Search Results for author:
Found 26 papers, 4 papers with code
MassiveSumm: a very large-scale, very multilingual, news summarisation dataset
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
Danish is a North Germanic language spoken principally in Denmark, a country with a long tradition of technological and scientific innovation.
Construction of Paired Knowledge Graph-Text Datasets Informed by Cyclic Evaluation
Guided by these observations, we construct a new, improved dataset called LAGRANGE using heuristics meant to improve equivalence between KG and text and show the impact of each of the heuristics on cyclic evaluation.
High-Resource Methodological Bias in Low-Resource Investigations
The central bottleneck for low-resource NLP is typically regarded to be the quantity of accessible data, overlooking the contribution of data quality.
DaNewsroom: A Large-scale Danish Summarisation Dataset
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.
Recurrent models and lower bounds for projective syntactic decoding
We also provide the first proof on the lower bounds of projective maximum spanning tree decoding.
On approximating dropout noise injection
This paper examines the assumptions of the derived equivalence between dropout noise injection and $L_2$ regularisation for logistic regression with negative log loss.
The glass ceiling in NLP
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.
When data permutations are pathological: the case of neural natural language inference
Consider two competitive machine learning models, one of which was considered state-of-the art, and the other a competitive baseline.
UniParse: A universal graph-based parsing toolkit
This paper describes the design and use of the graph-based parsing framework and toolkit UniParse, released as an open-source python software package.
The Word Analogy Testing Caveat
There are some important problems in the evaluation of word embeddings using standard word analogy tests.
How (not) to train a dependency parser: The curious case of jackknifing part-of-speech taggers
In dependency parsing, jackknifing taggers is indiscriminately used as a simple adaptation strategy.
Baselines and test data for cross-lingual inference
In this paper, we propose to advance the research in SNLI-style natural language inference toward multilingual evaluation.
The limits of automatic summarisation according to ROUGE
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
Approximate summary optimisation for selections of ROUGE It is standard to measure automatic summariser performance using the ROUGE metric.
Multilingual Projection for Parsing Truly Low-Resource Languages
We propose a novel approach to cross-lingual part-of-speech tagging and dependency parsing for truly low-resource languages.
A critical survey on measuring success in rank-based keyword assignment to documents
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
This paper presents an exhaustive study on the generation of graph input to unsupervised graph-based non-contextual single document keyword extraction systems.
