Democratizing access to natural language processing (NLP) technology is
...
Transformer-based language models have achieved remarkable success in
fe...
This evidence-based position paper critiques current research practices
...
Real-life multilingual systems should be able to efficiently incorporate...
Figurative language permeates human communication, but at the same time ...
Despite the major advances in NLP, significant disparities in NLP system...
While code-mixing is a common linguistic practice in many parts of the w...
Code-Switching, a common phenomenon in written text and conversation, ha...
We present NusaCrowd, a collaborative initiative to collect and unite
ex...
The BLOOM model is a large open-source multilingual language model capab...
Recent development in angle-resolved photoemission spectroscopy (ARPES)
...
At the center of the underlying issues that halt Indonesian natural lang...
Natural language processing (NLP) has a significant impact on society vi...
NLP research is impeded by a lack of resources and awareness of the
chal...
The recent development of language models has shown promising results by...
Code-switching is a speech phenomenon when a speaker switches language d...
Learning to converse using only a few examples is a great challenge in
c...
General-purpose language models have demonstrated impressive capabilitie...
While the recent advances in deep neural networks (DNN) bring remarkable...
Task-oriented compositional semantic parsing (TCSP) handles complex nest...
Information-seeking dialogue systems, including knowledge identification...
Task-oriented dialogue (ToD) benchmarks provide an important avenue to
m...
Over the past year, research in various domains, including Natural Langu...
The current pandemic has forced people globally to remain in isolation a...
To diversify and enrich generated dialogue responses, knowledge-grounded...
The data scarcity in low-resource languages has become a bottleneck to
b...
A benchmark provides an ecosystem to measure the advancement of models w...
In this thesis, we address the data scarcity and limitations of linguist...
Multilingual language models have shown decent performance in multilingu...
One crucial challenge of real-world multilingual speech recognition is t...
Despite the promising results of current cross-lingual models for spoken...
Task-oriented dialogue systems are either modularized with separate dial...
In this paper, we propose Minimalist Transfer Learning (MinTL) to simpli...
Although Indonesian is known to be the fourth most frequently used langu...
Most emotion recognition methods tackle the emotion understanding task b...
An increasing number of people in the world today speak a mixed-language...
Recently, fine-tuning pre-trained cross-lingual models (e.g., multilingu...
As an essential task in task-oriented dialog systems, slot filling requi...
Despite the great promise of Transformers in many sequence modeling task...
Personalized dialogue systems are an essential step toward better
human-...
Local dialects influence people to pronounce words of the same language
...
Existing models for cross-domain named entity recognition (NER) rely on
...
Recently, data-driven task-oriented dialogue systems have achieved promi...
Despite the surging demands for multilingual task-oriented dialog system...
High performing deep neural networks come at the cost of computational
c...
Training code-switched language models is difficult due to lack of data ...
In countries that speak multiple main languages, mixing up different
lan...
Despite their ubiquity in NLP tasks, Long Short-Term Memory (LSTM) netwo...
This paper describes CAiRE's submission to the unsupervised machine
tran...
In this paper, we present an end-to-end empathetic conversation agent CA...