Jacob Devlin


2021

pdf bib
Multi-Vector Attention Models for Deep Re-ranking
Giulio Zhou | Jacob Devlin
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Large-scale document retrieval systems often utilize two styles of neural network models which live at two different ends of the joint computation vs. accuracy spectrum. The first style is dual encoder (or two-tower) models, where the query and document representations are computed completely independently and combined with a simple dot product operation. The second style is cross-attention models, where the query and document features are concatenated in the input layer and all computation is based on the joint query-document representation. Dual encoder models are typically used for retrieval and deep re-ranking, while cross-attention models are typically used for shallow re-ranking. In this paper, we present a lightweight architecture that explores this joint cost vs. accuracy trade-off based on multi-vector attention (MVA). We thoroughly evaluate our method on the MS-MARCO passage retrieval dataset and show how to efficiently trade off retrieval accuracy with joint computation and offline document storage cost. We show that a highly compressed document representation and inexpensive joint computation can be achieved through a combination of learned pooling tokens and aggressive downprojection. Our code and model checkpoints are open-source and available on GitHub.

2019

pdf bib
Natural Questions: A Benchmark for Question Answering Research
Tom Kwiatkowski | Jennimaria Palomaki | Olivia Redfield | Michael Collins | Ankur Parikh | Chris Alberti | Danielle Epstein | Illia Polosukhin | Jacob Devlin | Kenton Lee | Kristina Toutanova | Llion Jones | Matthew Kelcey | Ming-Wei Chang | Andrew M. Dai | Jakob Uszkoreit | Quoc Le | Slav Petrov
Transactions of the Association for Computational Linguistics, Volume 7

We present the Natural Questions corpus, a question answering data set. Questions consist of real anonymized, aggregated queries issued to the Google search engine. An annotator is presented with a question along with a Wikipedia page from the top 5 search results, and annotates a long answer (typically a paragraph) and a short answer (one or more entities) if present on the page, or marks null if no long/short answer is present. The public release consists of 307,373 training examples with single annotations; 7,830 examples with 5-way annotations for development data; and a further 7,842 examples with 5-way annotated sequestered as test data. We present experiments validating quality of the data. We also describe analysis of 25-way annotations on 302 examples, giving insights into human variability on the annotation task. We introduce robust metrics for the purposes of evaluating question answering systems; demonstrate high human upper bounds on these metrics; and establish baseline results using competitive methods drawn from related literature.

pdf bib
Zero-Shot Entity Linking by Reading Entity Descriptions
Lajanugen Logeswaran | Ming-Wei Chang | Kenton Lee | Kristina Toutanova | Jacob Devlin | Honglak Lee
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We present the zero-shot entity linking task, where mentions must be linked to unseen entities without in-domain labeled data. The goal is to enable robust transfer to highly specialized domains, and so no metadata or alias tables are assumed. In this setting, entities are only identified by text descriptions, and models must rely strictly on language understanding to resolve the new entities. First, we show that strong reading comprehension models pre-trained on large unlabeled data can be used to generalize to unseen entities. Second, we propose a simple and effective adaptive pre-training strategy, which we term domain-adaptive pre-training (DAP), to address the domain shift problem associated with linking unseen entities in a new domain. We present experiments on a new dataset that we construct for this task and show that DAP improves over strong pre-training baselines, including BERT. The data and code are available at https://github.com/lajanugen/zeshel.

pdf bib
Synthetic QA Corpora Generation with Roundtrip Consistency
Chris Alberti | Daniel Andor | Emily Pitler | Jacob Devlin | Michael Collins
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics

We introduce a novel method of generating synthetic question answering corpora by combining models of question generation and answer extraction, and by filtering the results to ensure roundtrip consistency. By pretraining on the resulting corpora we obtain significant improvements on SQuAD2 and NQ, establishing a new state-of-the-art on the latter. Our synthetic data generation models, for both question generation and answer extraction, can be fully reproduced by finetuning a publicly available BERT model on the extractive subsets of SQuAD2 and NQ. We also describe a more powerful variant that does full sequence-to-sequence pretraining for question generation, obtaining exact match and F1 at less than 0.1% and 0.4% from human performance on SQuAD2.

pdf bib
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Jacob Devlin | Ming-Wei Chang | Kenton Lee | Kristina Toutanova
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

We introduce a new language representation model called BERT, which stands for Bidirectional Encoder Representations from Transformers. Unlike recent language representation models (Peters et al., 2018a; Radford et al., 2018), BERT is designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers. As a result, the pre-trained BERT model can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks, such as question answering and language inference, without substantial task-specific architecture modifications. BERT is conceptually simple and empirically powerful. It obtains new state-of-the-art results on eleven natural language processing tasks, including pushing the GLUE score to 80.5 (7.7 point absolute improvement), MultiNLI accuracy to 86.7% (4.6% absolute improvement), SQuAD v1.1 question answering Test F1 to 93.2 (1.5 point absolute improvement) and SQuAD v2.0 Test F1 to 83.1 (5.1 point absolute improvement).

