Search Results for author: Gholamreza Haffari

Found 165 papers, 57 papers with code

Document Level Hierarchical Transformer

no code implementations ALTA 2021 Najam Zaidi, Trevor Cohn, Gholamreza Haffari

In this paper, we present a novel semi-autoregressive document generation model capable of revising and editing the generated text.

Document Level Machine Translation Imitation Learning +3

Lifelong Explainer for Lifelong Learners

1 code implementation EMNLP 2021 Xuelin Situ, Sameen Maruf, Ingrid Zukerman, Cecile Paris, Gholamreza Haffari

Our ablation study shows that the ER mechanism in our LLE approach enhances the learning capabilities of the student explainer.

text-classification Text Classification

Multilingual Neural Machine Translation: Can Linguistic Hierarchies Help?

no code implementations Findings (EMNLP) 2021 Fahimeh Saleh, Wray Buntine, Gholamreza Haffari, Lan Du

Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages.

Knowledge Distillation Machine Translation +2

Explaining Decision-Tree Predictions by Addressing Potential Conflicts between Predictions and Plausible Expectations

no code implementations INLG (ACL) 2021 Sameen Maruf, Ingrid Zukerman, Ehud Reiter, Gholamreza Haffari

We offer an approach to explain Decision Tree (DT) predictions by addressing potential conflicts between aspects of these predictions and plausible expectations licensed by background information.

Personal Information Leakage Detection in Conversations

1 code implementation EMNLP 2020 Qiongkai Xu, Lizhen Qu, Zeyu Gao, Gholamreza Haffari

In this work, we propose to protect personal information by warning users of detected suspicious sentences generated by conversational assistants.

Language Modelling

CausalScore: An Automatic Reference-Free Metric for Assessing Response Relevance in Open-Domain Dialogue Systems

no code implementations25 Jun 2024 Tao Feng, Lizhen Qu, Xiaoxi Kang, Gholamreza Haffari

Automatically evaluating the quality of responses in open-domain dialogue systems is a challenging but crucial task.

Towards Probing Speech-Specific Risks in Large Multimodal Models: A Taxonomy, Benchmark, and Insights

no code implementations25 Jun 2024 Hao Yang, Lizhen Qu, Ehsan Shareghi, Gholamreza Haffari

Based on the taxonomy, we create a small-scale dataset for evaluating current LMMs capability in detecting these categories of risk.

Causal Discovery Inspired Unsupervised Domain Adaptation for Emotion-Cause Pair Extraction

no code implementations18 Jun 2024 Yuncheng Hua, Yujin Huang, Shuo Huang, Tao Feng, Lizhen Qu, Chris Bain, Richard Bassed, Gholamreza Haffari

Inspired by causal discovery, we propose a novel deep latent model in the variational autoencoder (VAE) framework, which not only captures the underlying latent structures of data but also utilizes the easily transferable knowledge of emotions as the bridge to link the distributions of events in different domains.

Causal Discovery Emotion-Cause Pair Extraction +2

Exploring the Potential of Multimodal LLM with Knowledge-Intensive Multimodal ASR

no code implementations16 Jun 2024 Minghan Wang, Yuxia Wang, Thuy-Trang Vu, Ehsan Shareghi, Gholamreza Haffari

Recent advancements in multimodal large language models (MLLMs) have made significant progress in integrating information across various modalities, yet real-world applications in educational and scientific domains remain challenging.

SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking

1 code implementation16 Jun 2024 Zhuang Li, Yuncheng Hua, Thuy-Trang Vu, Haolan Zhan, Lizhen Qu, Gholamreza Haffari

Recent studies have shown that maintaining a consistent response style by human experts and enhancing data quality in training sets can significantly improve the performance of fine-tuned Large Language Models (LLMs) while reducing the number of training examples needed.

Open-Ended Question Answering

Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models

no code implementations13 Jun 2024 Minghao Wu, Thuy-Trang Vu, Lizhen Qu, Gholamreza Haffari

In this work, we propose a general, model-agnostic, reinforcement learning framework, Mixture-of-Skills (MoS), that learns to optimize data usage automatically during the fine-tuning process.

VersiCode: Towards Version-controllable Code Generation

1 code implementation11 Jun 2024 Tongtong Wu, Weigang Wu, Xingyu Wang, Kang Xu, Suyu Ma, Bo Jiang, Ping Yang, Zhenchang Xing, Yuan-Fang Li, Gholamreza Haffari

In this paper, we introduce VersiCode, the first comprehensive dataset designed to assess the ability of large language models to generate verifiable code for specific library versions.

Code Completion Code Generation +2

NAP^2: A Benchmark for Naturalness and Privacy-Preserving Text Rewriting by Learning from Human

no code implementations6 Jun 2024 Shuo Huang, William MacLean, Xiaoxi Kang, Anqi Wu, Lizhen Qu, Qiongkai Xu, Zhuang Li, Xingliang Yuan, Gholamreza Haffari

Increasing concerns about privacy leakage issues in academia and industry arise when employing NLP models from third-party providers to process sensitive texts.

