NLPExplorer

Aitor Soroa

Number of Papers:- 50

Number of Citations:- 390

First ACL Paper:- 2000

Latest ACL Paper:- 2024

Venues:-

NAACL

CoNLL

COLING

EMNLP

NLP-COVID19

RANLP

LREC

CogALex

ACL

EACL

*SEMEVAL

IJCNLP

LaTeCH

Co-Authors:-

Similar Authors:-

Do Multilingual Language Models Think Better in English? NAACL

XNLIeu: a dataset for cross-lingual NLI in Basque NAACL

Latxa: An Open Language Model and Evaluation Suite for Basque ACL

A LLM-based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation F i n d i n g s - E M N L P

Irune Zubiaga | Aitor Soroa | Rodrigo Agerri |

Scaling Laws for BERT in Low-Resource Settings F i n d i n g s - A C L

Principled Paraphrase Generation with Parallel Corpora ACL

BasqueGLUE: A Natural Language Understanding Benchmark for Basque LREC

Does Corpus Quality Really Matter for Low-Resource Languages? EMNLP

PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation F i n d i n g s - E M N L P

Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context Anchoring ACL IJCNLP

Ontology Population Reusing Resources for Dialogue Intent Detection: Generic and Multilingual Approach RANLP

Cristina Aceta | Izaskun Fernández | Aitor Soroa |

A Syntax-Aware Edit-based System for Text Simplification RANLP

Oscar M. Cumbicus-Pineda | Itziar Gonzalez-Dios | Aitor Soroa |

DoQA - Accessing Domain-Specific FAQs via Conversational QA ACL

Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning COLING

Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems EMNLP

Automatic Evaluation vs. User Preference in Neural Textual QuestionAnswering over COVID-19 Scientific Literature EMNLP NLP-COVID19

Conversational Question Answering in Low Resource Scenarios: A Dataset and Case Study for Basque LREC

Give your Text Representation Models some Love: the Case for Basque LREC

Analyzing the Limitations of Cross-lingual Word Embedding Mappings ACL

Learning Text Representations for 500K Classification Tasks on Named Entity Disambiguation CoNLL

Ander Barrena | Aitor Soroa | Eneko Agirre |

The risk of sub-optimal use of Open Source NLP Software: UKB is inadvertently state-of-the-art in knowledge-based WSD ACL WS

Eneko Agirre | Oier López de Lacalle | Aitor Soroa |

Interoperability of Annotation Schemes: Using the Pepper Framework to Display AWA Documents in the ANNIS Interface LREC

Talvany Carlotto | Zuhaitz Beloki | Xabier Artola | Aitor Soroa |

Two Architectures for Parallel Processing of Huge Amounts of Text LREC

Alleviating Poor Context with Background Knowledge for Named Entity Disambiguation ACL

Ander Barrena | Aitor Soroa | Eneko Agirre |

Random Walks and Neural Network Language Models on Knowledge Bases NAACL

Josu Goikoetxea | Aitor Soroa | Eneko Agirre |

Improving distant supervision using inference learning ACL IJCNLP

Roland Roller | Eneko Agirre | Aitor Soroa | Mark Stevenson |

evision PDF of 'Combining Mention Context and Hyperlinks from Wikipedia for Named Entity Disambiguation *SEMEVAL

Ander Barrena | Aitor Soroa | Eneko Agirre |

“One Entity per Discourse” and “One Entity per Collocation” Improve Named-Entity Disambiguation COLING

Random Walks for Knowledge-Based Word Sense Disambiguation CL

Eneko Agirre | Oier López de Lacalle | Aitor Soroa |

A stream computing approach towards scalable NLP LREC

Xabier Artola | Zuhaitz Beloki | Aitor Soroa |

Exploring the use of word embeddings and random walks on Wikipedia for the CogAlex shared task CogALex WS

Josu Goikoetxea | Eneko Agirre | Aitor Soroa |

PATHS: A System for Accessing Cultural Heritage Collections ACL

Comparing Taxonomies for Organising Collections of Documents COLING

Matching Cultural Heritage items to Wikipedia LREC

Enabling the Discovery of Digital Cultural Heritage Objects through Wikipedia LaTeCH WS

Exploring Knowledge Bases for Similarity LREC

Eneko Agirre | Montse Cuadros | German Rigau | Aitor Soroa |

Kyoto: An Integrated System for Specific Domain WSD *SEMEVAL

KYOTO: an open platform for mining facts WS

Personalizing PageRank for Word Sense Disambiguation EACL

Eneko Agirre | Aitor Soroa |

A Study on Similarity and Relatedness Using Distributional and WordNet-based Approaches NAACL

WikiWalk: Random walks on Wikipedia for Semantic Relatedness WS

Using the Multilingual Central Repository for Graph-Based Word Sense Disambiguation LREC

Eneko Agirre | Aitor Soroa |

Spelling Correction: from Two-Level Morphology to Open Source LREC

SemEval-2007 Task 02: Evaluating Word Sense Induction and Discrimination Systems *SEMEVAL

Eneko Agirre | Aitor Soroa |

UBC-AS: A Graph Based Unsupervised System for Induction and Classification *SEMEVAL

Eneko Agirre | Aitor Soroa |

Structure, Annotation and Tools in the Basque ZT Corpus LREC

Two graph-based algorithms for state-of-the-art WSD EMNLP WS

Eneko Agirre | David Martínez | Oier López de Lacalle | Aitor Soroa |

Evaluating and optimizing the parameters of an unsupervised graph-based WSD algorithm WS

Eneko Agirre | David Martínez | Oier López de Lacalle | Aitor Soroa |

A Class Library for the Integration of NLP Tools: Definition and implementation of an Abstract Data Type Collection for the manipulation of SGML documents in a context of stand-off linguistic annotation LREC

A Proposal for the Integration of NLP Tools using SGML-Tagged Documents LREC