Search Results for author: Natalie Schluter

Found 25 papers, 4 papers with code

MassiveSumm: a very large-scale, very multilingual, news summarisation dataset

1 code implementation EMNLP 2021 Daniel Varab, Natalie Schluter

We present the first investigation on the efficacy of resource building from news platforms in the low-resource language setting.

The Lacunae of Danish Natural Language Processing

no code implementations WS (NoDaLiDa) 2019 Andreas Kirkedal, Barbara Plank, Leon Derczynski, Natalie Schluter

Danish is a North Germanic language spoken principally in Denmark, a country with a long tradition of technological and scientific innovation.

High-Resource Methodological Bias in Low-Resource Investigations

no code implementations14 Nov 2022 Maartje ter Hoeve, David Grangier, Natalie Schluter

The central bottleneck for low-resource NLP is typically regarded to be the quantity of accessible data, overlooking the contribution of data quality.

Machine Translation POS +1

DaNewsroom: A Large-scale Danish Summarisation Dataset

no code implementations LREC 2020 Daniel Varab, Natalie Schluter

To support the comparison of future automatic summarisation systems for Danish, we include system performance on this dataset of strong well-established unsupervised baseline systems, together with an oracle extractive summariser, which is the first account of automatic summarisation system performance for Danish.

Abstractive Text Summarization

Recurrent models and lower bounds for projective syntactic decoding

no code implementations NAACL 2019 Natalie Schluter

We also provide the first proof on the lower bounds of projective maximum spanning tree decoding.

On approximating dropout noise injection

no code implementations27 May 2019 Natalie Schluter

This paper examines the assumptions of the derived equivalence between dropout noise injection and $L_2$ regularisation for logistic regression with negative log loss.


When data permutations are pathological: the case of neural natural language inference

1 code implementation EMNLP 2018 Natalie Schluter, Daniel Varab

Consider two competitive machine learning models, one of which was considered state-of-the art, and the other a competitive baseline.

Natural Language Inference

The glass ceiling in NLP

no code implementations EMNLP 2018 Natalie Schluter

In this paper, we provide empirical evidence based on a rigourously studied mathematical model for bi-populated networks, that a glass ceiling within the field of NLP has developed since the mid 2000s.

UniParse: A universal graph-based parsing toolkit

1 code implementation WS (NoDaLiDa) 2019 Daniel Varab, Natalie Schluter

This paper describes the design and use of the graph-based parsing framework and toolkit UniParse, released as an open-source python software package.

Dependency Parsing

The Word Analogy Testing Caveat

no code implementations NAACL 2018 Natalie Schluter

There are some important problems in the evaluation of word embeddings using standard word analogy tests.

Semantic Textual Similarity Transfer Learning +1

Baselines and test data for cross-lingual inference

1 code implementation LREC 2018 Željko Agić, Natalie Schluter

In this paper, we propose to advance the research in SNLI-style natural language inference toward multilingual evaluation.

Cross-Lingual Word Embeddings Machine Translation +3

The limits of automatic summarisation according to ROUGE

no code implementations EACL 2017 Natalie Schluter

This paper discusses some central caveats of summarisation, incurred in the use of the ROUGE metric for evaluation, with respect to optimal solutions.

Approximate unsupervised summary optimisation for selections of ROUGE

no code implementations JEPTALNRECITAL 2016 Natalie Schluter, H{\'e}ctor Mart{\'\i}nez Alonso

Approximate summary optimisation for selections of ROUGE It is standard to measure automatic summariser performance using the ROUGE metric.

A critical survey on measuring success in rank-based keyword assignment to documents

no code implementations JEPTALNRECITAL 2015 Natalie Schluter

Evaluation approaches for unsupervised rank-based keyword assignment are nearly as numerous as are the existing systems.

Effects of Graph Generation for Unsupervised Non-Contextual Single Document Keyword Extraction

no code implementations JEPTALNRECITAL 2015 Natalie Schluter

This paper presents an exhaustive study on the generation of graph input to unsupervised graph-based non-contextual single document keyword extraction systems.

Graph Generation Keyword Extraction

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