Privacy Preserving

Decompose, Enrich, and Extract! Schema-aware Event Extraction using LLMs

no code implementations3 Jun 2024 Fatemeh Shiri, Van Nguyen, Farhad Moghimifar, John Yoo, Gholamreza Haffari, Yuan-Fang Li

Large Language Models (LLMs) demonstrate significant capabilities in processing natural language data, promising efficient knowledge extraction from diverse textual sources to enhance situational awareness and support decision-making.

Decision Making Event Argument Extraction +4

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models

no code implementations23 May 2024 Akide Liu, Jing Liu, Zizheng Pan, Yefei He, Gholamreza Haffari, Bohan Zhuang

In this paper, we present a simple yet effective approach, called MiniCache, to compress the KV cache across layers from a novel depth perspective, significantly reducing the memory footprint for LLM inference.

Quantization

Double Mixture: Towards Continual Event Detection from Speech

1 code implementation20 Apr 2024 Jingqi Kang, Tongtong Wu, Jinming Zhao, Guitao Wang, Yinwei Wei, Hao Yang, Guilin Qi, Yuan-Fang Li, Gholamreza Haffari

To address the challenges of catastrophic forgetting and effective disentanglement, we propose a novel method, 'Double Mixture.'

Continual Learning Disentanglement +1

Modelling Political Coalition Negotiations Using LLM-based Agents

no code implementations18 Feb 2024 Farhad Moghimifar, Yuan-Fang Li, Robert Thomson, Gholamreza Haffari

Coalition negotiations are a cornerstone of parliamentary democracies, characterised by complex interactions and strategic communications among political parties.

Language Modelling Large Language Model

Direct Evaluation of Chain-of-Thought in Multi-hop Reasoning with Knowledge Graphs

1 code implementation17 Feb 2024 Minh-Vuong Nguyen, Linhao Luo, Fatemeh Shiri, Dinh Phung, Yuan-Fang Li, Thuy-Trang Vu, Gholamreza Haffari

Large language models (LLMs) demonstrate strong reasoning abilities when prompted to generate chain-of-thought (CoT) explanations alongside answers.

Knowledge Graphs Multi-hop Question Answering +1

RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversations

no code implementations17 Feb 2024 Haolan Zhan, Zhuang Li, Xiaoxi Kang, Tao Feng, Yuncheng Hua, Lizhen Qu, Yi Ying, Mei Rianto Chandra, Kelly Rosalin, Jureynolds Jureynolds, Suraj Sharma, Shilin Qu, Linhao Luo, Lay-Ki Soon, Zhaleh Semnani Azad, Ingrid Zukerman, Gholamreza Haffari

While collecting sufficient human-authored data is costly, synthetic conversations provide suitable amounts of data to help mitigate the scarcity of training data, as well as the chance to assess the alignment between LLMs and humans in the awareness of social norms.

Improving Cross-Domain Low-Resource Text Generation through LLM Post-Editing: A Programmer-Interpreter Approach

no code implementations7 Feb 2024 Zhuang Li, Levon Haroutunian, Raj Tumuluri, Philip Cohen, Gholamreza Haffari

Post-editing has proven effective in improving the quality of text generated by large language models (LLMs) such as GPT-3. 5 or GPT-4, particularly when direct updating of their parameters to enhance text quality is infeasible or expensive.

Domain Generalization Machine Translation +1

Continual Learning for Large Language Models: A Survey

no code implementations2 Feb 2024 Tongtong Wu, Linhao Luo, Yuan-Fang Li, Shirui Pan, Thuy-Trang Vu, Gholamreza Haffari

Large language models (LLMs) are not amenable to frequent re-training, due to high training costs arising from their massive scale.

Continual Learning Continual Pretraining +2

Assistive Large Language Model Agents for Socially-Aware Negotiation Dialogues

no code implementations29 Jan 2024 Yuncheng Hua, Lizhen Qu, Gholamreza Haffari

We introduce a simple tuning-free and label-free In-Context Learning (ICL) method to identify high-quality ICL exemplars for the remediator, where we propose a novel select criteria, called value impact, to measure the quality of the negotiation outcomes.

In-Context Learning Language Modelling +1

Towards Event Extraction from Speech with Contextual Clues

1 code implementation27 Jan 2024 Jingqi Kang, Tongtong Wu, Jinming Zhao, Guitao Wang, Guilin Qi, Yuan-Fang Li, Gholamreza Haffari

While text-based event extraction has been an active research area and has seen successful application in many domains, extracting semantic events from speech directly is an under-explored problem.

Event Extraction speech-recognition +1

Importance-Aware Data Augmentation for Document-Level Neural Machine Translation

no code implementations27 Jan 2024 Minghao Wu, YuFei Wang, George Foster, Lizhen Qu, Gholamreza Haffari

Document-level neural machine translation (DocNMT) aims to generate translations that are both coherent and cohesive, in contrast to its sentence-level counterpart.

