Word2Vec: Optimal hyperparameters and their impact on natural language processing downstream tasks
Word2Vec is a prominent model for natural language processing tasks. Similar inspiration is
found in distributed embeddings (word-vectors) in recent state-of-the-art deep neural …
found in distributed embeddings (word-vectors) in recent state-of-the-art deep neural …
State-of-the-art in Open-domain Conversational AI: A Survey
We survey SoTA open-domain conversational AI models with the objective of presenting the
prevailing challenges that still exist to spur future research. In addition, we provide statistics …
prevailing challenges that still exist to spur future research. In addition, we provide statistics …
Hat5: Hate language identification using text-to-text transfer transformer
We investigate the performance of a state-of-the-art (SoTA) architecture T5 (available on the
SuperGLUE) and compare it with 3 other previous SoTA architectures across 5 different …
SuperGLUE) and compare it with 3 other previous SoTA architectures across 5 different …
Sm {\aa} prat: Dialogpt for natural language generation of swedish dialogue by transfer learning
Building open-domain conversational systems (or chatbots) that produce convincing
responses is a recognized challenge. Recent state-of-the-art (SoTA) transformer-based …
responses is a recognized challenge. Recent state-of-the-art (SoTA) transformer-based …
Understanding the role of objectivity in machine learning and research evaluation
This article makes the case for more objectivity in Machine Learning (ML) research. Any
research work that claims to hold benefits has to be scrutinized based on many parameters …
research work that claims to hold benefits has to be scrutinized based on many parameters …
[HTML][HTML] Bipol: A novel multi-axes bias evaluation metric with explainability for NLP
We introduce bipol, a new metric with explainability, for estimating social bias in text data.
Harmful bias is prevalent in many online sources of data that are used for training machine …
Harmful bias is prevalent in many online sources of data that are used for training machine …
Potential idiomatic expression (PIE)-english: Corpus for classes of idioms
TP Adewumi, R Vadoodi, A Tripathy… - arXiv preprint arXiv …, 2021 - arxiv.org
We present a fairly large, Potential Idiomatic Expression (PIE) dataset for Natural Language
Processing (NLP) in English. The challenges with NLP systems with regards to tasks such …
Processing (NLP) in English. The challenges with NLP systems with regards to tasks such …
Word2vec: Optimal hyper-parameters and their impact on nlp downstream tasks
Word2Vec is a prominent model for natural language processing (NLP) tasks. Similar
inspiration is found in distributed embeddings for new state-of-the-art (SotA) deep neural …
inspiration is found in distributed embeddings for new state-of-the-art (SotA) deep neural …
AfriWOZ: Corpus for Exploiting Cross-Lingual Transfer for Dialogue Generation in Low-Resource, African Languages
T Adewumi, M Adeyemi, A Anuoluwapo… - … Joint Conference on …, 2023 - ieeexplore.ieee.org
Dialogue generation is an important NLP task fraught with many challenges. The challenges
become more daunting for low-resource African languages. To enable the creation of …
become more daunting for low-resource African languages. To enable the creation of …
AfriWOZ: Corpus for Exploiting Cross-Lingual Transferability for Generation of Dialogues in Low-Resource, African Languages
T Adewumi, M Adeyemi, A Anuoluwapo… - arXiv preprint arXiv …, 2022 - arxiv.org
Dialogue generation is an important NLP task fraught with many challenges. The challenges
become more daunting for low-resource African languages. To enable the creation of …
become more daunting for low-resource African languages. To enable the creation of …