (2023.eacl-main)

Copied to clipboard

Challenge: Modern natural language processing (NLP) heavily relies on machine learning, where prediction models are learned by minimizing a loss function over the training data.
Approach: They prove that separable negative log-likelihood losses for structured prediction are not Bayes consistent.
Outcome: The proposed model does not predict the most probable structure in the data distribution for a given input.
Structural generalization in COGS: Supertagging is (almost) all you need (2023.emnlp-main)

Copied to clipboard

Challenge: Recent studies have shown that neural networks fail to generalize on out-of-distribution examples.
Approach: They extend a neural graph-based parsing framework to address compositional generalization limitations . they introduce a supertagging step with valency constraints and reduce the graph prediction problem .
Outcome: The proposed approach improves results on COGS datasets that require structural generalization.
Bregman Conditional Random Fields: Sequence Labeling with Parallelizable Inference Algorithms (2025.acl-long)

Copied to clipboard

Challenge: Existing methods for sequence labeling are hidden Markov models and conditional random fields (CRF).
Approach: They propose a new discriminative model for sequence labeling called Bregman conditional random fields (BCRF) they propose to use Fenchel-Young losses to learn from partial labels.
Outcome: The proposed model performs better in highly constrained settings than the existing model, which is slower and faster.
Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming (P19-1)

Copied to clipboard

Challenge: Discrete structures are ubiquitous in the study of natural languages, for example in morphology, syntax and discourse analysis.
Approach: They treat projective dependency trees as latent variables in their probabilistic model and induce them in such a way as to be beneficial for a downstream task.
Outcome: The proposed model is effective on sentiment analysis and natural language inference tasks and is fully differentiable.
Nested Named Entity Recognition as Single-Pass Sequence Labeling (2025.findings-emnlp)

Copied to clipboard

Challenge: nested named entity recognition is a sequence labeling task that can be trained using any off-the-shelf sequence labelling library.
Approach: They use prior work that linearizes constituency structures to create a nested named entity recognition task.
Outcome: The proposed method reduces the complexity of the predicted nested entity recognition problem to a simple token classification task.
DocPolarBERT: A Pre-trained Model for Document Understanding with Relative Polar Coordinate Encoding of Layout Structures (2026.eacl-long)

Copied to clipboard

Challenge: Existing models that take text block positions into account are not efficient for document understanding.
Approach: They propose a layout-aware BERT model that takes into account text block positions in relative polar coordinate system rather than the Cartesian one.
Outcome: The proposed model eliminates the need for absolute positional embeddings on a dataset more than six times smaller than the widely used IIT-CDIP corpus.

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