Data Augmentation Machine Translation +2

Natural Language Processing for Dialects of a Language: A Survey

no code implementations11 Jan 2024 Aditya Joshi, Raj Dabre, Diptesh Kanojia, Zhuang Li, Haolan Zhan, Gholamreza Haffari, Doris Dippold

Motivated by the performance degradation of NLP models for dialectic datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches.

Attribute Machine Translation +4

DeSIQ: Towards an Unbiased, Challenging Benchmark for Social Intelligence Understanding

no code implementations24 Oct 2023 Xiao-Yu Guo, Yuan-Fang Li, Gholamreza Haffari

One representative benchmark for its study is Social Intelligence Queries (Social-IQ), a dataset of multiple-choice questions on videos of complex social interactions.

Language Modelling Multiple-choice

Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning

no code implementations2 Oct 2023 Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, Shirui Pan

In this paper, we propose a novel method called reasoning on graphs (RoG) that synergizes LLMs with KGs to enable faithful and interpretable reasoning.

Knowledge Graphs Language Modelling +2

Reranking for Natural Language Generation from Logical Forms: A Study based on Large Language Models

no code implementations21 Sep 2023 Levon Haroutunian, Zhuang Li, Lucian Galescu, Philip Cohen, Raj Tumuluri, Gholamreza Haffari

Our approach involves initially generating a set of candidate outputs by prompting an LLM and subsequently reranking them using a task-specific reranker model.

Text Generation

ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning

no code implementations4 Sep 2023 Linhao Luo, Jiaxin Ju, Bo Xiong, Yuan-Fang Li, Gholamreza Haffari, Shirui Pan

Logical rules are essential for uncovering the logical connections between relations, which could improve reasoning performance and provide interpretable results on knowledge graphs (KGs).

Knowledge Graphs

T3L: Translate-and-Test Transfer Learning for Cross-Lingual Text Classification

1 code implementation8 Jun 2023 Inigo Jauregi Unanue, Gholamreza Haffari, Massimo Piccardi

Cross-lingual text classification leverages text classifiers trained in a high-resource language to perform text classification in other languages with no or minimal fine-tuning (zero/few-shots cross-lingual transfer).

Cross-Lingual Transfer Language Modelling +3

Investigating Pre-trained Audio Encoders in the Low-Resource Condition

1 code implementation28 May 2023 Hao Yang, Jinming Zhao, Gholamreza Haffari, Ehsan Shareghi

Pre-trained speech encoders have been central to pushing state-of-the-art results across various speech understanding and generation tasks.

FACTUAL: A Benchmark for Faithful and Consistent Textual Scene Graph Parsing

1 code implementation27 May 2023 Zhuang Li, Yuyang Chai, Terry Yue Zhuo, Lizhen Qu, Gholamreza Haffari, Fei Li, Donghong Ji, Quan Hung Tran

Textual scene graph parsing has become increasingly important in various vision-language applications, including image caption evaluation and image retrieval.

Graph Similarity Human Judgment Correlation +4

NormMark: A Weakly Supervised Markov Model for Socio-cultural Norm Discovery

no code implementations26 May 2023 Farhad Moghimifar, Shilin Qu, Tongtong Wu, Yuan-Fang Li, Gholamreza Haffari

Norms, which are culturally accepted guidelines for behaviours, can be integrated into conversational models to generate utterances that are appropriate for the socio-cultural context.

The Best of Both Worlds: Combining Human and Machine Translations for Multilingual Semantic Parsing with Active Learning

no code implementations22 May 2023 Zhuang Li, Lizhen Qu, Philip R. Cohen, Raj V. Tumuluri, Gholamreza Haffari

Multilingual semantic parsing aims to leverage the knowledge from the high-resource languages to improve low-resource semantic parsing, yet commonly suffers from the data imbalance problem.

Active Learning Semantic Parsing

Active Continual Learning: On Balancing Knowledge Retention and Learnability

no code implementations6 May 2023 Thuy-Trang Vu, Shahram Khadivi, Mahsa Ghorbanali, Dinh Phung, Gholamreza Haffari

Acquiring new knowledge without forgetting what has been learned in a sequence of tasks is the central focus of continual learning (CL).

Active Learning Continual Learning +1

Turning Flowchart into Dialog: Augmenting Flowchart-grounded Troubleshooting Dialogs via Synthetic Data Generation

1 code implementation2 May 2023 Haolan Zhan, Sameen Maruf, Lizhen Qu, YuFei Wang, Ingrid Zukerman, Gholamreza Haffari

Flowchart-grounded troubleshooting dialogue (FTD) systems, which follow the instructions of a flowchart to diagnose users' problems in specific domains (e. g., vehicle, laptop), have been gaining research interest in recent years.

Data Augmentation Response Generation +2

Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion

1 code implementation17 Apr 2023 Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, Shirui Pan

In this paper, we propose a normalizing flow-based neural process for few-shot knowledge graph completion (NP-FKGC).

