Misinformation threatens modern society by promoting distrust in science, changing
narratives in public health, heightening social polarization, and disrupting democratic …

Current approaches in paraphrase generation and detection heavily rely on a single general
similarity score, ignoring the intricate linguistic properties of language. This paper introduces …

We present ProtoTEx, a novel white-box NLP classification architecture based on prototype
networks. ProtoTEx faithfully explains model decisions based on prototype tensors that …

In this paper, we present InferES-an original corpus for Natural Language Inference (NLI) in
European Spanish. We propose, implement, and analyze a variety of corpus-creating …

Across all fields of academic study, experts cite their sources when sharing information.
While large language models (LLMs) excel at synthesizing information, they do not provide …

In this paper, we present a new approach for the evaluation, error analysis, and
interpretation of supervised and unsupervised Paraphrase Identification (PI) systems. Our …

Paraphrase identification has been formulated as a binary classification task to decide
whether two sentences hold a paraphrase relationship. Existing paraphrase datasets only …

In this paper, we approach the problem of semantic search by introducing a task of
paraphrase span detection, ie given a segment of text as a query phrase, the task is to …

Despite the remarkable progress in the field of computational argumentation, dialogue
systems concerned with argumentative tasks often rely on structured knowledge about …

In this paper, we present a methodology for decomposing and comparing multiple meaning
relations (paraphrasing, textual entailment, contradiction, and specificity). The methodology …