IMPLI: Investigating NLI models' performance on figurative language
Natural language inference (NLI) has been widely used as a task to train and evaluate
models for language understanding. However, the ability of NLI models to perform …
models for language understanding. However, the ability of NLI models to perform …
Translate meanings, not just words: Idiomkb's role in optimizing idiomatic translation with language models
To translate well, machine translation (MT) systems and general-purposed language models
(LMs) need a deep understanding of both source and target languages and cultures …
(LMs) need a deep understanding of both source and target languages and cultures …
DiPlomat: a dialogue dataset for situated pragmatic reasoning
The ability to discern and comprehend pragmatic meanings is a cornerstone of social and
emotional intelligence, referred to as pragmatic reasoning. Despite the strides made in the …
emotional intelligence, referred to as pragmatic reasoning. Despite the strides made in the …
Getting BART to ride the idiomatic train: Learning to represent idiomatic expressions
Idiomatic expressions (IEs), characterized by their non-compositionality, are an important
part of natural language. They have been a classical challenge to NLP, including pre-trained …
part of natural language. They have been a classical challenge to NLP, including pre-trained …
Computational Approaches to the Detection of Lesser-Known Rhetorical Figures: A Systematic Survey and Research Challenges
Rhetorical figures play a major role in our everyday communication as they make text more
interesting, more memorable, or more persuasive. Therefore, it is important to …
interesting, more memorable, or more persuasive. Therefore, it is important to …
[HTML][HTML] Vector representations of idioms in conversational systems
In this study, we demonstrate that an open-domain conversational system trained on idioms
or figurative language generates more fitting responses to prompts containing idioms …
or figurative language generates more fitting responses to prompts containing idioms …
Spanning the spectrum of hatred detection: a Persian multi-label hate speech dataset with annotator rationales
Z Delbari, NS Moosavi, MT Pilehvar - Proceedings of the AAAI …, 2024 - ojs.aaai.org
With the alarming rise of hate speech in online communities, the demand for effective NLP
models to identify instances of offensive language has reached a critical point. However, the …
models to identify instances of offensive language has reached a critical point. However, the …
Is Less More? Quality, Quantity and Context in Idiom Processing with Natural Language Models
A Knietaite, A Allsebrook, A Minkov… - arXiv preprint arXiv …, 2024 - arxiv.org
Compositionality in language models presents a problem when processing idiomatic
expressions, as their meaning often cannot be directly derived from their individual parts …
expressions, as their meaning often cannot be directly derived from their individual parts …
Introducing Rhetorical Parallelism Detection: A New Task with Datasets, Metrics, and Baselines
S Bothwell, J DeBenedetto, T Crnkovich… - arXiv preprint arXiv …, 2023 - arxiv.org
Rhetoric, both spoken and written, involves not only content but also style. One common
stylistic tool is $\textit {parallelism} $: the juxtaposition of phrases which have the same …
stylistic tool is $\textit {parallelism} $: the juxtaposition of phrases which have the same …
Figuratively Speaking: Authorship Attribution via Multi-Task Figurative Language Modeling
GA Katsios, N Sa, T Strzalkowski - arXiv preprint arXiv:2406.08218, 2024 - arxiv.org
The identification of Figurative Language (FL) features in text is crucial for various Natural
Language Processing (NLP) tasks, where understanding of the author's intended meaning …
Language Processing (NLP) tasks, where understanding of the author's intended meaning …