Graph Neural Network Meta-Learning +1

Koala: An Index for Quantifying Overlaps with Pre-training Corpora

no code implementations26 Mar 2023 Thuy-Trang Vu, Xuanli He, Gholamreza Haffari, Ehsan Shareghi

In very recent years more attention has been placed on probing the role of pre-training data in Large Language Models (LLMs) downstream behaviour.

Memorization

ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learning

no code implementations CVPR 2023 Islam Nassar, Munawar Hayat, Ehsan Abbasnejad, Hamid Rezatofighi, Gholamreza Haffari

Finally, ProtoCon addresses the poor training signal in the initial phase of training (due to fewer confident predictions) by introducing an auxiliary self-supervised loss.

Online Clustering Pseudo Label

Less is More: Mitigate Spurious Correlations for Open-Domain Dialogue Response Generation Models by Causal Discovery

1 code implementation2 Mar 2023 Tao Feng, Lizhen Qu, Gholamreza Haffari

In this paper, we conduct the first study on spurious correlations for open-domain response generation models based on a corpus CGDIALOG curated in our work.

Causal Discovery Informativeness +1

Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translation

no code implementations16 Feb 2023 Minghao Wu, George Foster, Lizhen Qu, Gholamreza Haffari

Existing work in document-level neural machine translation commonly concatenates several consecutive sentences as a pseudo-document, and then learns inter-sentential dependencies.

Machine Translation Translation

Active Learning for Multilingual Semantic Parser

no code implementations30 Jan 2023 Zhuang Li, Gholamreza Haffari

Current multilingual semantic parsing (MSP) datasets are almost all collected by translating the utterances in the existing datasets from the resource-rich language to the target language.

Active Learning Semantic Parsing +1

Energy-based Self-Training and Normalization for Unsupervised Domain Adaptation

no code implementations ICCV 2023 Samitha Herath, Basura Fernando, Ehsan Abbasnejad, Munawar Hayat, Shahram Khadivi, Mehrtash Harandi, Hamid Rezatofighi, Gholamreza Haffari

EBL can be used to improve the instance selection for a self-training task on the unlabelled target domain, and 2. alignment and normalizing energy scores can learn domain-invariant representations.

Unsupervised Domain Adaptation

Let's Negotiate! A Survey of Negotiation Dialogue Systems

no code implementations18 Dec 2022 Haolan Zhan, YuFei Wang, Tao Feng, Yuncheng Hua, Suraj Sharma, Zhuang Li, Lizhen Qu, Gholamreza Haffari

Negotiation is one of the crucial abilities in human communication, and there has been a resurgent research interest in negotiation dialogue systems recently, which goal is to empower intelligent agents with such ability that can efficiently help humans resolve conflicts or reach beneficial agreements.

Learning Object-Language Alignments for Open-Vocabulary Object Detection

1 code implementation27 Nov 2022 Chuang Lin, Peize Sun, Yi Jiang, Ping Luo, Lizhen Qu, Gholamreza Haffari, Zehuan Yuan, Jianfei Cai

In this paper, we propose a novel open-vocabulary object detection framework directly learning from image-text pair data.

Object object-detection +3

Complex Reading Comprehension Through Question Decomposition

no code implementations7 Nov 2022 Xiao-Yu Guo, Yuan-Fang Li, Gholamreza Haffari

Multi-hop reading comprehension requires not only the ability to reason over raw text but also the ability to combine multiple evidence.

Language Modelling Multi-Hop Reading Comprehension

Towards Relation Extraction From Speech

1 code implementation17 Oct 2022 Tongtong Wu, Guitao Wang, Jinming Zhao, Zhaoran Liu, Guilin Qi, Yuan-Fang Li, Gholamreza Haffari

We explore speech relation extraction via two approaches: the pipeline approach conducting text-based extraction with a pretrained ASR module, and the end2end approach via a new proposed encoder-decoder model, or what we called SpeechRE.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

RedApt: An Adaptor for wav2vec 2 Encoding \\ Faster and Smaller Speech Translation without Quality Compromise

no code implementations16 Oct 2022 Jinming Zhao, Hao Yang, Gholamreza Haffari, Ehsan Shareghi

Pre-trained speech Transformers in speech translation (ST) have facilitated state-of-the-art (SotA) results; yet, using such encoders is computationally expensive.

Translation

Teaching Neural Module Networks to Do Arithmetic

no code implementations COLING 2022 Jiayi Chen, Xiao-Yu Guo, Yuan-Fang Li, Gholamreza Haffari

Answering complex questions that require multi-step multi-type reasoning over raw text is challenging, especially when conducting numerical reasoning.

Feature-based Learning for Diverse and Privacy-Preserving Counterfactual Explanations

1 code implementation27 Sep 2022 Vy Vo, Trung Le, Van Nguyen, He Zhao, Edwin Bonilla, Gholamreza Haffari, Dinh Phung

Interpretable machine learning seeks to understand the reasoning process of complex black-box systems that are long notorious for lack of explainability.

counterfactual Diversity +4

An Additive Instance-Wise Approach to Multi-class Model Interpretation

1 code implementation7 Jul 2022 Vy Vo, Van Nguyen, Trung Le, Quan Hung Tran, Gholamreza Haffari, Seyit Camtepe, Dinh Phung

A popular attribution-based approach is to exploit local neighborhoods for learning instance-specific explainers in an additive manner.

