26 citations · 44 across the 9 of their papers we have counts for
13 papers
Does task decomposition improve automatic NLG evaluation?
Sebastian Steindl, Nikos Voskarides, Alberto Gasparin +1
The LLM-as-a-judge (LLMaJ) framework has emerged as a promising solution for cheap, reproducible, reference-free Natural Language Generation (NLG) evaluation. Prior work seeks to i…
Post-hoc Alignment of LLM-judges to Human Judgment Distribution
Sebastian Steindl, Nikos Voskarides, Alberto Gasparin +1
The LLM-as-a-judge (LLMaJ) framework offers a cost-effective and reproducible solution for automatic evaluation. However, current evaluation practices typically compare LLMaJ judgm…
Bias Beyond English: Counterfactual Tests for Bias in Sentiment Analysis in Four Languages
Seraphina Goldfarb-Tarrant, Adam Lopez, Roi Blanco +1
Sentiment analysis (SA) systems are used in many products and hundreds of languages. Gender and racial biases are well-studied in English SA systems, but understudied in other lang…
BookQA: Stories of Challenges and Opportunities
Stefanos Angelidis, Lea Frermann, Diego Marcheggiani +2
We present a system for answering questions based on the full text of books (BookQA), which first selects book passages given a question at hand, and then uses a memory network to…
Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling
Diego Marcheggiani, Ivan Titov
Semantic role labeling (SRL) is the task of identifying predicates and labeling argument spans with semantic roles. Even though most semantic-role formalisms are built upon constit…
You Shall Know a User by the Company It Keeps: Dynamic Representations for Social Media Users in NLP
Marco Del Tredici, Diego Marcheggiani, Sabine Schulte im Walde +1
Information about individuals can help to better understand what they say, particularly in social media where texts are short. Current approaches to modelling social media users pa…
Deep Graph Convolutional Encoders for Structured Data to Text Generation
Diego Marcheggiani, Laura Perez-Beltrachini
Most previous work on neural text generation from graph-structured data relies on standard sequence-to-sequence methods. These approaches linearise the input graph to be fed to a r…
Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks
Diego Marcheggiani, Jasmijn Bastings, Ivan Titov
Semantic representations have long been argued as potentially useful for enforcing meaning preservation and improving generalization performance of machine translation methods. In…
Graph Convolutional Encoders for Syntax-aware Neural Machine Translation
Jasmijn Bastings, Ivan Titov, Wilker Aziz +2
We present a simple and effective approach to incorporating syntactic structure into neural attention-based encoder-decoder models for machine translation. We rely on graph-convolu…
Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
Diego Marcheggiani, Ivan Titov
Semantic role labeling (SRL) is the task of identifying the predicate-argument structure of a sentence. It is typically regarded as an important step in the standard NLP pipeline.…
A Simple and Accurate Syntax-Agnostic Neural Model for Dependency-based Semantic Role Labeling
Diego Marcheggiani, Anton Frolov, Ivan Titov
We introduce a simple and accurate neural model for dependency-based semantic role labeling. Our model predicts predicate-argument dependencies relying on states of a bidirectional…
On the Impact of Entity Linking in Microblog Real-Time Filtering
Giacomo Berardi, Diego Ceccarelli, Andrea Esuli +1
Microblogging is a model of content sharing in which the temporal locality of posts with respect to important events, either of foreseeable or unforeseeable nature, makes applica-…
On the Effects of Low-Quality Training Data on Information Extraction from Clinical Reports
Diego Marcheggiani, Fabrizio Sebastiani
In the last five years there has been a flurry of work on information extraction from clinical documents, i.e., on algorithms capable of extracting, from the informal and unstructu…