David Weiss
My research focuses on improving machine learning for tough, practical applications that have difficult constraints. At Google my team works to scale ML for natural language processing.
Some of our notable projects are SyntaxNet and Parsey McParseface, and the Chrome Compact Language Detector, which runs on all devices.
Prior to Google: I completed my Ph.D in 2014 at the University of Pennsylvania with Ben Taskar, as part of the GRASP Lab. Previously, I was a research specialist at the Princeton Computational Memory Lab, and I graduated from Princeton University with a degree in Computer Science and a certificate in Neuroscience in 2007. My advisors were Dave Blei (CS) and Ken Norman (Psychology).
Fun fact: I was a member of Team Dinosaur Planet, Grand Prize Team, and The Ensemble, the greatest Netflix Prize wrecking crew ever created. Our team was written up in the New York Times.
Research Areas
Authored Publications
Sort By
Learning Cross-Context Entity Representations from Text
Jeffrey Ling
Zifei Shan
Thibault Févry
arXiv (2020)
Preview abstract
Language modeling tasks, in which words, or word-pieces, are predicted on the basis of a local context, have been very effective for learning word embeddings and context dependent representations of phrases. Motivated by the observation that efforts to code world knowledge into machine readable knowledge bases or human readable encyclopedias tend to be entity-centric, we investigate the use of a fill-in-the-blank task to learn context independent representations of entities from the text contexts in which those entities were mentioned. We show that large scale training of neural models allows us to learn high quality entity representations, and we demonstrate successful results on four domains: (1) existing entity-level typing benchmarks, including a 64% error reduction over previous work on TypeNet (Murty et al., 2018); (2) a novel few-shot category reconstruction task; (3) existing entity linking benchmarks, where we match the state-of-the-art on CoNLL-Aida without linking-specific features and obtain a score of 89.8% on TAC-KBP 2010 without using any alias table, external knowledge base or in domain training data and (4) answering trivia questions, which uniquely identify entities. Our global entity representations encode fine-grained type categories, such as Scottish footballers, and can answer trivia questions such as: Who was the last inmate of Spandau jail in Berlin?
View details
Preview abstract
Language modeling tasks, in which words are predicted on the basis of a local context, have been very effective for learning word embeddings and context dependent representations of phrases. Motivated by the observation that efforts to code world knowledge into machine readable knowledge bases tend to be entity-centric, we investigate the use of a fill-in-the-blank task to learn context independent representations of entities from the contexts in which those entities were mentioned. We show that large scale training of neural models allows us to learn extremely high fidelity entity typing information, which we demonstrate with few-shot reconstruction of Wikipedia categories. Our learning approach is powerful enough to encode specialized topics such as Giro d'Italia cyclists.
View details
Preview abstract
We address the problem of fine-grained multilingual language identification: providing a language code for every token in a sentence, including codemixed text containing multiple languages. Such text is increasingly prevalent online, in documents, social media, and message boards. In this paper, we show that a feed-forward network with a simple globally constrained decoder can accurately and rapidly label both codemixed and monolingual text in 100 languages and 100 language pairs. This model outperforms previously published multilingual approaches in terms of both accuracy and speed, yielding an 800x speed-up and a 19.2% averaged absolute gain on three codemixed datasets.
View details
Preview abstract
A wide variety of neural-network architectures have been proposed for the task of Chinese word segmentation. Surprisingly, we find that a bidirectional LSTM model, when combined with standard deep learning techniques and best practices, can achieve better accuracy on many of the popular datasets as compared to models based on more complex neuralnetwork architectures. Furthermore, our error analysis shows that out-of-vocabulary words remain challenging for neural-network models, and many of the remaining errors are unlikely to be fixed through architecture changes. Instead, more effort should be made on exploring resources for further improvement.
View details
Linguistically-Informed Self-Attention for Semantic Role Labeling
Emma Strubell
Pat Verga
Andrew McCallum
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018)
Preview abstract
Current state-of-the-art semantic role labeling (SRL) uses a deep neural network with no explicit linguistic features. However, prior work has shown that gold syntax trees can dramatically improve SRL decoding, suggesting the possibility of increased accuracy from explicit modeling of syntax. In this work, we present linguistically-informed self-attention (LISA): a neural network model that combines multi-head self-attention with multi-task learning across dependency parsing, part-of-speech tagging, predicate detection and SRL. Unlike previous models which require significant pre-processing to prepare linguistic features, LISA can incorporate syntax using merely raw tokens as input, encoding the sequence only once to simultaneously perform parsing, predicate detection and role labeling for all predicates. Syntax is incorporated by training one attention head to attend to syntactic parents for each token. Moreover, if a high-quality syntactic parse is already available, it can be beneficially injected at test time without re-training our SRL model. In experiments on CoNLL-2005 SRL, LISA achieves new state-of-the-art performance for a model using predicted predicates and standard word embeddings, attaining 2.5 F1 absolute higher than the previous state-of-the-art on newswire and more than 3.5 F1 on out-of-domain data, nearly 10% reduction in error. On ConLL-2012 English SRL we also show an improvement of more than 2.5 F1. LISA also out-performs the state-of-the-art with contextually-encoded (ELMo) word representations, by nearly 1.0 F1 on news and more than 2.0 F1 on out-of-domain text.
View details
Natural Language Processing with Small Feed-Forward Networks
Jan A. Botha
Emily Pitler
Anton Bakalov
Alex Salcianu
Ryan Mcdonald
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Association for Computational Linguistics, Copenhagen, Denmark, 2879–2885
Preview abstract
We show that small and shallow feedforward neural networks can achieve near state-of-the-art results on a range of unstructured and structured language processing tasks while being considerably cheaper in memory and computational requirements than deep recurrent models. Motivated by resource-constrained environments like mobile phones, we showcase simple techniques for obtaining such small neural network models, and investigate different tradeoffs when deciding how to allocate a small memory budget.
View details
Globally Normalized Transition-Based Neural Networks
Association for Computational Linguistics (2016)
Preview abstract
We introduce a globally normalized transition-based neural network
model that achieves state-of-the-art part-of-speech tagging,
dependency parsing and sentence compression results. Our model is a
simple feed-forward neural network that operates on a task-specific
transition system, yet achieves comparable or better accuracies than
recurrent models.
We discuss the importance of global as opposed to local normalization:
a key insight is that the label bias problem implies that
globally
normalized models can be strictly more expressive
than locally normalized models.
View details
Preview abstract
Traditional syntax models typically leverage part-of-speech (POS) information by constructing features from hand-tuned templates. We demonstrate that a better approach is to utilize POS tags as a regularizer of learned representations. We propose a simple method for learning a stacked pipeline of models which we call “stack-propagation”. We apply this to dependency parsing and tagging, where we use the hidden layer of the tagger network as a representation of the input tokens for the parser. At test time, our parser does not require predicted POS tags. On 19 languages from the Universal Dependencies, our method is 1.3% (absolute) more accurate than a state-of-the-art graph-based approach and 2.7% more accurate than the most comparable greedy model.
View details
Structured Training for Neural Network Transition-Based Parsing
Preview
Proceedings of the 53th Annual Meeting of the Association for Computational Linguistics (ACL '15) (2015)
Improved Transition-Based Parsing and Tagging with Neural Networks
Preview
Greg Coppola
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing (EMNLP '15)
