RANLP 2019

ETNLP: a visual-aided systematic approach to select pre-trained embeddings for a downstream task

RANLP 2019 vietnlp/etnlp

We demonstrate the effectiveness of the proposed approach on our pre-trained word embedding models in Vietnamese to select which models are suitable for a named entity recognition (NER) task.

NAMED ENTITY RECOGNITION WORD EMBEDDINGS

From the Paft to the Fiiture: a Fully Automatic NMT and Word Embeddings Method for OCR Post-Correction

RANLP 2019 mikahama/natas

A great deal of historical corpora suffer from errors introduced by the OCR (optical character recognition) methods used in the digitization process.

MACHINE TRANSLATION OPTICAL CHARACTER RECOGNITION WORD EMBEDDINGS

Beyond English-Only Reading Comprehension: Experiments in Zero-Shot Multilingual Transfer for Bulgarian

RANLP 2019 mhardalov/bg-reason-BERT

Recently, reading comprehension models achieved near-human performance on large-scale datasets such as SQuAD, CoQA, MS Macro, RACE, etc.

READING COMPREHENSION

Augmenting a BiLSTM tagger with a Morphological Lexicon and a Lexical Category Identification Step

RANLP 2019 steinst/ABLTagger

Previous work on using BiLSTM models for PoS tagging has primarily focused on small tagsets.

NE-Table: A Neural key-value table for Named Entities

RANLP 2019 IBM/ne-table-datasets

Many Natural Language Processing (NLP) tasks depend on using Named Entities (NEs) that are contained in texts and in external knowledge sources.

GOAL-ORIENTED DIALOG QUESTION ANSWERING READING COMPREHENSION WORD EMBEDDINGS

Detecting Toxicity in News Articles: Application to Bulgarian

RANLP 2019 yoandinkov/ranlp-2019

Online media aim for reaching ever bigger audience and for attracting ever longer attention span.