Timothy Dozat
YOU?
Author Swipe
View article: Universal Dependencies
Universal Dependencies Open
Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research f…
View article: FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction
FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction Open
The recent advent of self-supervised pre-training techniques has led to a surge in the use of multimodal learning in form document understanding. However, existing approaches that extend the mask language modeling to other modalities requi…
View article: FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction
FormNetV2: Multimodal Graph Contrastive Learning for Form Document Information Extraction Open
Chen-Yu Lee, Chun-Liang Li, Hao Zhang, Timothy Dozat, Vincent Perot, Guolong Su, Xiang Zhang, Kihyuk Sohn, Nikolay Glushnev, Renshen Wang, Joshua Ainslie, Shangbang Long, Siyang Qin, Yasuhisa Fujii, Nan Hua, Tomas Pfister. Proceedings of t…
View article: FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation
FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation Open
We present FRMT, a new dataset and evaluation benchmark for Few-shot Region-aware Machine Translation, a type of style-targeted translation. The dataset consists of professional translations from English into two regional variants each of …
View article: Dialect-robust Evaluation of Generated Text
Dialect-robust Evaluation of Generated Text Open
Jiao Sun, Thibault Sellam, Elizabeth Clark, Tu Vu, Timothy Dozat, Dan Garrette, Aditya Siddhant, Jacob Eisenstein, Sebastian Gehrmann. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long …
View article: Dialect-robust Evaluation of Generated Text
Dialect-robust Evaluation of Generated Text Open
Evaluation metrics that are not robust to dialect variation make it impossible to tell how well systems perform for many groups of users, and can even penalize systems for producing text in lower-resource dialects. However, currently, ther…
View article: FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation
FRMT: A Benchmark for Few-Shot Region-Aware Machine Translation Open
We present FRMT, a new dataset and evaluation benchmark for Few-shot Region-aware Machine Translation, a type of style-targeted translation. The dataset consists of professional translations from English into two regional variants each of …
View article: FormNet: Structural Encoding beyond Sequential Modeling in Form Document\n Information Extraction
FormNet: Structural Encoding beyond Sequential Modeling in Form Document\n Information Extraction Open
Sequence modeling has demonstrated state-of-the-art performance on natural\nlanguage and document understanding tasks. However, it is challenging to\ncorrectly serialize tokens in form-like documents in practice due to their\nvariety of la…
View article: FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction
FormNet: Structural Encoding beyond Sequential Modeling in Form Document Information Extraction Open
Sequence modeling has demonstrated state-of-the-art performance on natural language and document understanding tasks. However, it is challenging to correctly serialize tokens in form-like documents in practice due to their variety of layou…
View article: Universal Dependencies 2.8.1
Universal Dependencies 2.8.1 Open
Universal Dependencies is a project that seeks to develop cross-linguistically consistent treebank annotation for many languages, with the goal of facilitating multilingual parser development, cross-lingual learning, and parsing research f…
View article: Universal Dependencies for Multilingual Open Information Extraction
Universal Dependencies for Multilingual Open Information Extraction Open
In this paper, we present our approach for Multilingual Open Information Extraction. Our sequence labeling based approach builds only on Universal Dependency representation to capture OpenIE’s regularities and to perform Cross-lingual Mult…
View article: Universal Dependency Parsing from Scratch
Universal Dependency Parsing from Scratch Open
This paper describes Stanford's system at the CoNLL 2018 UD Shared Task. We introduce a complete neural pipeline system that takes raw text as input, and performs all tasks required by the shared task, ranging from tokenization and sentenc…
View article: Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning
Proceedings of the Shared Task on Cross-Framework Meaning Representation Parsing at the 2019 Conference on Natural Language Learning Open
We are excited (and a little relieved) to present the proceedings from the 2019 Shared Task on Cross-Framework Meaning Representation Parsing (MRP) at the Conference for Computational Language Learning (CoNLL).This volume provides linguist…
View article: Simpler but More Accurate Semantic Dependency Parsing
Simpler but More Accurate Semantic Dependency Parsing Open
While syntactic dependency annotations concentrate on the surface or functional structure of a sentence, semantic dependency annotations aim to capture between-word relationships that are more closely related to the meaning of a sentence, …
View article: Simpler but More Accurate Semantic Dependency Parsing
Simpler but More Accurate Semantic Dependency Parsing Open
While syntactic dependency annotations concentrate on the surface or functional structure of a sentence, semantic dependency annotations aim to capture between-word relationships that are more closely related to the meaning of a sentence, …
View article: Universal Dependency Parsing from Scratch
Universal Dependency Parsing from Scratch Open
This paper describes Stanford’s system at the CoNLL 2018 UD Shared Task. We introduce a complete neural pipeline system that takes raw text as input, and performs all tasks required by the shared task, ranging from tokenization and sentenc…
View article: Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task
Stanford's Graph-based Neural Dependency Parser at the CoNLL 2017 Shared Task Open
This paper describes the neural dependency parser submitted by Stanford to the CoNLL 2017 Shared Task on parsing Universal Dependencies. Our system uses relatively simple LSTM networks to produce part of speech tags and labeled dependency …
View article: Deep Biaffine Attention for Neural Dependency Parsing
Deep Biaffine Attention for Neural Dependency Parsing Open
This paper builds off recent work from Kiperwasser & Goldberg (2016) using neural attention in a simple graph-based dependency parser. We use a larger but more thoroughly regularized parser than other recent BiLSTM-based approaches, with b…