Search Results for author:
Found 71 papers, 39 papers with code
Clozer”:" Adaptable Data Augmentation for Cloze-style Reading Comprehension
Task-adaptive pre-training (TAPT) alleviates the lack of labelled data and provides performance lift by adapting unlabelled data to downstream task.
CI-AVSR: A Cantonese Audio-Visual Speech Datasetfor In-car Command Recognition
With the rise of deep learning and intelligent vehicles, the smart assistant has become an essential in-car component to facilitate driving and provide extra functionalities.
Integrating Question Rewrites in Conversational Question Answering: A Reinforcement Learning Approach
Resolving dependencies among dialogue history is one of the main obstacles in the research on conversational question answering (QA).
Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sense
In this paper, we demonstrate using false friends -- words that are orthographically similar but have completely different meanings in two languages -- as a possible approach to pinpoint the limitation of cross-lingual sense disambiguation in LLMs.
WorldCuisines: A Massive-Scale Benchmark for Multilingual and Multicultural Visual Question Answering on Global Cuisines
This benchmark includes a visual question answering (VQA) dataset with text-image pairs across 30 languages and dialects, spanning 9 language families and featuring over 1 million data points, making it the largest multicultural VQA benchmark to date.
Towards Efficient and Robust VQA-NLE Data Generation with Large Vision-Language Models
Natural Language Explanation (NLE) aims to elucidate the decision-making process by providing detailed, human-friendly explanations in natural language.
LLM for Everyone: Representing the Underrepresented in Large Language Models
A comprehensive evaluation of LLMs is conducted to assess their capabilities in these languages, revealing the challenges of multilingual and multicultural generalization.
Linguistic Minimal Pairs Elicit Linguistic Similarity in Large Language Models
Our large-scale experiments, spanning 100+ LLMs and 150k minimal pairs in three languages, reveal properties of linguistic similarity from four key aspects: consistency across LLMs, relation to theoretical categorizations, dependency to semantic context, and cross-lingual alignment of relevant phenomena.
LLM Internal States Reveal Hallucination Risk Faced With a Query
The hallucination problem of Large Language Models (LLMs) significantly limits their reliability and trustworthiness.
Belief Revision: The Adaptability of Large Language Models Reasoning
We evaluate $\sim$30 LMs across diverse prompting strategies and found that LMs generally struggle to appropriately revise their beliefs in response to new information.
SEACrowd: A Multilingual Multimodal Data Hub and Benchmark Suite for Southeast Asian Languages
Southeast Asia (SEA) is a region rich in linguistic diversity and cultural variety, with over 1, 300 indigenous languages and a population of 671 million people.
CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark
Visual Question Answering (VQA) is an important task in multimodal AI, and it is often used to test the ability of vision-language models to understand and reason on knowledge present in both visual and textual data.
What Makes for Good Image Captions?
This paper establishes a formal information-theoretic framework for image captioning, conceptualizing captions as compressed linguistic representations that selectively encode semantic units in images.
High-Dimension Human Value Representation in Large Language Models
there is an urgent need to understand the scope and nature of human values injected into these models before their release.
Cendol: Open Instruction-tuned Generative Large Language Models for Indonesian Languages
To bridge this quality gap, we introduce Cendol, a collection of Indonesian LLMs encompassing both decoder-only and encoder-decoder architectures across a range of model sizes.
LLMs Are Few-Shot In-Context Low-Resource Language Learners
Our study concludes the significance of few-shot in-context information on enhancing the low-resource understanding quality of LLMs through semantically relevant information by closing the language gap in the target language and aligning the semantics between the targeted low-resource and the high-resource language that the model is proficient in.
Subobject-level Image Tokenization
Transformer-based vision models typically tokenize images into fixed-size square patches as input units, which lacks the adaptability to image content and overlooks the inherent pixel grouping structure.
LinguAlchemy: Fusing Typological and Geographical Elements for Unseen Language Generalization
Pretrained language models (PLMs) have become remarkably adept at task and language generalization.
IndoRobusta: Towards Robustness Against Diverse Code-Mixed Indonesian Local Languages
Significant progress has been made on Indonesian NLP.
The Obscure Limitation of Modular Multilingual Language Models
We expose the limitation of modular multilingual language models (MLMs) in multilingual inference scenarios with unknown languages.
IndoToD: A Multi-Domain Indonesian Benchmark For End-to-End Task-Oriented Dialogue Systems
Task-oriented dialogue (ToD) systems have been mostly created for high-resource languages, such as English and Chinese.
InstructTODS: Large Language Models for End-to-End Task-Oriented Dialogue Systems
We present InstructTODS, a novel off-the-shelf framework for zero-shot end-to-end task-oriented dialogue systems that can adapt to diverse domains without fine-tuning.