2018

pdf bib
Universal Neural Machine Translation for Extremely Low Resource Languages
Jiatao Gu | Hany Hassan | Jacob Devlin | Victor O.K. Li
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

In this paper, we propose a new universal machine translation approach focusing on languages with a limited amount of parallel data. Our proposed approach utilizes a transfer-learning approach to share lexical and sentence level representations across multiple source languages into one target language. The lexical part is shared through a Universal Lexical Representation to support multi-lingual word-level sharing. The sentence-level sharing is represented by a model of experts from all source languages that share the source encoders with all other languages. This enables the low-resource language to utilize the lexical and sentence representations of the higher resource languages. Our approach is able to achieve 23 BLEU on Romanian-English WMT2016 using a tiny parallel corpus of 6k sentences, compared to the 18 BLEU of strong baseline system which uses multi-lingual training and back-translation. Furthermore, we show that the proposed approach can achieve almost 20 BLEU on the same dataset through fine-tuning a pre-trained multi-lingual system in a zero-shot setting.

2017

pdf bib
Sharp Models on Dull Hardware: Fast and Accurate Neural Machine Translation Decoding on the CPU
Jacob Devlin
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Attentional sequence-to-sequence models have become the new standard for machine translation, but one challenge of such models is a significant increase in training and decoding cost compared to phrase-based systems. In this work we focus on efficient decoding, with a goal of achieving accuracy close the state-of-the-art in neural machine translation (NMT), while achieving CPU decoding speed/throughput close to that of a phrasal decoder. We approach this problem from two angles: First, we describe several techniques for speeding up an NMT beam search decoder, which obtain a 4.4x speedup over a very efficient baseline decoder without changing the decoder output. Second, we propose a simple but powerful network architecture which uses an RNN (GRU/LSTM) layer at bottom, followed by a series of stacked fully-connected layers applied at every timestep. This architecture achieves similar accuracy to a deep recurrent model, at a small fraction of the training and decoding cost. By combining these techniques, our best system achieves a very competitive accuracy of 38.3 BLEU on WMT English-French NewsTest2014, while decoding at 100 words/sec on single-threaded CPU. We believe this is the best published accuracy/speed trade-off of an NMT system.

2016

pdf bib
Visual Storytelling
Ting-Hao Kenneth Huang | Francis Ferraro | Nasrin Mostafazadeh | Ishan Misra | Aishwarya Agrawal | Jacob Devlin | Ross Girshick | Xiaodong He | Pushmeet Kohli | Dhruv Batra | C. Lawrence Zitnick | Devi Parikh | Lucy Vanderwende | Michel Galley | Margaret Mitchell
Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Generating Natural Questions About an Image
Nasrin Mostafazadeh | Ishan Misra | Jacob Devlin | Margaret Mitchell | Xiaodong He | Lucy Vanderwende
Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2015

pdf bib
A Survey of Current Datasets for Vision and Language Research
Francis Ferraro | Nasrin Mostafazadeh | Ting-Hao Huang | Lucy Vanderwende | Jacob Devlin | Michel Galley | Margaret Mitchell
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Pre-Computable Multi-Layer Neural Network Language Models
Jacob Devlin | Chris Quirk | Arul Menezes
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
Statistical Machine Translation Features with Multitask Tensor Networks
Hendra Setiawan | Zhongqiang Huang | Jacob Devlin | Thomas Lamar | Rabih Zbib | Richard Schwartz | John Makhoul
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

pdf bib
Language Models for Image Captioning: The Quirks and What Works
Jacob Devlin | Hao Cheng | Hao Fang | Saurabh Gupta | Li Deng | Xiaodong He | Geoffrey Zweig | Margaret Mitchell
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)

2014

pdf bib
Fast and Robust Neural Network Joint Models for Statistical Machine Translation
Jacob Devlin | Rabih Zbib | Zhongqiang Huang | Thomas Lamar | Richard Schwartz | John Makhoul
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

2013

pdf bib
Factored Soft Source Syntactic Constraints for Hierarchical Machine Translation
Zhongqiang Huang | Jacob Devlin | Rabih Zbib
Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing

2012

pdf bib
Unsupervised Morphology Rivals Supervised Morphology for Arabic MT
David Stallard | Jacob Devlin | Michael Kayser | Yoong Keok Lee | Regina Barzilay
Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

pdf bib
Automatic Tune Set Generation for Machine Translation with Limited Indomain Data
Jinying Chen | Jacob Devlin | Huaigu Cao | Rohit Prasad | Premkumar Natarajan
Proceedings of the 16th Annual conference of the European Association for Machine Translation

pdf bib
Machine Translation of Arabic Dialects
Rabih Zbib | Erika Malchiodi | Jacob Devlin | David Stallard | Spyros Matsoukas | Richard Schwartz | John Makhoul | Omar F. Zaidan | Chris Callison-Burch
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Trait-Based Hypothesis Selection For Machine Translation
Jacob Devlin | Spyros Matsoukas
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

2011

pdf bib
System Combination Using Discriminative Cross-Adaptation
Jacob Devlin | Antti-Veikko Rosti | Sankaranarayanan Ananthakrishnan | Spyros Matsoukas
Proceedings of 5th International Joint Conference on Natural Language Processing