Additive models Interpretable Machine Learning

M-Adapter: Modality Adaptation for End-to-End Speech-to-Text Translation

1 code implementation3 Jul 2022 Jinming Zhao, Hao Yang, Ehsan Shareghi, Gholamreza Haffari

End-to-end speech-to-text translation models are often initialized with pre-trained speech encoder and pre-trained text decoder.

Decoder Speech-to-Text Translation +1

Variational Autoencoder with Disentanglement Priors for Low-Resource Task-Specific Natural Language Generation

1 code implementation27 Feb 2022 Zhuang Li, Lizhen Qu, Qiongkai Xu, Tongtong Wu, Tianyang Zhan, Gholamreza Haffari

In this paper, we propose a variational autoencoder with disentanglement priors, VAE-DPRIOR, for task-specific natural language generation with none or a handful of task-specific labeled examples.

Data Augmentation Disentanglement +3

Utilizing Wordnets for Cognate Detection among Indian Languages

no code implementations GWC 2019 Diptesh Kanojia, Kevin Patel, Pushpak Bhattacharyya, Malhar Kulkarni, Gholamreza Haffari

Automatic Cognate Detection (ACD) is a challenging task which has been utilized to help NLP applications like Machine Translation, Information Retrieval and Computational Phylogenetics.

Information Retrieval Machine Translation +1

Challenge Dataset of Cognates and False Friend Pairs from Indian Languages

1 code implementation LREC 2020 Diptesh Kanojia, Pushpak Bhattacharyya, Malhar Kulkarni, Gholamreza Haffari

In this paper, we describe the creation of two cognate datasets for twelve Indian languages, namely Sanskrit, Hindi, Assamese, Oriya, Kannada, Gujarati, Tamil, Telugu, Punjabi, Bengali, Marathi, and Malayalam.

Information Retrieval Machine Translation +2

BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule

no code implementations CVPR 2022 Miao Zhang, Jilin Hu, Steven Su, Shirui Pan, Xiaojun Chang, Bin Yang, Gholamreza Haffari

Differentiable Architecture Search (DARTS) has received massive attention in recent years, mainly because it significantly reduces the computational cost through weight sharing and continuous relaxation.

Neural Architecture Search Variational Inference

Medical Visual Question Answering: A Survey

no code implementations19 Nov 2021 Zhihong Lin, Donghao Zhang, Qingyi Tao, Danli Shi, Gholamreza Haffari, Qi Wu, Mingguang He, ZongYuan Ge

Medical Visual Question Answering~(VQA) is a combination of medical artificial intelligence and popular VQA challenges.

Medical Visual Question Answering Question Answering +1

Multimodal Transformer with Variable-length Memory for Vision-and-Language Navigation

1 code implementation10 Nov 2021 Chuang Lin, Yi Jiang, Jianfei Cai, Lizhen Qu, Gholamreza Haffari, Zehuan Yuan

Vision-and-Language Navigation (VLN) is a task that an agent is required to follow a language instruction to navigate to the goal position, which relies on the ongoing interactions with the environment during moving.

Decoder Navigate +1

Multilingual Neural Machine Translation:Can Linguistic Hierarchies Help?

no code implementations15 Oct 2021 Fahimeh Saleh, Wray Buntine, Gholamreza Haffari, Lan Du

Multilingual Neural Machine Translation (MNMT) trains a single NMT model that supports translation between multiple languages, rather than training separate models for different languages.

Knowledge Distillation Machine Translation +2

Pretrained Language Model in Continual Learning: A Comparative Study

no code implementations ICLR 2022 Tongtong Wu, Massimo Caccia, Zhuang Li, Yuan-Fang Li, Guilin Qi, Gholamreza Haffari

In this paper, we thoroughly compare the continual learning performance over the combination of 5 PLMs and 4 veins of CL methods on 3 benchmarks in 2 typical incremental settings.

Continual Learning Language Modelling

Generate, Annotate, and Learn: Generative Models Advance Self-Training and Knowledge Distillation

no code implementations29 Sep 2021 Xuanli He, Islam Nassar, Jamie Ryan Kiros, Gholamreza Haffari, Mohammad Norouzi

To obtain strong task-specific generative models, we either fine-tune a large language model (LLM) on inputs from specific tasks, or prompt a LLM with a few input examples to generate more unlabeled examples.

Few-Shot Learning Knowledge Distillation +2

Total Recall: a Customized Continual Learning Method for Neural Semantic Parsers

1 code implementation EMNLP 2021 Zhuang Li, Lizhen Qu, Gholamreza Haffari

We conduct extensive experiments to study the research problems involved in continual semantic parsing and demonstrate that a neural semantic parser trained with TotalRecall achieves superior performance than the one trained directly with the SOTA continual learning algorithms and achieve a 3-6 times speedup compared to re-training from scratch.

