Search Results for author: Ayu Purwarianti

Found 29 papers, 14 papers with code

What Linguistic Features and Languages are Important in LLM Translation?

no code implementations21 Feb 2024 Ryandito Diandaru, Lucky Susanto, Zilu Tang, Ayu Purwarianti, Derry Wijaya

Large Language Models (LLMs) demonstrate strong capability across multiple tasks, including machine translation.

Machine Translation Translation

The Obscure Limitation of Modular Multilingual Language Models

no code implementations21 Nov 2023 Muhammad Farid Adilazuarda, Samuel Cahyawijaya, Ayu Purwarianti

We expose the limitation of modular multilingual language models (MLMs) in multilingual inference scenarios with unknown languages.

Language Identification

Indo LEGO-ABSA: A Multitask Generative Aspect Based Sentiment Analysis for Indonesian Language

1 code implementation3 Nov 2023 Randy Zakya Suchrady, Ayu Purwarianti

Therefore, this research aims to implement the multitask learning and prompting approach in aspect-based sentiment analysis for Bahasa Indonesia using generative pre-trained language models.

Aspect-Based Sentiment Analysis Aspect Sentiment Triplet Extraction +2

Replicable Benchmarking of Neural Machine Translation (NMT) on Low-Resource Local Languages in Indonesia

1 code implementation2 Nov 2023 Lucky Susanto, Ryandito Diandaru, Adila Krisnadhi, Ayu Purwarianti, Derry Wijaya

Neural machine translation (NMT) for low-resource local languages in Indonesia faces significant challenges, including the need for a representative benchmark and limited data availability.

Benchmarking Machine Translation +2

Domain-Specific Language Model Post-Training for Indonesian Financial NLP

1 code implementation15 Oct 2023 Ni Putu Intan Maharani, Yoga Yustiawan, Fauzy Caesar Rochim, Ayu Purwarianti

In this paper, we construct an Indonesian self-supervised financial corpus, Indonesian financial sentiment analysis dataset, Indonesian financial topic classification dataset, and release a family of BERT models for financial NLP.

Language Modelling Sentiment Analysis +1

Low-Resource Clickbait Spoiling for Indonesian via Question Answering

no code implementations12 Oct 2023 Ni Putu Intan Maharani, Ayu Purwarianti, Alham Fikri Aji

Clickbait spoiling aims to generate a short text to satisfy the curiosity induced by a clickbait post.

Question Answering

QASiNa: Religious Domain Question Answering using Sirah Nabawiyah

1 code implementation12 Oct 2023 Muhammad Razif Rizqullah, Ayu Purwarianti, Alham Fikri Aji

This concludes Chat GPT is unsuitable for question answering task in religious domain especially for Islamic religion.

Large Language Model Question Answering +1

Sequential Labelling and DNABERT For Splice Site Prediction in Homo Sapiens DNA

1 code implementation15 Dec 2022 Muhammad Anwari Leksono, Ayu Purwarianti

Recent predictions are carried out with models trained on sequence with fixed splice site location which eliminates possibility of multiple splice sites existence in single sequence.

Splice Site Prediction

Speech Artifact Removal from EEG Recordings of Spoken Word Production with Tensor Decomposition

no code implementations1 Jun 2022 Holy Lovenia, Hiroki Tanaka, Sakriani Sakti, Ayu Purwarianti, Satoshi Nakamura

Research about brain activities involving spoken word production is considerably underdeveloped because of the undiscovered characteristics of speech artifacts, which contaminate electroencephalogram (EEG) signals and prevent the inspection of the underlying cognitive processes.

blind source separation EEG +2

A Comparative Study on Language Models for Task-Oriented Dialogue Systems

1 code implementation21 Jan 2022 Vinsen Marselino Andreas, Genta Indra Winata, Ayu Purwarianti

The recent development of language models has shown promising results by achieving state-of-the-art performance on various natural language tasks by fine-tuning pretrained models.

Dialogue State Tracking Hallucination +2

Sequence-to-Sequence Learning for Indonesian Automatic Question Generator

1 code implementation29 Sep 2020 Ferdiant Joshua Muis, Ayu Purwarianti

Research in automatic question generator (AQG) has been conducted for more than 10 years, mainly focused on factoid question.

Question Answering Question Generation +1

Improving Joint Layer RNN based Keyphrase Extraction by Using Syntactical Features

no code implementations15 Sep 2020 Miftahul Mahfuzh, Sidik Soleman, Ayu Purwarianti

Since JRNN in general requires a large amount of data as the training examples and creating those examples is expensive, we used a data augmentation method to increase the number of training examples.

Data Augmentation Keyphrase Extraction

Combining Word and Character Vector Representation on Neural Machine Translation

no code implementations13 Sep 2020 K. M. Shahih, Ayu Purwarianti

This paper describes combinations of word vector representation and character vector representation in English-Indonesian neural machine translation (NMT).

Machine Translation NMT +1

Relation Detection for Indonesian Language using Deep Neural Network -- Support Vector Machine

no code implementations12 Sep 2020 Ramos Janoah Hasudungan, Ayu Purwarianti

In this paper, we employ neural network to do relation detection between two named entities for Indonesian Language.

POS Position +2

Improving Indonesian Text Classification Using Multilingual Language Model

1 code implementation12 Sep 2020 Ilham Firdausi Putra, Ayu Purwarianti

Using the feature-based approach, we observe its performance on various data sizes and total added English data.

General Classification Language Modelling +3

Improving Bi-LSTM Performance for Indonesian Sentiment Analysis Using Paragraph Vector

no code implementations12 Sep 2020 Ayu Purwarianti, Ida Ayu Putu Ari Crisdayanti

Meanwhile, in the problem scope of Indonesian sentiment analysis, phrases that express the sentiment of a document might not appear in the first or last part of the document that can lead to incorrect sentiment classification.

Sentiment Analysis Sentiment Classification

Coreference Resolution System for Indonesian Text with Mention Pair Method and Singleton Exclusion using Convolutional Neural Network

1 code implementation11 Sep 2020 Turfa Auliarachman, Ayu Purwarianti

In this paper, we propose a new coreference resolution system for Indonesian text with mention pair method that uses deep neural network to learn the relations of the two mentions.

coreference-resolution Word Embeddings

Cannot find the paper you are looking for? You can Submit a new open access paper.