paper-with-me

Papers

Neural Syntactic Generative Models with Exact Marginalization

2018-06-01 · NAACL 2018 6 · Jan Buys, Phil Blunsom

We present neural syntactic generative models with exact marginalization that support both dependency parsing and language modeling. Exact marginalization is made tractable through dynamic programming over shift-reduce parsing and minimal RNN-based feature sets. Our algorithms complement previous approaches by supporting batched training and enabling online computation of next word probabilities. For supervised dependency parsing, our model achieves a state-of-the-art result among generative approaches. We also report empirical results on unsupervised syntactic models and their role in language modeling. We find that our model formulation of latent dependencies with exact marginalization do not lead to better intrinsic language modeling performance than vanilla RNNs, and that parsing accuracy is not correlated with language modeling perplexity in stack-based models.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Dependency ParsingLanguage ModelingLanguage ModellingTransition-Based Dependency Parsing

Similar Papers 제목 키워드 기반

Efficient Marginalization of Discrete and Structured Latent Variables via Sparsity

2020-07-03 · NeurIPS 2020 12 · Gonçalo M. Correia, Vlad Niculae, Wilker Aziz, André F. T. Martins

Training neural network models with discrete (categorical or structured) latent variables can be computationally challenging, due to the need for marginalization over large or combinatorial sets. To circumvent this issue…

Improving NLP through Marginalization of Hidden Syntactic Structure

2012-07-01 · EMNLP 2012 7 · Jason Naradowsky, Sebastian Riedel, David Smith
Named Entity Recognition (NER)Relation ExtractionSemantic Role Labeling

Evidential Softmax for Sparse Multimodal Distributions in Deep Generative Models

2021-10-27 · NeurIPS 2021 12 · Phil Chen, Masha Itkina, Ransalu Senanayake, Mykel J. Kochenderfer

Many applications of generative models rely on the marginalization of their high-dimensional output probability distributions. Normalization functions that yield sparse probability distributions can make exact marginaliz…

Generative Marginalization Models

2023-10-19 · Sulin Liu, Peter J. Ramadge, Ryan P. Adams

We introduce marginalization models (MAMs), a new family of generative models for high-dimensional discrete data. They offer scalable and flexible generative modeling by explicitly modeling all induced marginal distribut…

Explaining Away Syntactic Structure in Semantic Document Representations

2018-06-05 · Erik Holmer, Andreas Marfurt

Most generative document models act on bag-of-words input in an attempt to focus on the semantic content and thereby partially forego syntactic information. We argue that it is preferable to keep the original word order …