Continual Learning Semantic Parsing

Generalised Unsupervised Domain Adaptation of Neural Machine Translation with Cross-Lingual Data Selection

1 code implementation EMNLP 2021 Thuy-Trang Vu, Xuanli He, Dinh Phung, Gholamreza Haffari

Once the in-domain data is detected by the classifier, the NMT model is then adapted to the new domain by jointly learning translation and domain discrimination tasks.

Contrastive Learning Machine Translation +3

Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Training

no code implementations EMNLP 2021 Minghao Wu, Yitong Li, Meng Zhang, Liangyou Li, Gholamreza Haffari, Qun Liu

In this work, we propose an approach, MultiUAT, that dynamically adjusts the training data usage based on the model's uncertainty on a small set of trusted clean data for multi-corpus machine translation.

Machine Translation Translation

Learning to Explain: Generating Stable Explanations Fast

1 code implementation ACL 2021 Xuelin Situ, Ingrid Zukerman, Cecile Paris, Sameen Maruf, Gholamreza Haffari

The importance of explaining the outcome of a machine learning model, especially a black-box model, is widely acknowledged.

All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-training

1 code implementation CVPR 2021 Islam Nassar, Samitha Herath, Ehsan Abbasnejad, Wray Buntine, Gholamreza Haffari

We train two classifiers with two different views of the class labels: one classifier uses the one-hot view of the labels and disregards any potential similarity among the classes, while the other uses a distributed view of the labels and groups potentially similar classes together.

Semi-Supervised Image Classification

Domain Adaptative Causality Encoder

1 code implementation ALTA 2020 Farhad Moghimifar, Gholamreza Haffari, Mahsa Baktashmotlagh

Our experiments on four different benchmark causality datasets demonstrate the superiority of our approach over the existing baselines, by up to 7% improvement, on the tasks of identification and localisation of the causal relations from the text.

Multi-objective semi-supervised clustering to identify health service patterns for injured patients

no code implementations16 Nov 2020 Hadi Akbarzadeh Khorshidi, Uwe Aickelin, Gholamreza Haffari, Behrooz Hassani-Mahmooei

The practical purpose of developing this pattern recognition method is to group patients, who are injured in transport accidents, in the early stages post-injury.

Clustering

COSMO: Conditional SEQ2SEQ-based Mixture Model for Zero-Shot Commonsense Question Answering

1 code implementation COLING 2020 Farhad Moghimifar, Lizhen Qu, Yue Zhuo, Mahsa Baktashmotlagh, Gholamreza Haffari

However, current approaches in this realm lack the ability to perform commonsense reasoning upon facing an unseen situation, mostly due to incapability of identifying a diverse range of implicit social relations.

Question Answering

Context Dependent Semantic Parsing: A Survey

1 code implementation COLING 2020 Zhuang Li, Lizhen Qu, Gholamreza Haffari

Semantic parsing is the task of translating natural language utterances into machine-readable meaning representations.

Semantic Parsing

Few-Shot Complex Knowledge Base Question Answering via Meta Reinforcement Learning

1 code implementation EMNLP 2020 Yuncheng Hua, Yuan-Fang Li, Gholamreza Haffari, Guilin Qi, Tongtong Wu

Our method achieves state-of-the-art performance on the CQA dataset (Saha et al., 2018) while using only five trial trajectories for the top-5 retrieved questions in each support set, and metatraining on tasks constructed from only 1% of the training set.

Knowledge Base Question Answering Meta Reinforcement Learning +3

Understanding Unnatural Questions Improves Reasoning over Text

no code implementations COLING 2020 Xiao-Yu Guo, Yuan-Fang Li, Gholamreza Haffari

A prominent approach to this task is based on the programmer-interpreter framework, where the programmer maps the question into a sequence of reasoning actions which is then executed on the raw text by the interpreter.

Diversity Natural Questions +1

Effective Unsupervised Domain Adaptation with Adversarially Trained Language Models

1 code implementation EMNLP 2020 Thuy-Trang Vu, Dinh Phung, Gholamreza Haffari

Recent work has shown the importance of adaptation of broad-coverage contextualised embedding models on the domain of the target task of interest.

named-entity-recognition Named Entity Recognition +2

SummPip: Unsupervised Multi-Document Summarization with Sentence Graph Compression

1 code implementation17 Jul 2020 Jinming Zhao, Ming Liu, Longxiang Gao, Yuan Jin, Lan Du, He Zhao, He Zhang, Gholamreza Haffari

Obtaining training data for multi-document summarization (MDS) is time consuming and resource-intensive, so recent neural models can only be trained for limited domains.

Clustering Document Summarization +2

Dynamic Programming Encoding for Subword Segmentation in Neural Machine Translation

1 code implementation ACL 2020 Xuanli He, Gholamreza Haffari, Mohammad Norouzi

This paper introduces Dynamic Programming Encoding (DPE), a new segmentation algorithm for tokenizing sentences into subword units.

