Mandy Guo


2023

pdf bib
mLongT5: A Multilingual and Efficient Text-To-Text Transformer for Longer Sequences
David Uthus | Santiago Ontanon | Joshua Ainslie | Mandy Guo
Findings of the Association for Computational Linguistics: EMNLP 2023

We present our work on developing a multilingual, efficient text-to-text transformer that is suitable for handling long inputs. This model, called mLongT5, builds upon the architecture of LongT5, while leveraging the multilingual datasets used for pretraining mT5 and the pretraining tasks of UL2. We evaluate this model on a variety of multilingual summarization and question-answering tasks, and the results show stronger performance for mLongT5 when compared to existing multilingual models such as mBART or M-BERT.

pdf bib
A Suite of Generative Tasks for Multi-Level Multimodal Webpage Understanding
Andrea Burns | Krishna Srinivasan | Joshua Ainslie | Geoff Brown | Bryan Plummer | Kate Saenko | Jianmo Ni | Mandy Guo
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Webpages have been a rich, scalable resource for vision-language and language only tasks. Yet only pieces of webpages are kept in existing datasets: image-caption pairs, long text articles, or raw HTML, never all in one place. Webpage tasks have resultingly received little attention and structured image-text data left underused. To study multimodal webpage understanding, we introduce the Wikipedia Webpage suite (WikiWeb2M) containing 2M pages with all of the associated image, text, and structure data. We verify its utility on three generative tasks: page description generation, section summarization, and contextual image captioning. We design a novel attention mechanism Prefix Global, which selects the most relevant image and text content as global tokens to attend to the rest of the webpage for context. By using page structure to separate such tokens, it performs better than full attention with lower computational complexity. Extensive experiments show that the new data in WikiWeb2M improves task performance compared to prior work.

pdf bib
CoLT5: Faster Long-Range Transformers with Conditional Computation
Joshua Ainslie | Tao Lei | Michiel de Jong | Santiago Ontanon | Siddhartha Brahma | Yury Zemlyanskiy | David Uthus | Mandy Guo | James Lee-Thorp | Yi Tay | Yun-Hsuan Sung | Sumit Sanghai
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing

Many natural language processing tasks benefit from long inputs, but processing long documents with Transformers is expensive – not only due to quadratic attention complexity but also from applying feedforward and projection layers to every token. However, not all tokens are equally important, especially for longer documents. We propose CoLT5, a long-input Transformer model that builds on this intuition by employing conditional computation, devoting more resources to important tokens in both feedforward and attention layers. We show that CoLT5 achieves stronger performance than LongT5 with much faster training and inference, achieving SOTA on the long-input SCROLLS benchmark. Moreover, CoLT5 can effectively and tractably make use of extremely long inputs, showing strong gains up to 64k input length.

2022

pdf bib
LongT5: Efficient Text-To-Text Transformer for Long Sequences
Mandy Guo | Joshua Ainslie | David Uthus | Santiago Ontanon | Jianmo Ni | Yun-Hsuan Sung | Yinfei Yang
Findings of the Association for Computational Linguistics: NAACL 2022

Recent work has shown that either (1) increasing the input length or (2) increasing model size can improve the performance of Transformer-based neural models. In this paper, we present LongT5, a new model that explores the effects of scaling both the input length and model size at the same time. Specifically, we integrate attention ideas from long-input transformers (ETC), and adopt pre-training strategies from summarization pre-training (PEGASUS) into the scalable T5 architecture. The result is a new attention mechanism we call Transient Global (TGlobal), which mimics ETC’s local/global attention mechanism, but without requiring additional side-inputs. We are able to achieve state-of-the-art results on several summarization and question answering tasks, as well as outperform the original T5 models on these tasks. We have open sourced our architecture and training code, as well as our pre-trained model checkpoints.

