Papers by Elisa Bassignana
CrossRE: A Cross-Domain Dataset for Relation Extraction (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Relation Extraction (RE) evaluation is limited to in-domain setups . despite the drought of research on cross-domain RE, its practical importance remains . |
| Approach: | They propose a cross-domain benchmark for relation extraction which includes multi-label annotations and meta-data to include explanations and flags of difficult instances. |
| Outcome: | The proposed model includes explanations and flags of difficult instances. |
What’s wrong with your model? A Quantitative Analysis of Relation Classification (2024.starsem-1)
Copied to clipboard
| Challenge: | A major trend in NLP research aims at designing more sophisticated setups to improve the state-of-the-art (SOTA) on a target task. |
| Approach: | They propose an in-depth analysis suite for Relation Classification to be used for prediction tasks. |
| Outcome: | The proposed model improves over the baseline by >3 Micro-F1 . the proposed model is based on a case study and a preliminary error-guided analysis . |
How to Encode Domain Information in Relation Classification (2024.lrec-main)
Copied to clipboard
Elisa Bassignana, Viggo Unmack Gascou, Frida Nøhr Laustsen, Gustav Kristensen, Marie Haahr Petersen, Rob van der Goot, Barbara Plank
| Challenge: | Existing deep learning models require a lot of training data to obtain high performance. |
| Approach: | They propose a multi-domain training setup for Relation Classification (RC) they compare different ways to enrich input instances with domain information . |
| Outcome: | The proposed model improves > 2 Macro-F1 against the baseline setup. |
Silver Syntax Pre-training for Cross-Domain Relation Extraction (2023.findings-acl)
Copied to clipboard
| Challenge: | Relation Extraction (RE) is the task of extracting structured knowledge from unstructured text. |
| Approach: | They exploit the affinity between syntactic structure and semantic RE to obtain low-cost pre-training data. |
| Outcome: | The proposed model outperforms baseline models in five out of six cross-domain setups without additional annotated data. |
What Do You Mean by Relation Extraction? A Survey on Datasets and Study on Scientific Relation Classification (2022.acl-srw)
Copied to clipboard
| Challenge: | Existing RE surveys focus on modeling techniques, but there are few that are based on real-world scenarios. |
| Approach: | They propose to survey RE datasets and revisit the task definition and its adoption by the community. |
| Outcome: | The proposed approach improves the reliability of RE evaluations across multiple datasets and reveals significant discrepancies in annotations. |
The AI Gap: How Socioeconomic Status Affects Language Technology Interactions (2025.acl-long)
Copied to clipboard
| Challenge: | Socioeconomic status (SES) fundamentally influences how people interact with technology, but it is limited by proxy metrics and synthetic data. |
| Approach: | They collect 6,482 prompts from previous interactions of 1,000 individuals from ‘diverse socioeconomic backgrounds’ about their use of language technologies and generative AI. |
| Outcome: | The findings show that higher SES groups have higher levels of abstraction, convey requests more concisely, and topics like ‘inclusivity’ and ‘travel’. |
Experimental Standards for Deep Learning in Natural Language Processing Research (2022.findings-emnlp)
Copied to clipboard
Dennis Ulmer, Elisa Bassignana, Max Müller-Eberstein, Daniel Varab, Mike Zhang, Rob van der Goot, Christian Hardmeier, Barbara Plank
| Challenge: | a lack of common experimental standards remains an open challenge to the field at large . |
| Approach: | They propose to distill discussions on experimental standards into a single, widely-applicable methodology. |
| Outcome: | Using best practices, we can strengthen experimental evidence, improve reproducibility and enable scientific progress. |
Can Humans Identify Domains? (2024.lrec-main)
Copied to clipboard
Maria Barrett, Max Müller-Eberstein, Elisa Bassignana, Amalie Brogaard Pauli, Mike Zhang, Rob van der Goot
| Challenge: | Textual domain is a crucial property within the Natural Language Processing community due to its effects on downstream model performance. |
| Approach: | They examine the level of human disagreement and the relative difficulty of each annotation task by training classifiers to perform the same task. |
| Outcome: | The authors show that human proficiency in identifying related intrinsic textual properties is low and that disagreements are high. |
Evidence > Intuition: Transferability Estimation for Encoder Selection (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing studies on LM transferability have focused on a priori tuning of encoders . prior work has examined the different yet related tasks of performance prediction . |
| Approach: | They propose to generate quantitative evidence to predict which LM will perform best on a target task without fine-tuning all candidates. |
| Outcome: | The proposed model outperforms the standard of human practitioner ranking in 94% of the setups. |