Results 61 to 70 of about 212,436 (345)
Universal Adversarial Triggers for Attacking and Analyzing NLP [PDF]
Adversarial examples highlight model vulnerabilities and are useful for evaluation and interpretation. We define universal adversarial triggers: input-agnostic sequences of tokens that trigger a model to produce a specific prediction when concatenated to
Eric Wallace +4 more
semanticscholar +1 more source
A collection of Wa texts in the Chinese orthography for use in NLP
This is a collection of Wa texts for use in NLP, following the orthography prevalent in ...
Watkins, Justin, Hill, Nathan
core +1 more source
Persian Causality Corpus (PerCause) and the Causality Detection Benchmark
Recognizing causal elements and causal relations in the text is among the challenging issues in natural language processing (NLP), specifically in low-resource languages such as Persian. In this research, we prepare a causality human-annotated corpus for
Zeinab Rahimi, Mehrnoush ShamsFard
doaj
Social networks like Twitter are increasingly important in the creation of new ways of communication. They have also become useful tools for social and linguistic research due to the massive amounts of public textual data available.
Joseba Fernandez de Landa +2 more
doaj +1 more source
A collection of Wa texts and a Wa wordlist (PRC orthography) for use in NLP
This is a collection of Wa texts for use in NLP, following the orthography prevalent in ...
Watkins, Justin, Hill, Nathan
core +1 more source
A collection of Akha vocabulary and texts for use in NLP
This is a collection of Akha (ISO ahk) vocabulary and texts for use in ...
Hill, Nathan, Akha, Ghoemeh
core +1 more source
Cross-Lingual Bimodal Emotion Recognition with LLM-Based Label Smoothing
Bimodal emotion recognition based on audio and text is widely adopted in video-constrained real-world applications such as call centers and voice assistants.
Elena Ryumina +4 more
doaj +1 more source
On the definition of toxicity in NLP
The fundamental problem in toxicity detection task lies in the fact that the toxicity is ill-defined. This causes us to rely on subjective and vague data in models' training, which results in non-robust and non-accurate results: garbage in - garbage out.
Sergey Berezin +2 more
openaire +3 more sources
The growing demand for personalized human–computer interaction calls for methods that jointly model emotional states and personality traits. However, large-scale multimodal corpora annotated for both tasks are still lacking.
Elena Ryumina +7 more
doaj +1 more source
Multimodal Sequential Fashion Attribute Prediction
We address multimodal product attribute prediction of fashion items based on product images and titles. The product attributes, such as type, sub-type, cut or fit, are in a chain format, with previous attribute values constraining the values of the next ...
Hasan Sait Arslan +3 more
doaj +1 more source