Machine Translation Segmentation +1

Decoding As Dynamic Programming For Recurrent Autoregressive Models

no code implementations ICLR 2020 Najam Zaidi, Trevor Cohn, Gholamreza Haffari

Decoding in autoregressive models (ARMs) consists of searching for a high scoring output sequence under the trained model.

Text Infilling

Contextual Neural Machine Translation Improves Translation of Cataphoric Pronouns

1 code implementation ACL 2020 KayYen Wong, Sameen Maruf, Gholamreza Haffari

In this work, we investigate the effect of future sentences as context by comparing the performance of a contextual NMT model trained with the future context to the one trained with the past context.

Machine Translation NMT +1

Learning to Multi-Task Learn for Better Neural Machine Translation

no code implementations10 Jan 2020 Poorya Zaremoodi, Gholamreza Haffari

We effectively and efficiently learn the training schedule policy within the imitation learning framework using an oracle policy algorithm that dynamically sets the importance weights of auxiliary tasks based on their contributions to the generalisability of the main NMT task.

Imitation Learning Low Resource NMT +5

A Survey on Document-level Neural Machine Translation: Methods and Evaluation

1 code implementation18 Dec 2019 Sameen Maruf, Fahimeh Saleh, Gholamreza Haffari

Machine translation (MT) is an important task in natural language processing (NLP) as it automates the translation process and reduces the reliance on human translators.

Document Level Machine Translation Machine Translation +1

Question Generation from Paragraphs: A Tale of Two Hierarchical Models

no code implementations8 Nov 2019 Vishwajeet Kumar, Raktim Chaki, Sai Teja Talluri, Ganesh Ramakrishnan, Yuan-Fang Li, Gholamreza Haffari

Specifically, we propose (a) a novel hierarchical BiLSTM model with selective attention and (b) a novel hierarchical Transformer architecture, both of which learn hierarchical representations of paragraphs.

Question Generation Question-Generation +2

Adaptively Scheduled Multitask Learning: The Case of Low-Resource Neural Machine Translation

no code implementations WS 2019 Poorya Zaremoodi, Gholamreza Haffari

The role of training schedule becomes even more crucial in \textit{biased-MTL} where the goal is to improve one (or a subset) of tasks the most, e. g. translation quality.

Low Resource Neural Machine Translation Low-Resource Neural Machine Translation +2

Monash University's Submissions to the WNGT 2019 Document Translation Task

no code implementations WS 2019 Sameen Maruf, Gholamreza Haffari

We describe the work of Monash University for the shared task of Rotowire document translation organised by the 3rd Workshop on Neural Generation and Translation (WNGT 2019).

de-en Document Translation +2

Neural Speech Translation using Lattice Transformations and Graph Networks

no code implementations WS 2019 Daniel Beck, Trevor Cohn, Gholamreza Haffari

Speech translation systems usually follow a pipeline approach, using word lattices as an intermediate representation.

Translation

Learning How to Active Learn by Dreaming

1 code implementation ACL 2019 Thuy-Trang Vu, Ming Liu, Dinh Phung, Gholamreza Haffari

Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary.

Active Learning named-entity-recognition +5

Selective Attention for Context-aware Neural Machine Translation

1 code implementation NAACL 2019 Sameen Maruf, André F. T. Martins, Gholamreza Haffari

Despite the progress made in sentence-level NMT, current systems still fall short at achieving fluent, good quality translation for a full document.

Decoder Machine Translation +3

Medical Multimodal Classifiers Under Scarce Data Condition

no code implementations24 Feb 2019 Faik Aydin, Maggie Zhang, Michelle Ananda-Rajah, Gholamreza Haffari

To overcome the challenges of the small training dataset which only has 3K frontal X-ray images and medical reports in pairs, we have adopted transfer learning for the multimodal which concatenates the layers of image and text submodels.

Clustering Transfer Learning

A new simple and effective measure for bag-of-word inter-document similarity measurement

no code implementations9 Feb 2019 Sunil Aryal, Kai Ming Ting, Takashi Washio, Gholamreza Haffari

To measure the similarity of two documents in the bag-of-words (BoW) vector representation, different term weighting schemes are used to improve the performance of cosine similarity---the most widely used inter-document similarity measure in text mining.

Exploring Textual and Speech information in Dialogue Act Classification with Speaker Domain Adaptation

no code implementations ALTA 2018 Xuanli He, Quan Hung Tran, William Havard, Laurent Besacier, Ingrid Zukerman, Gholamreza Haffari

In spite of the recent success of Dialogue Act (DA) classification, the majority of prior works focus on text-based classification with oracle transcriptions, i. e. human transcriptions, instead of Automatic Speech Recognition (ASR)'s transcriptions.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

Sequence to Sequence Mixture Model for Diverse Machine Translation

no code implementations CONLL 2018 Xuanli He, Gholamreza Haffari, Mohammad Norouzi

In this paper, we develop a novel sequence to sequence mixture (S2SMIX) model that improves both translation diversity and quality by adopting a committee of specialized translation models rather than a single translation model.

