Gholamreza Haffari
12 papers in the PaperMetrix corpus
Papers by this author
-
Decoding As Dynamic Programming For Recurrent Autoregressive Models
2020 · Monash University Research Portal (Monash University)
Decoding in autoregressive models (ARMs) consists of searching for a high scoring output sequence under the trained model. Standard decoding methods, based on unidirectional greedy algorithm or beam search, are suboptimal due to error propagation …
-
Scene Graph Modification Based on Natural Language Commands
2020 · arXiv (Cornell University)
Structured representations like graphs and parse trees play a crucial role in many Natural Language Processing systems. In recent years, the advancements in multi-turn user interfaces necessitate the need for controlling and updating these structured …
-
Neural-Symbolic Commonsense Reasoner with Relation Predictors
2021
Farhad Moghimifar, Lizhen Qu, Terry Yue Zhuo, Gholamreza Haffari, Mahsa Baktashmotlagh. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: …
-
Active Learning for Multilingual Semantic Parser
2023 · arXiv (Cornell University)
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. However, manual translation is costly. To reduce the translation …
-
Simultaneous Machine Translation with Large Language Models
2023 · arXiv (Cornell University)
Real-world simultaneous machine translation (SimulMT) systems face more challenges than just the quality-latency trade-off. They also need to address issues related to robustness with noisy input, processing long contexts, and flexibility for knowledge injection. These …
-
RENOVI: A Benchmark Towards Remediating Norm Violations in Socio-Cultural Conversations
2024 · arXiv (Cornell University)
Norm violations occur when individuals fail to conform to culturally accepted behaviors, which may lead to potential conflicts. Remediating norm violations requires social awareness and cultural sensitivity of the nuances at play. To equip interactive …
-
IMO: Greedy Layer-Wise Sparse Representation Learning for Out-of-Distribution Text Classification with Pre-trained Models
2024 · arXiv (Cornell University)
Machine learning models have made incredible progress, but they still struggle when applied to examples from unseen domains. This study focuses on a specific problem of domain generalization, where a model is trained on one …
-
Mixture-of-Skills: Learning to Optimize Data Usage for Fine-Tuning Large Language Models
2024 · arXiv (Cornell University)
Large language models (LLMs) are typically fine-tuned on diverse and extensive datasets sourced from various origins to develop a comprehensive range of skills, such as writing, reasoning, chatting, coding, and more. Each skill has unique …
-
Graph-to-Sequence Learning using Gated Graph Neural Networks
2018
Many NLP applications can be framed as a graph-to-sequence learning problem. Previous work proposing neural architectures on this setting obtained promising results compared to grammar-based approaches but still rely on linearisation heuristics and/or standard recurrent …
-
The Context-Dependent Additive Recurrent Neural Net
2018
Quan Hung Tran, Tuan Lai, Gholamreza Haffari, Ingrid Zukerman, Trung Bui, Hung Bui. Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long …
-
Iterative Back-Translation for Neural Machine Translation
2018
We present iterative back-translation, a method for generating increasingly better synthetic parallel data from monolingual data to train neural machine translation systems. Our proposed method is very simple yet effective and highly applicable in practice. …
-
Learning to Actively Learn Neural Machine Translation
2018
Traditional active learning (AL) methods for machine translation (MT) rely on heuristics. However, these heuristics are limited when the characteristics of the MT problem change due to e.g. the language pair or the amount of …