2021

pdf bib
TextSETTR: Few-Shot Text Style Extraction and Tunable Targeted Restyling
Parker Riley | Noah Constant | Mandy Guo | Girish Kumar | David Uthus | Zarana Parekh
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

We present a novel approach to the problem of text style transfer. Unlike previous approaches requiring style-labeled training data, our method makes use of readily-available unlabeled text by relying on the implicit connection in style between adjacent sentences, and uses labeled data only at inference time. We adapt T5 (Raffel et al., 2020), a strong pretrained text-to-text model, to extract a style vector from text and use it to condition the decoder to perform style transfer. As our label-free training results in a style vector space encoding many facets of style, we recast transfers as “targeted restyling” vector operations that adjust specific attributes of the input while preserving others. We demonstrate that training on unlabeled Amazon reviews data results in a model that is competitive on sentiment transfer, even compared to models trained fully on labeled data. Furthermore, applying our novel method to a diverse corpus of unlabeled web text results in a single model capable of transferring along multiple dimensions of style (dialect, emotiveness, formality, politeness, sentiment) despite no additional training and using only a handful of exemplars at inference time.

pdf bib
Neural Retrieval for Question Answering with Cross-Attention Supervised Data Augmentation
Yinfei Yang | Ning Jin | Kuo Lin | Mandy Guo | Daniel Cer
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

Early fusion models with cross-attention have shown better-than-human performance on some question answer benchmarks, while it is a poor fit for retrieval since it prevents pre-computation of the answer representations. We present a supervised data mining method using an accurate early fusion model to improve the training of an efficient late fusion retrieval model. We first train an accurate classification model with cross-attention between questions and answers. The cross-attention model is then used to annotate additional passages in order to generate weighted training examples for a neural retrieval model. The resulting retrieval model with additional data significantly outperforms retrieval models directly trained with gold annotations on Precision at N (P@N) and Mean Reciprocal Rank (MRR).

pdf bib
MultiReQA: A Cross-Domain Evaluation forRetrieval Question Answering Models
Mandy Guo | Yinfei Yang | Daniel Cer | Qinlan Shen | Noah Constant
Proceedings of the Second Workshop on Domain Adaptation for NLP

Retrieval question answering (ReQA) is the task of retrieving a sentence-level answer to a question from an open corpus (Ahmad et al.,2019).This dataset paper presents MultiReQA, a new multi-domain ReQA evaluation suite composed of eight retrieval QA tasks drawn from publicly available QA datasets. We explore systematic retrieval based evaluation and transfer learning across domains over these datasets using a number of strong base-lines including two supervised neural models, based on fine-tuning BERT and USE-QA models respectively, as well as a surprisingly effective information retrieval baseline, BM25. Five of these tasks contain both training and test data, while three contain test data only. Performing cross training on the five tasks with training data shows that while a general model covering all domains is achievable, the best performance is often obtained by training exclusively on in-domain data.

pdf bib
MURAL: Multimodal, Multitask Representations Across Languages
Aashi Jain | Mandy Guo | Krishna Srinivasan | Ting Chen | Sneha Kudugunta | Chao Jia | Yinfei Yang | Jason Baldridge
Findings of the Association for Computational Linguistics: EMNLP 2021

Both image-caption pairs and translation pairs provide the means to learn deep representations of and connections between languages. We use both types of pairs in MURAL (MUltimodal, MUltitask Representations Across Languages), a dual encoder that solves two tasks: 1) image-text matching and 2) translation pair matching. By incorporating billions of translation pairs, MURAL extends ALIGN (Jia et al.)–a state-of-the-art dual encoder learned from 1.8 billion noisy image-text pairs. When using the same encoders, MURAL’s performance matches or exceeds ALIGN’s cross-modal retrieval performance on well-resourced languages across several datasets. More importantly, it considerably improves performance on under-resourced languages, showing that text-text learning can overcome a paucity of image-caption examples for these languages. On the Wikipedia Image-Text dataset, for example, MURAL-base improves zero-shot mean recall by 8.1% on average for eight under-resourced languages and by 6.8% on average when fine-tuning. We additionally show that MURAL’s text representations cluster not only with respect to genealogical connections but also based on areal linguistics, such as the Balkan Sprachbund.

