• Publications
  • Influence
Entity Linking meets Word Sense Disambiguation: a Unified Approach
TLDR
We present Babelfy, a unified graph-based approach to EL and WSD based on a loose identification of candidate meanings coupled with a densest subgraph heuristic which selects high-coherence semantic interpretations. Expand
  • 701
  • 105
  • PDF
Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison
TLDR
In this paper we develop a unified evaluation framework and analyze the performance of various Word Sense Disambiguation systems in a fair setup. Expand
  • 175
  • 38
  • PDF
Neural Sequence Learning Models for Word Sense Disambiguation
TLDR
We propose and study in depth a series of end-to-end neural architectures directly tailored to the task, from bidirectional Long Short-Term Memory to encoder-decoder models. Expand
  • 123
  • 29
  • PDF
An Analysis of Encoder Representations in Transformer-Based Machine Translation
TLDR
We investigate the representations of the encoder by extracting dependency relations based on self-attention weights, we perform four probing tasks to study the amount of syntactic and semantic captured information and we also test attention in transfer learning scenario. Expand
  • 107
  • 7
  • PDF
EuroSense: Automatic Harvesting of Multilingual Sense Annotations from Parallel Text
TLDR
We present EUROSENSE, a multilingual sense-annotated resource based on the joint disambiguation of the Europarl parallel corpus, with almost 123 million sense annotations for over 155 thousand distinct concepts and entities from a languageindependent unified sense inventory. Expand
  • 28
  • 4
  • PDF
Multilingual NMT with a language-independent attention bridge
TLDR
We propose a multilingual encoder-decoder architecture capable of obtaining multilingual sentence representations by means of incorporating an intermediate {\em attention bridge} that is shared across all languages. Expand
  • 16
  • 3
  • PDF
Automatic Identification and Disambiguation of Concepts and Named Entities in the Multilingual Wikipedia
TLDR
We present an automatic multilingual annotation of the Wikipedia dumps in two languages, with both word senses (i.e. concepts) and named entities, thanks to a state-of-the-art multilingual Word Sense Disambiguation and Entity Linking system. Expand
  • 12
  • 2
  • PDF
The MuCoW Test Suite at WMT 2019: Automatically Harvested Multilingual Contrastive Word Sense Disambiguation Test Sets for Machine Translation
TLDR
We present MUCOW, a multilingual contrastive test suite that covers 16 language pairs with more than 200 000 contrastive sentence pairs, automatically built from word-aligned parallel corpora and the wide-coverage multilingual sense inventory of BabelNet. Expand
  • 11
  • 2
  • PDF
The University of Helsinki Submissions to the WMT19 News Translation Task
TLDR
In this paper we present the University of Helsinki submissions to the WMT 2019 news translation task in three language pairs: English-German, English-Finnish and Finnish-English. Expand
  • 6
  • 2
  • PDF
A Large-Scale Multilingual Disambiguation of Glosses
TLDR
We present a large-scale high-quality corpus of disambiguated glosses in multiple languages, comprising sense annotations of both concepts and named entities from a unified sense inventory. Expand
  • 20
  • 1
  • PDF
...
1
2
3
...