Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations

Kiperwasser, Eliyahu; Goldberg, Yoav

doi:10.48550/arxiv.1603.04351

Cited by 19 publications

(41 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A regularized parser with bi-affine classifiers has been proposed for the prediction of arcs and labels [88]. Bidirectional-LSTMs have been used in dependency parsers for feature representation [89]. A new control structure has been introduced for sequence-tosequence neural networks based on the stack LSTM and has been used in transition-based parsing [90].…”

Section: Model Accuracymentioning

confidence: 99%

Natural Language Processing Advancements By Deep Learning: A Survey

Torfi,

Shirvani,

Keneshloo

et al. 2020

Preprint

View full text Add to dashboard Cite

Natural Language Processing (NLP) helps empower intelligent machines by enhancing a better understanding of the human language for linguistic-based human-computer communication. Recent developments in computational power and the advent of large amounts of linguistic data have heightened the need and demand for automating semantic analysis using data-driven approaches. The utilization of data-driven strategies is pervasive now due to the significant improvements demonstrated through the usage of deep learning methods in areas such as Computer Vision, Automatic Speech Recognition, and in particular, NLP. This survey categorizes and addresses the different aspects and applications of NLP that have benefited from deep learning. It covers core NLP tasks and applications, and describes how deep learning methods and models advance these areas. We further analyze and compare different approaches and state-of-the-art models.

show abstract

Section: Model Accuracymentioning

confidence: 99%

Natural Language Processing Advancements By Deep Learning: A Survey

Torfi,

Shirvani,

Keneshloo

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Considering the impact of time,we set 2017 (full year) as the training dataset and 2018 (until June) as test dataset which contains 26918 reviews (from 13225 users to 450 restaurants). After tokenizing and POS tagging, review texts are transformed into syntax relations (shown in Figure 1) by utilizing the spaCy CNN dependency parsing model (Kiperwasser and Goldberg, 2016;Goldberg and Nivre, 2012), and these relation pairs containing users opinions towards aspects are extracted in the form of tuples liked<opinion, aspect>.…”

Section: Data Preprocessing and Feature Extractionmentioning

confidence: 99%

A Neural Network Based Explainable Recommender System

Lin¹,

Liu²

2018

Preprint

View full text Add to dashboard Cite

Recommendation system could help the companies to persuade users to visit or consume at a particular place, which was based on many traditional methods such as the set of collaborative filtering algorithms. Most research discusses the model design or feature engineering methods to minimize the root mean square error (RMSE) of rating prediction, but lacks exploring the ways to generate the reasons for recommendations. This paper proposed an integrated neural network based model which integrates rating scores prediction and explainable words generation. Based on the experimental results, this model presented lower RMSE compared with traditional methods, and generate the explanation of recommendation to convince customers to visit the recommended place.

show abstract

“…One approach to deriving scene graphs from captions / sentences is to use NLP methods for dependency parsing. These methods extend the transition-based parser work of [15], to embrace more complex graphs [16], or more sophisticated transition schemes [13].…”

Section: Introductionmentioning

confidence: 99%

Scene Graph Parsing by Attention Graph

Andrews,

Chia,

Witteveen

2019

Preprint

View full text Add to dashboard Cite

Scene graph representations, which form a graph of visual object nodes together with their attributes and relations, have proved useful across a variety of vision and language applications. Recent work in the area has used Natural Language Processing dependency tree methods to automatically build scene graphs. In this work, we present an 'Attention Graph' mechanism that can be trained endto-end, and produces a scene graph structure that can be lifted directly from the top layer of a standard Transformer model. The scene graphs generated by our model achieve an F-score similarity of 52.21% to ground-truth graphs on the evaluation set using the SPICE metric, surpassing the best previous approaches by 2.5%.

show abstract

Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations

Cited by 19 publications

References 0 publications

Natural Language Processing Advancements By Deep Learning: A Survey

Natural Language Processing Advancements By Deep Learning: A Survey

A Neural Network Based Explainable Recommender System

Scene Graph Parsing by Attention Graph

Contact Info

Product

Resources

About