Papers by Marjan Ghazvininejad
Non-Autoregressive Semantic Parsing for Compositional Task-Oriented Dialog (2021.naacl-main)
Copied to clipboard
| Challenge: | Semantic parsing using sequence-to-sequence models is stymied by higher compute requirements and higher latency. |
| Approach: | They propose a non-autoregressive approach to predict semantic parse trees with an efficient seq2seq model architecture. |
| Outcome: | The proposed architecture achieves an 81% reduction in latency on TOP dataset and retains competitive performance over non-pretrained models on three different semantic parsing datasets. |
Discourse-Aware Soft Prompting for Text Generation (2022.emnlp-main)
Copied to clipboard
| Challenge: | Recent advances in pre-trained langauge models (PLMs) have made great impact on text generation research. |
| Approach: | They propose to use hierarchical blocking to simulate a higher-level discourse structure of human written text and attention sparsity to learn sparse transformations on the softmax-function. |
| Outcome: | The proposed methods perform better on some generation tasks but don't generalize across all generation tasks. |
Simple and Effective Retrieve-Edit-Rerank Text Generation (2020.acl-main)
Copied to clipboard
| Challenge: | Using retrieve-and-edit methods, text generation methods can be improved by reranking outputs from training sets and learning models to produce the final output. |
| Approach: | They propose to extend retrieve-and-edit seq2seq methods with a simple post-generation ranking approach that retrieves multiple outputs and edits each independently to produce the final output. |
| Outcome: | The proposed approach outperforms existing methods on two machine translation datasets and shows room for improvement with better candidate output selection in future work. |
Prompting Contrastive Explanations for Commonsense Reasoning Tasks (2021.findings-acl)
Copied to clipboard
| Challenge: | Large pretrained language models (PLMs) can achieve near-human performance on commonsense reasoning tasks, but provide little human-interpretable evidence of the underlying reasoning they use. |
| Approach: | They propose to use large pretrained language models to generate evidence for commonsense reasoning NLP tasks . they use models to contrast alternative explanations based on key attribute(s) required to justify the correct answer . |
| Outcome: | The proposed model improves performance on two commonsense reasoning benchmarks compared to previous non-contrastive alternatives. |
Multilingual Denoising Pre-training for Neural Machine Translation (2020.tacl-1)
Copied to clipboard
Yinhan Liu, Jiatao Gu, Naman Goyal, Xian Li, Sergey Edunov, Marjan Ghazvininejad, Mike Lewis, Luke Zettlemoyer
| Challenge: | Existing approaches to pre-train models focus on only English corpora, but this is not common in machine translation. |
| Approach: | They propose a sequence-to-sequence denoising auto-encoder pre-trained on monolingual corpora . they show that it produces significant performance gains across MT tasks . |
| Outcome: | The proposed model can achieve significant performance gains across a wide variety of MT tasks. |
Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation (2021.naacl-main)
Copied to clipboard
Alexander Fabbri, Simeng Han, Haoyuan Li, Haoran Li, Marjan Ghazvininejad, Shafiq Joty, Dragomir Radev, Yashar Mehdad
| Challenge: | Recent advances in summarization are driven by the availability of large datasets such as the CNN-DailyMail corpus and the New York Times corpus. |
| Approach: | They propose a method for fine-tuning pretrained models for summarization in unsupervised manner . they use Wikipedia data to produce pseudo-summaries which contain characteristics of target dataset . |
| Outcome: | The proposed method achieves state-of-the-art, zero-shot abstractive summarization performance on CNN-DailyMail dataset and compares with other methods on other datasets. |
XLM-V: Overcoming the Vocabulary Bottleneck in Multilingual Masked Language Models (2023.emnlp-main)
Copied to clipboard
Davis Liang, Hila Gonen, Yuning Mao, Rui Hou, Naman Goyal, Marjan Ghazvininejad, Luke Zettlemoyer, Madian Khabsa
| Challenge: | Large multilingual models rely on a single vocabulary shared across 100+ languages . this vocabulary bottleneck limits the representational capabilities of multilingual model XLM-R . |
| Approach: | They propose a new approach for scaling to large multilingual vocabularies by de-emphasizing token sharing between languages with little lexical overlap and assigning vocabulary capacity to achieve sufficient coverage for each individual language. |
| Outcome: | The proposed model outperforms XLM-R on all language tasks and is particularly effective on low-resource tasks. |
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation (P19-1)
Copied to clipboard
| Challenge: | Using a dictionary, given a rough, target language natives can uncover the latent, fully-fluent rendering of the translation. |
| Approach: | They propose a method that breaks translation into two steps by generating a dictionary and then ‘translating’ the resulting pseudo-translation into a fully fluent translation. |
| Outcome: | The proposed method 'gets better translation results on high-resource languages than previously published unsupervised MT studies' |
Neural Poetry Translation (N18-2)
Copied to clipboard
| Challenge: | despite recent advances in machine translation, automatic poetry translation remains a challenging problem. |
| Approach: | They propose a system that automatically translates a source text to an English poem . human evaluation of the translations ranks the quality as acceptable 78.2% of the time. |
| Outcome: | The proposed system always translates a source text to an English poem. human evaluation of the translations ranks the quality as acceptable 78.2% of the time. |
Natural Language to Code Translation with Execution (2022.emnlp-main)
Copied to clipboard
| Challenge: | Generative code models do not explicitly incorporate program semantics during training, but they are able to generate correct solutions for many problems. |
| Approach: | They introduce execution result-based minimum Bayes risk decoding for program selection . they select output programs from a generated candidate set by marginalizing over implementations that share the same semantics . |
| Outcome: | The proposed model outperforms all other methods on natural language-to-code translation. |
BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation (2022.findings-naacl)
