Picture for Diego Marcheggiani

Diego Marcheggiani

Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages

May 19, 2023
Seraphina Goldfarb-Tarrant, Adam Lopez, Roi Blanco, Diego Marcheggiani

* 5 pages, accepted to Findings of ACL 2023

Access Paper or Ask Questions

BookQA: Stories of Challenges and Opportunities

Oct 02, 2019
Stefanos Angelidis, Lea Frermann, Diego Marcheggiani, Roi Blanco, Lluís Màrquez

Figure 1 for BookQA: Stories of Challenges and Opportunities

Figure 2 for BookQA: Stories of Challenges and Opportunities

Figure 3 for BookQA: Stories of Challenges and Opportunities

Figure 4 for BookQA: Stories of Challenges and Opportunities

* Accepted at 2nd Workshop on Machine Reading for Question Answering (MRQA), EMNLP 2019

Access Paper or Ask Questions

Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling

Sep 21, 2019
Diego Marcheggiani, Ivan Titov

Figure 1 for Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling

Figure 2 for Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling

Figure 3 for Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling

Figure 4 for Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling

Access Paper or Ask Questions

You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP

Sep 01, 2019
Marco Del Tredici, Diego Marcheggiani, Sabine Schulte im Walde, Raquel Fernández

Figure 1 for You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP

Figure 2 for You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP

Figure 3 for You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP

Figure 4 for You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP

* To appear in Proceeding of EMNLP 2019

Access Paper or Ask Questions

Deep Graph Convolutional Encoders for Structured Data to Text Generation

Oct 23, 2018
Diego Marcheggiani, Laura Perez-Beltrachini

Figure 1 for Deep Graph Convolutional Encoders for Structured Data to Text Generation

Figure 2 for Deep Graph Convolutional Encoders for Structured Data to Text Generation

Figure 3 for Deep Graph Convolutional Encoders for Structured Data to Text Generation

Figure 4 for Deep Graph Convolutional Encoders for Structured Data to Text Generation

* INLG 2018

Access Paper or Ask Questions

Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

Jul 30, 2017
Diego Marcheggiani, Ivan Titov

Figure 1 for Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

Figure 2 for Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

Figure 3 for Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

Figure 4 for Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling

* To appear in EMNLP 2017

Access Paper or Ask Questions

A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

Jun 15, 2017
Diego Marcheggiani, Anton Frolov, Ivan Titov

Figure 1 for A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

Figure 2 for A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

Figure 3 for A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

Figure 4 for A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling

* To appear in CoNLL 2017

Access Paper or Ask Questions

On the Effects of Low-Quality Training Data on Information Extraction from Clinical Reports

Mar 04, 2015
Diego Marcheggiani, Fabrizio Sebastiani

Figure 1 for On the Effects of Low-Quality Training Data on Information Extraction from Clinical Reports

Figure 2 for On the Effects of Low-Quality Training Data on Information Extraction from Clinical Reports

* Submitted for publication

Access Paper or Ask Questions