Negative Object Presence Evaluation (NOPE) to Measure Object Hallucination in Vision-Language Models
Object hallucination poses a significant challenge in vision-language (VL) models, often leading to the generation of nonsensical or unfaithful responses with non-existent objects.
Survey of Social Bias in Vision-Language Models
This survey aims to provide researchers with a high-level insight into the similarities and differences of social bias studies in pre-trained models across NLP, CV, and VL.
PICK: Polished & Informed Candidate Scoring for Knowledge-Grounded Dialogue Systems
Grounding dialogue response generation on external knowledge is proposed to produce informative and engaging responses.
NusaWrites: Constructing High-Quality Corpora for Underrepresented and Extremely Low-Resource Languages
We compare the effectiveness of online scraping, human translation, and paragraph writing by native speakers in constructing datasets.
Cross-Lingual Cross-Age Group Adaptation for Low-Resource Elderly Speech Emotion Recognition
In this work, we analyze the transferability of emotion recognition across three different languages--English, Mandarin Chinese, and Cantonese; and 2 different age groups--adults and the elderly.
Multi-lingual and Multi-cultural Figurative Language Understanding
Figurative language permeates human communication, but at the same time is relatively understudied in NLP.
GlobalBench: A Benchmark for Global Progress in Natural Language Processing
Despite the major advances in NLP, significant disparities in NLP system performance across languages still exist.
Multilingual Large Language Models Are Not (Yet) Code-Switchers
Multilingual Large Language Models (LLMs) have recently shown great capabilities in a wide range of tasks, exhibiting state-of-the-art performance through zero-shot or few-shot prompting methods.
InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning
Our results demonstrate the effectiveness of InstructAlign in enabling the model to understand low-resource languages with limited parallel data while preventing catastrophic forgetting.
Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages
While code-mixing is a common linguistic practice in many parts of the world, collecting high-quality and low-cost code-mixed data remains a challenge for natural language processing (NLP) research.
Which One Are You Referring To? Multimodal Object Identification in Situated Dialogue
The demand for multimodal dialogue systems has been rising in various domains, emphasizing the importance of interpreting multimodal inputs from conversational and situational contexts.
A Multitask, Multilingual, Multimodal Evaluation of ChatGPT on Reasoning, Hallucination, and Interactivity
It is, for example, better at deductive than inductive reasoning.
Biomedical Image Reconstruction: A Survey
Biomedical image reconstruction research has been developed for more than five decades, giving rise to various techniques such as central and filtered back projection.
NusaCrowd: Open Source Initiative for Indonesian NLP Resources
We present NusaCrowd, a collaborative initiative to collect and unify existing resources for Indonesian languages, including opening access to previously non-public resources.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
BLOOM: A 176B-Parameter Open-Access Multilingual Language Model
Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions.
How Long Is Enough? Exploring the Optimal Intervals of Long-Range Clinical Note Language Modeling
Large pre-trained language models (LMs) have been widely adopted in biomedical and clinical domains, introducing many powerful LMs such as bio-lm and BioELECTRA.
Every picture tells a story: Image-grounded controllable stylistic story generation
Generating a short story out of an image is arduous.
NusaCrowd: A Call for Open and Reproducible NLP Research in Indonesian Languages
At the center of the underlying issues that halt Indonesian natural language processing (NLP) research advancement, we find data scarcity.
Kaggle Competition: Cantonese Audio-Visual Speech Recognition for In-car Commands
With the rise of deep learning and intelligent vehicles, the smart assistant has become an essential in-car component to facilitate driving and provide extra functionalities.
BigBIO: A Framework for Data-Centric Biomedical Natural Language Processing
Training and evaluating language models increasingly requires the construction of meta-datasets --diverse collections of curated data with clear provenance.
GEMv2: Multilingual NLG Benchmarking in a Single Line of Code
This problem is especially pertinent in natural language generation which requires ever-improving suites of datasets, metrics, and human evaluation to make definitive claims.
NusaX: Multilingual Parallel Sentiment Dataset for 10 Indonesian Local Languages
In this work, we focus on developing resources for languages in Indonesia.
Towards Answering Open-ended Ethical Quandary Questions
We explore the current capability of LLMs in providing an answer with a deliberative exchange of different perspectives to an ethical quandary, in the approach of Socratic philosophy, instead of providing a closed answer like an oracle.
SNP2Vec: Scalable Self-Supervised Pre-Training for Genome-Wide Association Study
We apply SNP2Vec to perform long-sequence genomics modeling, and we evaluate the effectiveness of our approach on predicting Alzheimer's disease risk in a Chinese cohort.
Can Question Rewriting Help Conversational Question Answering?
Question rewriting (QR) is a subtask of conversational question answering (CQA) aiming to ease the challenges of understanding dependencies among dialogue history by reformulating questions in a self-contained form.
