Search Results for author: Bernd Bohnet

Found 38 papers, 5 papers with code

The Third Multilingual Surface Realisation Shared Task (SR’20): Overview and Evaluation Results

1 code implementation MSR (COLING) 2020 Simon Mille, Anya Belz, Bernd Bohnet, Thiago castro Ferreira, Yvette Graham, Leo Wanner

As in SR’18 and SR’19, the shared task comprised two tracks: (1) a Shallow Track where the inputs were full UD structures with word order information removed and tokens lemmatised; and (2) a Deep Track where additionally, functional words and morphological information were removed.

Decoding Part-of-Speech from Human EEG Signals

no code implementations ACL 2022 Alex Murphy, Bernd Bohnet, Ryan Mcdonald, Uta Noppeney

This work explores techniques to predict Part-of-Speech (PoS) tags from neural signals measured at millisecond resolution with electroencephalography (EEG) during text reading.

Data Augmentation EEG +1

Named Entity Recognition as Dependency Parsing

1 code implementation ACL 2020 Juntao Yu, Bernd Bohnet, Massimo Poesio

Named Entity Recognition (NER) is a fundamental task in Natural Language Processing, concerned with identifying spans of text expressing references to entities.

Dependency Parsing named-entity-recognition +3

On Faithfulness and Factuality in Abstractive Summarization

2 code implementations ACL 2020 Joshua Maynez, Shashi Narayan, Bernd Bohnet, Ryan Mcdonald

It is well known that the standard likelihood training and approximate decoding objectives in neural text generation models lead to less human-like responses for open-ended tasks such as language modeling and story generation.

Abstractive Text Summarization Document Summarization +3

A Gold Standard Dependency Treebank for Turkish

no code implementations LREC 2020 Tolga Kayadelen, Adnan Ozturel, Bernd Bohnet

We introduce TWT; a new treebank for Turkish which consists of web and Wikipedia sentences that are annotated for segmentation, morphology, part-of-speech and dependency relations.

Dependency Parsing

The Second Multilingual Surface Realisation Shared Task (SR'19): Overview and Evaluation Results

no code implementations WS 2019 Simon Mille, Anja Belz, Bernd Bohnet, Yvette Graham, Leo Wanner

We report results from the SR{'}19 Shared Task, the second edition of a multilingual surface realisation task organised as part of the EMNLP{'}19 Workshop on Multilingual Surface Realisation.

Neural Mention Detection

1 code implementation LREC 2020 Juntao Yu, Bernd Bohnet, Massimo Poesio

We then evaluate our models for coreference resolution by using mentions predicted by our best model in start-of-the-art coreference systems.

Coreference Resolution NER

Underspecified Universal Dependency Structures as Inputs for Multilingual Surface Realisation

no code implementations WS 2018 Simon Mille, Anja Belz, Bernd Bohnet, Leo Wanner

In this paper, we present the datasets used in the Shallow and Deep Tracks of the First Multilingual Surface Realisation Shared Task (SR{'}18).

Natural Language Understanding Text Generation

The First Multilingual Surface Realisation Shared Task (SR'18): Overview and Evaluation Results

no code implementations WS 2018 Simon Mille, Anja Belz, Bernd Bohnet, Yvette Graham, Emily Pitler, Leo Wanner

We report results from the SR{'}18 Shared Task, a new multilingual surface realisation task organised as part of the ACL{'}18 Workshop on Multilingual Surface Realisation.

Shared Task Proposal: Multilingual Surface Realization Using Universal Dependency Trees

no code implementations WS 2017 Simon Mille, Bernd Bohnet, Leo Wanner, Anja Belz

We propose a shared task on multilingual Surface Realization, i. e., on mapping unordered and uninflected universal dependency trees to correctly ordered and inflected sentences in a number of languages.

Machine Translation POS +1

Dependency Language Models for Transition-based Dependency Parsing

no code implementations WS 2017 Juntao Yu, Bernd Bohnet

In this paper, we present an approach to improve the accuracy of a strong transition-based dependency parser by exploiting dependency language models that are extracted from a large parsed corpus.

Transition-Based Dependency Parsing

Static and Dynamic Feature Selection in Morphosyntactic Analyzers

no code implementations21 Mar 2016 Bernd Bohnet, Miguel Ballesteros, Ryan Mcdonald, Joakim Nivre

Experiments on five languages show that feature selection can result in more compact models as well as higher accuracy under all conditions, but also that a dynamic ordering works better than a static ordering and that joint systems benefit more than standalone taggers.

feature selection

Cannot find the paper you are looking for? You can Submit a new open access paper.