2020

pdf bib
Wiki-40B: Multilingual Language Model Dataset
Mandy Guo | Zihang Dai | Denny Vrandečić | Rami Al-Rfou
Proceedings of the Twelfth Language Resources and Evaluation Conference

We propose a new multilingual language model benchmark that is composed of 40+ languages spanning several scripts and linguistic families. With around 40 billion characters, we hope this new resource will accelerate the research of multilingual modeling. We train monolingual causal language models using a state-of-the-art model (Transformer-XL) establishing baselines for many languages. We also introduce the task of multilingual causal language modeling where we train our model on the combined text of 40+ languages from Wikipedia with different vocabulary sizes and evaluate on the languages individually. We released the cleaned-up text of 40+ Wikipedia language editions, the corresponding trained monolingual language models, and several multilingual language models with different fixed vocabulary sizes.

pdf bib
Multilingual Universal Sentence Encoder for Semantic Retrieval
Yinfei Yang | Daniel Cer | Amin Ahmad | Mandy Guo | Jax Law | Noah Constant | Gustavo Hernandez Abrego | Steve Yuan | Chris Tar | Yun-hsuan Sung | Brian Strope | Ray Kurzweil
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

We present easy-to-use retrieval focused multilingual sentence embedding models, made available on TensorFlow Hub. The models embed text from 16 languages into a shared semantic space using a multi-task trained dual-encoder that learns tied cross-lingual representations via translation bridge tasks (Chidambaram et al., 2018). The models achieve a new state-of-the-art in performance on monolingual and cross-lingual semantic retrieval (SR). Competitive performance is obtained on the related tasks of translation pair bitext retrieval (BR) and retrieval question answering (ReQA). On transfer learning tasks, our multilingual embeddings approach, and in some cases exceed, the performance of English only sentence embeddings.

2019

pdf bib
Hierarchical Document Encoder for Parallel Corpus Mining
Mandy Guo | Yinfei Yang | Keith Stevens | Daniel Cer | Heming Ge | Yun-hsuan Sung | Brian Strope | Ray Kurzweil
Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)

We explore using multilingual document embeddings for nearest neighbor mining of parallel data. Three document-level representations are investigated: (i) document embeddings generated by simply averaging multilingual sentence embeddings; (ii) a neural bag-of-words (BoW) document encoding model; (iii) a hierarchical multilingual document encoder (HiDE) that builds on our sentence-level model. The results show document embeddings derived from sentence-level averaging are surprisingly effective for clean datasets, but suggest models trained hierarchically at the document-level are more effective on noisy data. Analysis experiments demonstrate our hierarchical models are very robust to variations in the underlying sentence embedding quality. Using document embeddings trained with HiDE achieves the state-of-the-art on United Nations (UN) parallel document mining, 94.9% P@1 for en-fr and 97.3% P@1 for en-es.

2018

pdf bib
Effective Parallel Corpus Mining using Bilingual Sentence Embeddings
Mandy Guo | Qinlan Shen | Yinfei Yang | Heming Ge | Daniel Cer | Gustavo Hernandez Abrego | Keith Stevens | Noah Constant | Yun-Hsuan Sung | Brian Strope | Ray Kurzweil
Proceedings of the Third Conference on Machine Translation: Research Papers

This paper presents an effective approach for parallel corpus mining using bilingual sentence embeddings. Our embedding models are trained to produce similar representations exclusively for bilingual sentence pairs that are translations of each other. This is achieved using a novel training method that introduces hard negatives consisting of sentences that are not translations but have some degree of semantic similarity. The quality of the resulting embeddings are evaluated on parallel corpus reconstruction and by assessing machine translation systems trained on gold vs. mined sentence pairs. We find that the sentence embeddings can be used to reconstruct the United Nations Parallel Corpus (Ziemski et al., 2016) at the sentence-level with a precision of 48.9% for en-fr and 54.9% for en-es. When adapted to document-level matching, we achieve a parallel document matching accuracy that is comparable to the significantly more computationally intensive approach of Uszkoreit et al. (2010). Using reconstructed parallel data, we are able to train NMT models that perform nearly as well as models trained on the original data (within 1-2 BLEU).