Noah Constant
Authored Publications
Sort By
Character-Aware Models Improve Visual Text Rendering
Chitwan Saharia
William Chan
Sharan Narang
Irina Blok
RJ Mical
Mohammad Norouzi
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (2023)
Preview abstract
Current image generation models struggle to reliably produce well-formed visual text. In this paper, we investigate a key contributing factor: popular text-to-image models lack character-level input features, making it much harder to predict a word's visual makeup as a series of glyphs. To quantify this effect, we conduct a series of experiments comparing character-aware vs. character-blind text encoders. In the text-only domain, we find that character-aware models provide large gains on a novel spelling task (WikiSpell). Applying our learnings to the visual domain, we train a suite of image generation models, and show that character-aware variants outperform their character-blind counterparts across a range of novel text rendering tasks (our DrawText benchmark). Our models set a much higher state-of-the-art on visual spelling, with 30+ point accuracy gains over competitors on rare words, despite training on far fewer examples.
View details
FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation
Jan A. Botha
Xavier Garcia
Transactions of the Association for Computational Linguistics (2023)
Preview abstract
We present FRMT, a new dataset and evaluation benchmark for Few-shot Region-aware Machine Translation, a type of style-targeted translation. The dataset consists of professional translations from English into two regional variants each of Portuguese and Mandarin Chinese. Source documents are selected to enable detailed analysis of phenomena of interest, including lexically distinct terms and distractor terms. We explore automatic evaluation metrics for FRMT and validate their correlation with expert human evaluation across both region-matched and mismatched rating scenarios. Finally, we present a number of baseline models for this task, and offer guidelines for how researchers can train, evaluate, and compare their own models. Our dataset and evaluation code are publicly available: https://bit.ly/frmt-task
View details
Overcoming Catastrophic Forgetting in Zero-Shot Cross-Lingual Generation
Tu Vu
Aditya Barua
Mohit Iyyer
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Preview abstract
In this paper, we explore the challenging problem of performing a generative task in a target language when labeled data is only available in English, using summarization as a case study. We assume a strict setting with no access to parallel data or machine translation and find that common transfer learning approaches struggle in this setting, as a generative multilingual model fine-tuned purely on English catastrophically forgets how to generate non-English. Given the recent rise of parameter-efficient adaptation techniques, we conduct the first investigation into how one such method, prompt tuning (Lester et al., 2021), can overcome catastrophic forgetting to enable zero-shot cross-lingual generation. Our experiments show that parameter-efficient prompt tuning provides gains over standard fine-tuning when transferring between less-related languages, e.g., from English to Thai. However, a significant gap still remains between these methods and fully-supervised baselines. To improve cross-lingual transfer further, we explore several approaches, including: (1) mixing in unlabeled multilingual data, and (2) explicitly factoring prompts into recombinable language and task components. Our approaches can provide further quality gains, suggesting that robust zero-shot cross-lingual generation is within reach.
View details
SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer
Tu Vu
Rami Al-Rfou
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (2022)
Preview abstract
There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a frozen pre-trained model to perform different tasks, we propose a novel prompt-based transfer learning approach called SPoT: Soft Prompt Transfer. SPoT first learns a prompt on one or more source tasks and then uses it to initialize the prompt for a target task. We show that SPoT significantly boosts the performance of Prompt Tuning across many tasks. More remarkably, across all model sizes, SPoT matches or outperforms standard Model Tuning (which fine-tunes all model parameters) on the SuperGLUE benchmark, while using up to 27,000x fewer task-specific parameters. To understand where SPoT is most effective, we conduct a large-scale study on task transferability with 26 NLP tasks in 160 combinations, and demonstrate that many tasks can benefit each other via prompt transfer. Finally, we propose an efficient retrieval approach that interprets task prompts as task embeddings to identify similar tasks and predict the most transferable source tasks for a novel target task.
View details
Preview abstract
We provide the first exploration of sentence embeddings from text-to-text transformers (T5) including the effects of scaling up sentence encoders to 11B parameters. Sentence embeddings are broadly useful for language processing tasks. While T5 achieves impressive performance on language tasks, it is unclear how to produce sentence embeddings from encoder-decoder models. We investigate three methods to construct Sentence-T5 (ST5) models: two utilize only the T5 encoder and one using the full T5 encoder-decoder. We establish a new sentence representation transfer benchmark, SentGLUE, which extends the SentEval toolkit to nine tasks from the GLUE benchmark. Our encoder-only models outperform the previous best models on both SentEval and SentGLUE transfer tasks, including semantic textual similarity (STS). Scaling up ST5 from millions to billions of parameters shown to consistently improve performance. Finally, our encoder-decoder method achieves a new state-of-the-art on STS when using sentence embeddings.
