Gholamreza Haffari

Gholamreza Haffari

Auto-generated profile, based on publicly available information

Gholamreza Haffari

Monash University

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
8 June 2023 in Artificial Intelligence in Medicine
Verified
Journal Article
Closed access
ZLZhihong Lin
Zhihong Lin
DZDonghao Zhang
Donghao Zhang
QTQingyi Tao
Qingyi Tao
DSDanli Shi
Danli Shi
GHGholamreza Haffari
Gholamreza Haffari
ZGZongyuan Ge
Zongyuan Ge

10 February 2025 in ACM Computing Surveys
Verified
Journal Article
Open access
AJAditya Joshi
Aditya Joshi
RDRaj Dabre
Raj Dabre
DKDiptesh Kanojia
Diptesh Kanojia
ZLZhuang Li
Zhuang Li
HZHaolan Zhan
Haolan Zhan
DDDoris Dippold
Doris Dippold
State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a language. Motivated by the performance degradation of NLP models for dialectal datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches. We describe a wide range of NLP tasks in terms of two categories: natural language understanding (NLU) (for tasks such as dialect classification, sentiment analysis, parsing, and NLU benchmarks) and natural language generation (NLG) (for summarisation, machine translation, and dialogue systems). The survey is also broad in its coverage of languages which include English, Arabic, German, among others. We observe that past work in NLP concerning dialects goes deeper than mere dialect classification, and extends to several NLU and NLG tasks. For these tasks, we describe classical machine learning using statistical models, along with the recent deep learning-based approaches based on pre-trained language models. We expect that this survey will be useful to NLP researchers interested in building equitable language technologies by rethinking LLM benchmarks and model architectures.

12 August 2022 in Transactions of the Association for Computational Linguistics
Verified
Journal Article
Open access
PDF file
XHXuanli He
Xuanli He
INIslam Nassar
Islam Nassar
JKJamie Kiros
Jamie Kiros
GHGholamreza Haffari
Gholamreza Haffari
MNMohammad Norouzi
Mohammad Norouzi
This paper studies the use of language models as a source of synthetic unlabeled text for NLP. We formulate a general framework called “generate, annotate, and learn (GAL)” to take advantage of synthetic text within knowledge distillation, self-training, and few-shot learning applications. To generate high-quality task-specific text, we either fine-tune LMs on inputs from the task of interest, or prompt large LMs with few examples. We use the best available classifier to annotate synthetic text with soft pseudo labels for knowledge distillation and self-training, and use LMs to obtain hard labels for few-shot learning. We train new supervised models on the combination of labeled and pseudo-labeled data, which results in significant gains across several applications. We investigate key components of GAL and present theoretical and empirical arguments against the use of class-conditional LMs to generate synthetic labeled text instead of unlabeled text. GAL achieves new state-of-the-art knowledge distillation results for 6-layer transformers on the GLUE leaderboard.

18 June 2025
Verified
Book Chapter
Closed access
PDF file
LLLinhao Luo
Linhao Luo
JJJiaxin Ju
Jiaxin Ju
BXBo Xiong
Bo Xiong
YLYuan-Fang Li
Yuan-Fang Li
GHGholamreza Haffari
Gholamreza Haffari
SPShirui Pan
Shirui Pan

18 July 2023
Verified
Conference Paper
Open access
LLLinhao Luo
Linhao Luo
YLYuan-Fang Li
Yuan-Fang Li
GHGholamreza Haffari
Gholamreza Haffari
SPShirui Pan
Shirui Pan
Knowledge graphs (KGs), as a structured form of knowledge representation, have been widely applied in the real world. Recently, few-shot knowledge graph completion (FKGC), which aims to predict missing facts for unseen relations with few-shot associated facts, has attracted increasing attention from practitioners and researchers. However, existing FKGC methods are based on metric learning or meta-learning, which often suffer from the out-of-distribution and overfitting problems. Meanwhile, they are incompetent at estimating uncertainties in predictions, which is critically important as model predictions could be very unreliable in few-shot settings. Furthermore, most of them cannot handle complex relations and ignore path information in KGs, which largely limits their performance. In this paper, we propose a normalizing flow-based neural process for few-shot knowledge graph completion (NP-FKGC). Specifically, we unify normalizing flows and neural processes to model a complex distribution of KG completion functions. This offers a novel way to predict facts for few-shot relations while estimating the uncertainty. Then, we propose a stochastic ManifoldE decoder to incorporate the neural process and handle complex relations in few-shot settings. To further improve performance, we introduce an attentive relation path-based graph neural network to capture path information in KGs. Extensive experiments on three public datasets demonstrate that our method significantly outperforms the existing FKGC methods and achieves state-of-the-art performance. Code is available at https://github.com/RManLuo/NP-FKGC.git.

18 July 2023
Verified
Conference Paper
Open access
HZHaolan Zhan
Haolan Zhan
ZLZhuang Li
Zhuang Li
YWYufei Wang
Yufei Wang
LLLinhao Luo
Linhao Luo
TFTao Feng
Tao Feng
GHGholamreza Haffari
Gholamreza Haffari
Content Warning: this paper may contain content that is offensive or upsetting. Dialogue systems have been widely applied in many scenarios and are now more powerful and ubiquitous than ever before. With large neural models and massive available data, current dialogue systems have access to more knowledge than any people in their life. However, current dialogue systems still do not perform at a human level. One major gap between conversational agents and humans lies in their abilities to be aware of social norms. The development of socially-aware dialogue systems is impeded due to the lack of resources. In this paper, we present the first socially-aware dialogue corpus -- SocialDial based on Chinese social culture. SocialDial consists of two parts: 1,563 multi-turn dialogues between two human speakers with fine-grained labels, and 4,870 synthetic conversations generated by ChatGPT. The human corpus covers five categories of social norms, which have 14 sub-categories in total. Specifically, it contains social factor annotations including social relation, context, social distance, and social norms. However, collecting sufficient socially-aware dialogues is costly. Thus, we harness the power of ChatGPT and devise an ontology-based synthetic data generation framework. This framework is able to generate synthetic data at scale. To ensure the quality of synthetic dialogues, we design several mechanisms for quality control during data collection. Finally, we evaluate our dataset using several pre-trained models, such as BERT and RoBERTa. Comprehensive empirical results based on state-of-the-art neural models demonstrate that modeling of social norms for dialogue systems is a promising research direction. To the best of our knowledge, SocialDial is the first socially-aware dialogue dataset that covers multiple social factors and has fine-grained labels.