Estimating Mutual Information Between Dense Word Embeddings

no code implementations • ACL 2020 • Vitalii Zhelezniak, Aleks Savkov, ar, Nils Hammerla

In this work we go through a vast literature on estimating MI in such cases and single out the most promising methods, yielding a simple and elegant similarity measure for word embeddings.

Semantic Textual Similarity STS +1

Multilevel Heuristics for Rationale-Based Entity Relation Classification in Sentences

no code implementations • COLING 2018 • Shiou Tian Hsu, M Chaudhary, ar, Nagiza Samatova

Rationale-based models provide a unique way to provide justifiable results for relation classification models by identifying rationales (key words and phrases that a person can use to justify the relation in the sentence) during the process.

Classification General Classification +3

Defining Words with Words: Beyond the Distributional Hypothesis

no code implementations • WS 2016 • Iuliana-Elena Parasca, Andreas Lukas Rauter, Jack Roper, Aleks Rusinov, ar, Guillaume Bouchard, Sebastian Riedel, Pontus Stenetorp

Representation Learning

Knowledge Graph and Corpus Driven Segmentation and Answer Inference for Telegraphic Entity-seeking Queries

no code implementations • EMNLP 2014 • M Joshi, ar, Uma Sawant, Soumen Chakrabarti

Information Retrieval Knowledge Graphs +1

Chunking Clinical Text Containing Non-Canonical Language

no code implementations • WS 2014 • Aleks Savkov, ar, John Carroll, Jackie Cassell

Chunking Constituency Parsing +2

Segmenting Arabic Texts into Elementary Discourse Units (Segmentation de textes arabes en unit\'es discursives minimales) [in French]

no code implementations • JEPTALNRECITAL 2013 • Isk Keskes, ar, Farah Beanamara, lamia hadrich belguith

\'Etude comparative entre trois approches de r\'esum\'e automatique de documents arabes (Comparative Study of Three Approaches to Automatic Summarization of Arabic Documents) [in French]

no code implementations • JEPTALNRECITAL 2012 • Isk Keskes, ar, Mohamed Mahdi Boudabous, Mohamed H{\'e}di Maaloul, lamia hadrich belguith

Clause-based Discourse Segmentation of Arabic Texts

no code implementations • LREC 2012 • Isk Keskes, ar, Farah Benamara, lamia hadrich belguith

This paper describes a rule-based approach to segment Arabic texts into clauses.

Discourse Segmentation Question Answering +1

Linguistic Analysis Processing Line for Bulgarian

no code implementations • LREC 2012 • Aleks Savkov, ar, Laska Laskova, Stanislava Kancheva, Petya Osenova, Kiril Simov

This paper presents a linguistic processing pipeline for Bulgarian including morphological analysis, lemmatization and syntactic analysis of Bulgarian texts.

Language Modelling Lemmatization +5