View details
mT5: A massively multilingual pre-trained text-to-text transformer
Linting Xue
Mihir Sanjay Kale
Rami Al-Rfou
Aditya Barua
Colin Raffel
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2021), Association for Computational Linguistics, Online, pp. 483-498
Preview abstract
The recent “Text-to-Text Transfer Transformer” (T5) leveraged a unified text-to-text format and scale to attain state-of-the-art results on a wide variety of English-language NLP tasks. In this paper, we introduce mT5, a multilingual variant of T5 that was pre-trained on a new Common Crawl-based dataset covering 101 languages. We detail the design and modified training of mT5 and demonstrate its state-of-the-art performance on many multilingual benchmarks. We also describe a simple technique to prevent “accidental translation” in the zero-shot setting, where a generative model chooses to (partially) translate its prediction into the wrong language. All of the code and model checkpoints used in this work are publicly available.
View details
nmT5 - Is parallel data still relevant for pre-training massively multilingual language models?
Linting Xue
Mihir Sanjay Kale
Rami Al-Rfou
Annual Meeting of the Association for Computational Linguistics (ACL) (2021) (to appear)
Preview abstract
Recently, mT5 - a massively multilingual version of T5 - leveraged a unified text-to-text format to attain state-of-the-art results on a wide variety of multilingual NLP tasks. In this paper, we investigate the impact of incorporating parallel data into mT5 pre-training. We find that simply multi-tasking language modeling with objectives such as machine translation during pre-training leads to improved performance on downstream multilingual and cross-lingual tasks. However, the gains start to diminish as the model capacity increases, suggesting that parallel data might not be as essential for larger models. At the same time, even at larger model sizes, we find that pre-training with parallel data still provides benefits in the limited labelled data regime.
View details
LAReQA: Language-Agnostic Answer Retrieval from a Multilingual Pool
Uma Roy
Rami Al-Rfou
Aditya Barua
Aaron Phillips
Yinfei Yang
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 5919-5930
Preview abstract
We present LAReQA, a challenging new benchmark for language-agnostic answer retrieval from a multilingual candidate pool. Unlike previous cross-lingual tasks, LAReQA tests for “strong” cross-lingual alignment, requiring semantically related cross-language pairs to be closer in representation space than unrelated same-language pairs. This level of alignment is important for the practical task of cross-lingual information retrieval. Building on multilingual BERT (mBERT), we study different strategies for achieving strong alignment. We find that augmenting training data via machine translation is effective, and improves significantly over using mBERT out-of-the-box. Interestingly, model performance on zero-shot variants of our task that only target “weak” alignment is not predictive of performance on LAReQA. This finding underscores our claim that language-agnostic retrieval is a substantively new kind of cross-lingual evaluation, and suggests that measuring both weak and strong alignment will be important for improving cross-lingual systems going forward. We release our dataset and evaluation code at https://github.com/google-research-datasets/lareqa.
View details
Character-Level Language Modeling with Deeper Self-Attention
Rami Al-Rfou
DK Choe
Llion Jones
Thirty-Third AAAI Conference on Artificial Intelligence (2019)
Preview abstract
LSTMs and other RNN variants have shown strong performance on character-level language modeling.
These models are typically trained using truncated backpropagation through time, and it is common to assume that their success stems from their ability to remember long-term contexts.
In this paper, we show that a deep (64-layer) transformer model with fixed context outperforms RNN variants by a large margin, achieving 1.13 bits per character on text8.
To get good results at this depth, we show that it is important to add auxiliary losses, both at intermediate network layers and intermediate sequence positions.
View details
Preview abstract
Purely character-based language models have been lagging in quality on large scale datasets, and state-of-the-art language models currently rely on word tokenization. It has been assumed that injecting the prior knowledge of a tokenizer into the language model is essential to achieving competitive results.
In this paper, we show that, contrary to this conventional wisdom, tokenizer-free language models with sufficient capacity can achieve competitive performance on a large scale dataset. We train a vanilla transformer network with 40 self-attention layers on the One Billion Word (lm1b) benchmark and achieve new state of the art results for tokenizer-free language models, pushing these models to be on par with their word-based counterparts.
View details