Copied to clipboard
| Challenge: | Existing methods to improve Neural Machine Translation (NMT) for lowresource languages are often trained on heuristically aligned or automatically mined data. |
| Approach: | They propose to filter out imperfect translations that yield unreliable training signals for Neural Machine Translation (NMT) instead, they propose to refine mined bitexts by automatic editing . |
| Outcome: | The proposed method improves the quality of mined bitexts for low-resource languages by up to 8 BLEU points. |
Training on Synthetic Noise Improves Robustness to Natural Noise in Machine Translation (D19-55)
Copied to clipboard
| Challenge: | Recent machine translation methods are highly sensitive to orthographical variations such as spelling errors. |
| Approach: | They propose to train machine translation models with random synthetic noise at training time . they focus on translation performance on natural typos, and show robustness to such noise . |
| Outcome: | The proposed method significantly improves translation models on natural typos without accessing natural noise data or distribution. |
Recipes for Adapting Pre-trained Monolingual and Multilingual Models to Machine Translation (2021.eacl-main)
Copied to clipboard
| Challenge: | Recent advances in machine translation (MT) have improved performance on low-resource language pairs. |
| Approach: | They propose to freeze most BART parameters and add new ones to fine-tune a model trained on MT. |
| Outcome: | The proposed model outperforms naive fine-tuning on Vietnamese to English on a training set for Vietnamese to Vietnamese . the proposed model is able to fine- tune on smaller datasets while still maintaining the same model performance. |
Using Word Vectors to Improve Word Alignments for Low Resource Machine Translation (N18-2)
Copied to clipboard
| Challenge: | Using word similarities, we improve word alignments in low resource settings . word alignment is essential for statistical machine translation (MT) |
| Approach: | They propose a method for improving word alignments using word similarities using word vectors trained on monolingual data. |
| Outcome: | The proposed method improves word alignments in low-resource settings by improving alignments of infrequent tokens. |
BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension (2020.acl-main)
Copied to clipboard
Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, Luke Zettlemoyer
| Challenge: | Recent work has shown gains by improving the distribution of masked tokens and the order in which mucked tokens are predicted. |
| Approach: | They propose a denoising autoencoder for pretraining sequence-to-sequence models that corrupts text with an arbitrary noising function and learns a model to reconstruct the original text. |
| Outcome: | The proposed model outperforms RoBERTa on GLUE and SQUAD and provides a 1.1 BLEU increase over a back-translation system for machine translation. |
In-context Examples Selection for Machine Translation (2023.findings-acl)
Copied to clipboard
| Challenge: | Large-scale generative models can perform a wide range of NLP tasks using in-context learning. |
| Approach: | They aim to understand the properties of good in-context examples for machine translation in both in-domain and out-of-domain settings. |
| Outcome: | The proposed model outperforms a strong kNN-MT baseline in 2 out of 4 out-of-domain datasets. |
Mask-Predict: Parallel Decoding of Conditional Masked Language Models (D19-1)
Copied to clipboard
| Challenge: | a masked language model is used to train a model to predict subsets of mangled words . a parallel decoding algorithm can be used to generate translations in a constant number of iterations. |
| Approach: | They propose a model and a parallel decoding algorithm which train a machine to predict any subset of target words . they introduce conditional masked language models (CMLMs) which are trained with a mangled language model objective . |
| Outcome: | The proposed model improves state-of-the-art performance levels for non-autoregressive and parallel decoding models by over 4 BLEU on average. |
reWordBench: Benchmarking and Improving the Robustness of Reward Models with Transformed Inputs (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing reward models have a high performance on benchmarks, but performance degradation is often due to overfitting. |
| Approach: | They propose to explicitly train reward models to assign similar scores to paraphrases to improve their robustness. |
| Outcome: | The proposed model reduces degradation by half for the Chat Hard subset in RewardBench. |
Detecting Hallucinated Content in Conditional Neural Sequence Generation (2021.findings-acl)
Copied to clipboard
Chunting Zhou, Graham Neubig, Jiatao Gu, Mona Diab, Francisco Guzmán, Luke Zettlemoyer, Marjan Ghazvininejad
| Challenge: | Neural sequence models can generate fluent sentences, but they can also hallucinate additional content not supported by the input. |
| Approach: | They propose a task to predict whether each token in the output sequence is hallucinated and collect manually annotated evaluation sets for this task. |
| Outcome: | The proposed method outperforms baseline methods on machine translation and abstractive summarization datasets and achieves significant improvements in both supervised and unsupervised settings. |
Distributionally Robust Multilingual Machine Translation (2021.emnlp-main)
Copied to clipboard
| Challenge: | Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, but the data imbalance hinders it from performing uniformly across language pairs. |
| Approach: | They propose a distributionally robust optimization objective which minimizes the worst-case expected loss over the set of language pairs. |
| Outcome: | The proposed learning objective outperforms baseline methods on three sets of languages and shows that it is cost-effective and efficient. |
David helps Goliath: Inference-Time Collaboration Between Small Specialized and Large General Diffusion LMs (2024.naacl-long)
Copied to clipboard
| Challenge: | Existing studies of diffusion-based language models have been conducted on a smaller scale. |
| Approach: | They propose to scale an autoregressive diffusion model from 0.4B to 13B parameters and propose techniques to improve its training and inference efficiency. |
| Outcome: | The proposed model is able to combine a large general-purpose diffusion model with smaller, but specialized and contextualized diffusion models at inference time. |