Serhii Havrylov
2020
Obfuscation for Privacypreserving Syntactic Parsing
Zhifeng Hu

Serhii Havrylov

Ivan Titov

Shay B. Cohen
Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies
The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacypreserving transformation on natural language data, inspired by homomorphic encryption. Our primary tool is obfuscation, relying on the properties of natural language. Specifically, a given English text is obfuscated using a neural model that aims to preserve the syntactic relationships of the original sentence so that the obfuscated sentence can be parsed instead of the original one. The model works at the word level, and learns to obfuscate each word separately by changing it into a new word that has a similar syntactic role. The text obfuscated by our model leads to better performance on three syntactic parsers (two dependency and one constituency parsers) in comparison to an upperbound random substitution baseline. More specifically, the results demonstrate that as more terms are obfuscated (by their part of speech), the substitution upper bound significantly degrades, while the neural model maintains a relatively high performing parser. All of this is done without much sacrifice of privacy compared to the random substitution upper bound. We also further analyze the results, and discover that the substituted words have similar syntactic properties, but different semantic content, compared to the original words.
2019
Cooperative Learning of Disjoint Syntax and Semantics
Serhii Havrylov

Germán Kruszewski

Armand Joulin
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)
There has been considerable attention devoted to models that learn to jointly infer an expression’s syntactic structure and its semantics. Yet, Nangia and Bowman (2018) has recently shown that the current best systems fail to learn the correct parsing strategy on mathematical expressions generated from a simple contextfree grammar. In this work, we present a recursive model inspired by Choi et al. (2018) that reaches near perfect accuracy on this task. Our model is composed of two separated modules for syntax and semantics. They are cooperatively trained with standard continuous and discrete optimisation schemes. Our model does not require any linguistic structure for supervision, and its recursive nature allows for outofdomain generalisation. Additionally, our approach performs competitively on several natural language tasks, such as Natural Language Inference and Sentiment Analysis.
2018
Embedding Words as Distributions with a Bayesian Skipgram Model
Arthur Bražinskas

Serhii Havrylov

Ivan Titov
Proceedings of the 27th International Conference on Computational Linguistics
We introduce a method for embedding words as probability densities in a lowdimensional space. Rather than assuming that a word embedding is fixed across the entire text collection, as in standard word embedding methods, in our Bayesian model we generate it from a wordspecific prior density for each occurrence of a given word. Intuitively, for each word, the prior density encodes the distribution of its potential ‘meanings’. These prior densities are conceptually similar to Gaussian embeddings of ėwcitevilnis2014word. Interestingly, unlike the Gaussian embeddings, we can also obtain contextspecific densities: they encode uncertainty about the sense of a word given its context and correspond to the approximate posterior distributions within our model. The contextdependent densities have many potential applications: for example, we show that they can be directly used in the lexical substitution task. We describe an effective estimation method based on the variational autoencoding framework. We demonstrate the effectiveness of our embedding technique on a range of standard benchmarks.
Search
Coauthors
 Ivan Titov 2
 Zhifeng Hu 1
 Shay B. Cohen 1
 Arthur Bražinskas 1
 Germán Kruszewski 1
 show all...