Clustering Diversity +2

Automatic Post-Editing of Machine Translation: A Neural Programmer-Interpreter Approach

1 code implementation EMNLP 2018 Thuy-Trang Vu, Gholamreza Haffari

Automated Post-Editing (PE) is the task of automatically correct common and repetitive errors found in machine translation (MT) output.

Automatic Post-Editing Translation

Contextual Neural Model for Translating Bilingual Multi-Speaker Conversations

1 code implementation WS 2018 Sameen Maruf, André F. T. Martins, Gholamreza Haffari

In this work, we propose the task of translating Bilingual Multi-Speaker Conversations, and explore neural architectures which exploit both source and target-side conversation histories for this task.

Document Translation Machine Translation +1

Incorporating Syntactic Uncertainty in Neural Machine Translation with a Forest-to-Sequence Model

no code implementations COLING 2018 Poorya Zaremoodi, Gholamreza Haffari

Incorporating syntactic information in Neural Machine Translation (NMT) can lead to better reorderings, particularly useful when the language pairs are syntactically highly divergent or when the training bitext is not large.

Machine Translation NMT +2

Iterative Back-Translation for Neural Machine Translation

no code implementations WS 2018 Vu Cong Duy Hoang, Philipp Koehn, Gholamreza Haffari, Trevor Cohn

We present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems.

Machine Translation Translation

Learning How to Actively Learn: A Deep Imitation Learning Approach

1 code implementation ACL 2018 Ming Liu, Wray Buntine, Gholamreza Haffari

Heuristic-based active learning (AL) methods are limited when the data distribution of the underlying learning problems vary.

Active Learning General Classification +8

Incorporating Syntactic Uncertainty in Neural Machine Translation with Forest-to-Sequence Model

no code implementations19 Nov 2017 Poorya Zaremoodi, Gholamreza Haffari

In this paper, we propose a forest-to-sequence Attentional Neural Machine Translation model to make use of exponentially many parse trees of the source sentence to compensate for the parser errors.

Machine Translation Sentence +1

Document Context Neural Machine Translation with Memory Networks

no code implementations ACL 2018 Sameen Maruf, Gholamreza Haffari

We present a document-level neural machine translation model which takes both source and target document context into account using memory networks.

Machine Translation Structured Prediction +1

Persian-Spanish Low-Resource Statistical Machine Translation Through English as Pivot Language

no code implementations RANLP 2017 Benyamin Ahmadnia, Javier Serrano, Gholamreza Haffari

This paper is an attempt to exclusively focus on investigating the pivot language technique in which a bridging language is utilized to increase the quality of the Persian-Spanish low-resource Statistical Machine Translation (SMT).

Machine Translation Sentence +1

Efficient Benchmarking of NLP APIs using Multi-armed Bandits

no code implementations EACL 2017 Gholamreza Haffari, Tuan Dung Tran, Mark Carman

Comparing NLP systems to select the best one for a task of interest, such as named entity recognition, is critical for practitioners and researchers.

Benchmarking Multi-Armed Bandits +5

Towards Decoding as Continuous Optimization in Neural Machine Translation

no code implementations11 Jan 2017 Cong Duy Vu Hoang, Gholamreza Haffari, Trevor Cohn

We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation.

Machine Translation NMT +1

Improving Word Alignment of Rare Words with Word Embeddings

no code implementations COLING 2016 Masoud Jalili Sabet, Heshaam Faili, Gholamreza Haffari

We address the problem of inducing word alignment for language pairs by developing an unsupervised model with the capability of getting applied to other generative alignment models.

Machine Translation Sentence +2

Word Representation Models for Morphologically Rich Languages in Neural Machine Translation

no code implementations WS 2017 Ekaterina Vylomova, Trevor Cohn, Xuanli He, Gholamreza Haffari

Dealing with the complex word forms in morphologically rich languages is an open problem in language processing, and is particularly important in translation.

Hard Attention Machine Translation +1

A Latent Variable Recurrent Neural Network for Discourse Relation Language Models

1 code implementation7 Mar 2016 Yangfeng Ji, Gholamreza Haffari, Jacob Eisenstein

This paper presents a novel latent variable recurrent neural network architecture for jointly modeling sequences of words and (possibly latent) discourse relations between adjacent sentences.

Classification Dialog Act Classification +4

Novel Bernstein-like Concentration Inequalities for the Missing Mass

no code implementations10 Mar 2015 Bahman Yari Saeed Khanloo, Gholamreza Haffari

We are concerned with obtaining novel concentration inequalities for the missing mass, i. e. the total probability mass of the outcomes not observed in the sample.

Learning Theory

Structured Prediction of Sequences and Trees using Infinite Contexts

no code implementations9 Mar 2015 Ehsan Shareghi, Gholamreza Haffari, Trevor Cohn, Ann Nicholson

Linguistic structures exhibit a rich array of global phenomena, however commonly used Markov models are unable to adequately describe these phenomena due to their strong locality assumptions.

Part-Of-Speech Tagging Structured Prediction