• Publications
  • Influence
Exploiting Context for Biomedical Entity Recognition: From Syntax to the Web
TLDR
We describe a machine learning system for the recognition of names in biomedical texts. Expand
  • 155
  • 16
  • PDF
An Annotation Scheme for Information Status in Dialogue
TLDR
We present an annotation scheme for information status (IS) in dialogue, and validate it on three Switchboard dialogues. Expand
  • 85
  • 16
  • PDF
The Meaning Factory: Formal Semantics for Recognizing Textual Entailment and Determining Semantic Similarity
TLDR
Shared Task 1 of SemEval-2014 comprised two subtasks on the same dataset of sentence pairs: recognizing textual entailment and determining textual similarity. Expand
  • 81
  • 11
  • PDF
N-GrAM: New Groningen Author-profiling Model
TLDR
We describe our participation in the PAN 2017 shared task on Author Profiling, identifying authors’ gender and language variety for English, Spanish, Arabic and Portuguese. Expand
  • 66
  • 10
  • PDF
Using the Web for Nominal Anaphora Resolution
We present a novel method for resolving non-pronominal anaphora. Instead of using handcrafted lexical resources, we search the Web with shallow patterns which can be predetermined for the type ofExpand
  • 86
  • 10
  • PDF
Exploring the boundaries: gene and protein identification in biomedical text
TLDR
We present a maximum-entropy based system incorporating a diverse set of features for identifying gene and protein names in biomedical abstracts.ResultsThis system was entered in the BioCreative comparative evaluation and achieved a precision of 0.84 in the "open" evaluation and a recall of 99% in the closed evaluation. Expand
  • 114
  • 8
  • PDF
Sentiment analysis on Italian tweets
TLDR
We describe TWITA, the first corpus of Italian tweets, which is created via a completely automatic procedure, portable to any other language. Expand
  • 90
  • 8
  • PDF
Syntactic Features and Word Similarity for Supervised Metonymy Resolution
TLDR
We show that syntactic head-modifier relations are a high precision feature for metonymy recognition but suffer from data sparseness. Expand
  • 49
  • 8
  • PDF
Towards a Corpus Annotated for Metonymies: the Case of Location Names
TLDR
We present a framework for annotating metonymies in domain-independent text that considers the regularity, productivity and underspecification of metonymic usage. Expand
  • 49
  • 8
  • PDF
Adding Semantics to Data-Driven Paraphrasing
TLDR
We add an interpretable semantics to the paraphrase database (PPDB). Expand
  • 52
  • 7
  • PDF