Clozer: Adaptable Data Augmentation for Cloze-style Reading Comprehension
Task-adaptive pre-training (TAPT) alleviates the lack of labelled data and provides performance lift by adapting unlabelled data to downstream task.
One Country, 700+ Languages: NLP Challenges for Underrepresented Languages and Dialects in Indonesia
NLP research is impeded by a lack of resources and awareness of the challenges presented by underrepresented languages and dialects.
VScript: Controllable Script Generation with Visual Presentation
In order to offer a customized script tool and inspire professional scriptwriters, we present VScript.
CI-AVSR: A Cantonese Audio-Visual Speech Dataset for In-car Command Recognition
With the rise of deep learning and intelligent vehicle, the smart assistant has become an essential in-car component to facilitate driving and provide extra functionalities.
Automatic Speech Recognition Datasets in Cantonese: A Survey and New Dataset
We further conduct experiments with Fairseq S2T Transformer, a state-of-the-art ASR model, on the biggest existing dataset, Common Voice zh-HK, and our proposed MDCC, and the results show the effectiveness of our dataset.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
ASCEND: A Spontaneous Chinese-English Dataset for Code-switching in Multi-turn Conversation
ASCEND (A Spontaneous Chinese-English Dataset) is a high-quality Mandarin Chinese-English code-switching corpus built on spontaneous multi-turn conversational dialogue sources collected in Hong Kong.
NL-Augmenter: A Framework for Task-Sensitive Natural Language Augmentation
Data augmentation is an important component in the robustness evaluation of models in natural language processing (NLP) and in enhancing the diversity of the data they are trained on.
Greenformer: Factorization Toolkit for Efficient Deep Neural Networks
While the recent advances in deep neural networks (DNN) bring remarkable success, the computational cost also increases considerably.
Greenformers: Improving Computation and Memory Efficiency in Transformer Models via Low-Rank Approximation
We also show that Low-Rank Transformer is more suitable for on-device deployment, as it significantly reduces the model size.
ERICA: An Empathetic Android Companion for Covid-19 Quarantine
Over the past year, research in various domains, including Natural Language Processing (NLP), has been accelerated to fight against the COVID-19 pandemic, yet such research has just started on dialogue systems.
Retrieval-Free Knowledge-Grounded Dialogue Response Generation with Adapters
This paper proposes KnowExpert, a framework to bypass the explicit retrieval process and inject knowledge into the pre-trained language models with lightweight adapters and adapt to the knowledge-grounded dialogue task.
Weakly-supervised Multi-task Learning for Multimodal Affect Recognition
In this paper, we propose to leverage these datasets using weakly-supervised multi-task learning to improve the generalization performance on each of them.
IndoNLG: Benchmark and Resources for Evaluating Indonesian Natural Language Generation
Natural language generation (NLG) benchmarks provide an important avenue to measure progress and develop better NLG systems.
Are Multilingual Models Effective in Code-Switching?
Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks.
Multimodal End-to-End Sparse Model for Emotion Recognition
Existing works on multimodal affective computing tasks, such as emotion recognition, generally adopt a two-phase pipeline, first extracting feature representations for each single modality with hand-crafted algorithms and then performing end-to-end learning with the extracted features.
Model Generalization on COVID-19 Fake News Detection
Amid the pandemic COVID-19, the world is facing unprecedented infodemic with the proliferation of both fake and real information.
CrossNER: Evaluating Cross-Domain Named Entity Recognition
Cross-domain named entity recognition (NER) models are able to cope with the scarcity issue of NER samples in target domains.
Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems
In this paper, we propose a method to embed the KB, of any size, directly into the model parameters.
IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding
Although Indonesian is known to be the fourth most frequently used language over the internet, the research progress on this language in the natural language processing (NLP) is slow-moving due to a lack of available resources.
Meta-Transfer Learning for Code-Switched Speech Recognition
An increasing number of people in the world today speak a mixed-language as a result of being multilingual.
XPersona: Evaluating Multilingual Personalized Chatbot
Experimental results show that the multilingual trained models outperform the translation-pipeline and that they are on par with the monolingual models, with the advantage of having a single model across multiple languages.
Learning Fast Adaptation on Cross-Accented Speech Recognition
The great variability and complex characteristics of accents creates a major challenge for training a robust and accent-agnostic automatic speech recognition (ASR) system.
Audio and Speech Processing Sound
On the Importance of Word Order Information in Cross-lingual Sequence Labeling
To verify this hypothesis, we investigate whether making models insensitive to the word order of the source language can improve the adaptation performance in target languages.
Lightweight and Efficient End-to-End Speech Recognition Using Low-Rank Transformer
Highly performing deep neural networks come at the cost of computational complexity that limits their practicality for deployment on portable devices.
