Papers by Ariadna Quattoni
Entity Disambiguation on a Tight Labeling Budget (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to training entity disambiguation models require a small labeling budget . a defense research analyst might need to map military equipment to a knowledge base describing emergent defense technologies. |
| Approach: | They propose a method that combines feature diversity with low rank correction . they use bilinear tensor models to train a model that uses a rich representation of context . |
| Outcome: | The proposed approach reduces the amount of labeled data necessary to achieve a given performance. |
Measuring Alignment Bias in Neural Seq2seq Semantic Parsers (2022.starsem-1)
Copied to clipboard
| Challenge: | Sequence-to-sequence semantic parsers with attention mechanisms have changed the research landscape . emergence of seq2seq models have led to questions about alignments . |
| Approach: | They investigate whether seq2seq models can handle both simple and complex alignments. |
| Outcome: | The proposed model performs better on monotonic and complex alignments compared to monotonic models . |
Analyzing Text Representations by Measuring Task Alignment (2023.acl-short)
Copied to clipboard
| Challenge: | Recent advances in text classification have shown that pre-trained representations are key for text classification. |
| Approach: | They propose a task alignment score that measures alignment at different levels of granularity. |
| Outcome: | The proposed score shows that task alignment can explain the performance of a given representation. |
SPOT: Zero-Shot Semantic Parsing Over Property Graphs (2025.findings-acl)
Copied to clipboard
| Challenge: | Knowledge Graphs (KGs) are becoming increasingly popular as a means of storing structured data. |
| Approach: | They propose a method to generate training data for semantic parsing over Property Graphs without human annotations by matching tree patterns to the KG and paraphrasing the query program with an LLM. |
| Outcome: | The proposed method generates training data for parsing over Property Graphs without human annotations on two property graph benchmarks utilizing the Cypher query language. |
Domain Pre-training Impact on Representations (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a small, specialized corpus can produce effective representations, but the quality of pre-training is not affected by the choice of corpus. |
| Approach: | They focus on the representation quality achieved through pre-training alone . |
| Outcome: | The results show that pre-training on a small, specialized corpus produces effective representations. |
Interpolated Spectral NGram Language Models (P19-1)
Copied to clipboard
| Challenge: | Spectral methods for learning weighted non-deterministic automata have nice theoretical and algorithmic properties, but they have been challenging to get competitive results on language modeling tasks. |
| Approach: | They propose a method for scaling up spectral learning and use interpolated predictions that are optimized to maximize perplexity. |
| Outcome: | The proposed method matches state-of-the-art ngram models while being very fast to train. |
Translate First Reorder Later: Leveraging Monotonicity in Semantic Parsing (2023.findings-eacl)
Copied to clipboard
| Challenge: | Existing approaches that model alignments between sentences fail at compositional generalization tasks, resulting in a resurgence of such approaches. |
| Approach: | They propose a two-step approach that first translates input sentences monotonically and then reorders them to obtain the correct output. |
| Outcome: | The proposed approach improves compositional generalization over existing models and other approaches that exploit gold alignment annotations. |
Align and Augment: Generative Data Augmentation for Compositional Generalization (2024.eacl-long)
Copied to clipboard
| Challenge: | Recent work on semantic parsing has shown that seq2seq models find compositional generalization challenging. |
| Approach: | They propose a data-augmentation strategy that exploits alignment annotations between sentences and their corresponding meaning representations to improve compositional generalization. |
| Outcome: | The proposed model improves compositional generalization performance by exploiting alignment annotations between sentences and their corresponding meaning representations. |
ZOGRASCOPE: A New Benchmark for Semantic Parsing over Property Graphs (2025.findings-emnlp)
Copied to clipboard
| Challenge: | PGs are increasingly used in knowledge graphs, but they are underrepresented in research . a benchmark is designed specifically for PG and queries written in Cypher. |
| Approach: | They propose a benchmark specifically for PGs and queries written in Cypher. |
| Outcome: | The proposed benchmark is designed specifically for PGs and queries written in Cypher. |
Minimizing Annotation Effort via Max-Volume Spectral Sampling (2021.findings-emnlp)
Copied to clipboard
| Challenge: | Spectral sampling strategies that minimize the number of annotations required to train a model are proposed. |
| Approach: | They propose a method that maximizes the amount of information useful for the learning algorithm by minimizing redundancy of samples in the selection. |
| Outcome: | The proposed method maximizes the amount of information useful for the learning algorithm or minimizes redundancy of samples in the selection. |
Leveraging the Structure of Pre-trained Embeddings to Minimize Annotation Effort (2024.naacl-long)
Copied to clipboard
| Challenge: | Current approaches for text classification are based on fine-tuning the representations computed by large language models. |
| Approach: | They propose to exploit structural properties of pre-trained embeddings to spread information . they use a semisupervised strategy to train models with minimal annotation effort . |
| Outcome: | The proposed method outperforms self-training and random walk labels on different datasets. |