• Publications
  • Influence
Automated Concatenation of Embeddings for Structured Prediction
TLDR
This paper proposes Automated Concatenation of Embeddings (ACE) to automate the process of finding better concatenations of embeddings for structured prediction tasks, based on a formulation inspired by recent progress on neural architecture search.
Second-Order Semantic Dependency Parsing with End-to-End Neural Networks
TLDR
This paper proposes a second-order semantic dependency parser, which takes into consideration not only individual dependency edges but also interactions between pairs of edges, and shows that second- order parsing can be approximated using mean field variational inference or loopy belief propagation.
Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning
TLDR
This paper finds empirically that the contextual representations computed on the retrieval-based input view, constructed through the concatenation of a sentence and its external contexts, can achieve significantly improved performance compared to the original input view based only on the sentence.
Enhanced Universal Dependency Parsing with Second-Order Inference and Mixture of Training Data
TLDR
This paper presents the system used in the submission to the IWPT 2020 Shared Task, a graph-based parser with second-order inference that specially mixed the training data of Tamil with other languages and significantly improved the performance of Tamil.
Structure-Level Knowledge Distillation For Multilingual Sequence Labeling
TLDR
This paper proposes two novel KD methods based on structure-level information that approximately minimizes the distance between the student’s and the teachers’ structure- level probability distributions, and aggregates theructure-level knowledge to local distributions and minimizesThe distance between two local probability distributions.
Second-Order Neural Dependency Parsing with Message Passing and End-to-End Training
TLDR
This paper empirically shows that the approaches match the accuracy of very recent state-of-the-art second-order graph-based neural dependency parsers and have significantly faster speed in both training and testing.
Structural Knowledge Distillation: Tractably Distilling Information for Structured Predictor
TLDR
A factorized form of the knowledge distillation objective for structured prediction, which is tractable for many typical choices of the teacher and student models and shows the tractability and empirical effectiveness of structural knowledgedistillation between sequence labeling and dependency parsing models.
More Embeddings, Better Sequence Labelers?
TLDR
This paper conducts extensive experiments on 3 tasks over 18 datasets and 8 languages to study the accuracy of sequence labeling with various embedding concatenations and concludes that concatenating more embedding variants leads to better accuracy in rich-resource and cross-domain settings and some conditions of low-resource settings.
ShanghaiTech at MRP 2019: Sequence-to-Graph Transduction with Second-Order Edge Inference for Cross-Framework Meaning Representation Parsing
TLDR
This system is a graph-based parser which combines an extended pointer-generator network that generates nodes and a second-order mean field variational inference module that predicts edges that achieved 1st and 2nd place for the DM and PSD frameworks respectively on the in-framework ranks.
Enhanced Universal Dependency Parsing with Automated Concatenation of Embeddings
TLDR
This paper describes the system used in the submission to the IWPT 2021 Shared Task, a graph-based parser with the technique of Automated Concatenation of Embeddings (ACE) to automatically find the better concatenation of embeddings for the task of enhanced universal dependencies.
...
...