Author pages are created from data sourced from our academic publisher partnerships and public sources.
Share This Author
ParsiNLU: A Suite of Language Understanding Challenges for Persian
- Daniel Khashabi, Arman Cohan, Yadollah Yaghoobzadeh
- Computer Science, LinguisticsTransactions of the Association for Computational…
- 11 December 2020
This work introduces ParsiNLU, the first benchmark in Persian language that includes a range of language understanding tasks—reading comprehension, textual entailment, and so on, and presents the first results on state-of-the-art monolingual and multilingual pre-trained language models on this benchmark and compares them with human performance.
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
The efficacy of NL-Augmenter is demonstrated by using several of its tranformations to analyze the robustness of popular natural language models and the infrastructure, datacards and robutstness analysis results are shown.
EmoTag – Towards an Emotion-Based Analysis of Emojis
This work provides a method to quantify the emotional association of basic emotions such as anger, fear, joy, and sadness for a set of emojis, and collects and process a unique corpus of 20 million emoji-centric tweets, such that it can capture rich emoji semantics using a comparably small dataset.
What Sparks Joy: The AffectVec Emotion Database
This work harnesses the power of Big Data by using neural vector space models trained with large-scale supervision from co-occurrence patterns to induce AffectVec, a new emotion database providing graded emotion intensity scores for English language words with regard to a fine-grained inventory of over 200 different emotion categories.
Guilt by Association: Emotion Intensities in Lexical Representations
Overall, it is found that word vectors carry substantial potential for inducing fine-grained emotion intensity scores, showing a far higher correlation with human ground truth ratings than achieved by state-ofthe-art emotion lexicons.
A New Wavelet Based SVM Classifier for Wild Fire Detection Using Decision Fusion Framework in Video
- Shahab Raji
- Computer Science
The new wavelet kernel is proposed to improve the generalization ability of the support vector machine (SVM) and utilizes the principle of wavelet analysis to facilitate nonlinear characteristic extraction of the image data.