Sebastian Padó

FrameNet’s <i>Using</i> relation as a source of concept-based paraphrases

2018 · Constructions and Frames

Abstract Characterizing paraphrases formally has proven to be a challenging task. Hasegawa et al. (2011) pointed out the usefulness of FrameNet for paraphrase research, focusing on paraphrases which are backed by underlying classical linguistic relationships …

SemEval-2010 Task 8: Multi-Way Classification of Semantic Relations Between Pairs of Nominals

2019 · arXiv (Cornell University)

SemEval-2 Task 8 focuses on Multi-way classification of semantic relations between pairs of nominals. The task was designed to compare different approaches to semantic relation classification and to provide a standard testbed for future research. …

Masking Actor Information Leads to Fairer Political Claims Detection

2020

A central concern in Computational Social Sciences (CSS) is fairness: where the role of NLP is to scale up text analysis to large corpora, the quality of automatic analyses should be as independent as possible …

Improving Neural Political Statement Classification with Class Hierarchical Information

2022 · Findings of the Association for Computational Linguistics: ACL 2022

Many tasks in text-based computational social science (CSS) involve the classification of political statements into categories based on a domain-specific codebook. In order to be useful for CSS analysis, these categories must be fine-grained. The …

Understanding the Relation of User and News Representations in Content-Based Neural News Recommendation

2022 · arXiv (Cornell University)

A number of models for neural content-based news recommendation have been proposed. However, there is limited understanding of the relative importances of the three main components of such systems (news encoder, user encoder, and scoring …

Representation biases in sentence transformers

2023

Variants of the BERT architecture specialised for producing full-sentence representations often achieve better performance on downstream tasks than sentence embeddings extracted from vanilla BERT. However, there is still little understanding of what properties of inputs …

An Attribution Method for Siamese Encoders

2023 · arXiv (Cornell University)

Despite the success of Siamese encoder models such as sentence transformers (ST), little is known about the aspects of inputs they pay attention to. A barrier is that their predictions cannot be attributed to individual …