1 code implementation • ParlaCLARIN (LREC) 2022 • Ruben van Heusden, Maarten Marx, Jaap Kamps
In this paper, we investigate the task of linking entities from ParlaMint in different languages to a knowledge base, and evaluating the performance of three entity linking methods.
no code implementations • 6 Jul 2022 • David Rau, Jaap Kamps
Even though term-based methods such as BM25 provide strong baselines in ranking, under certain conditions they are dominated by large pre-trained masked language models (MLMs) such as BERT.
1 code implementation • 5 Apr 2022 • David Rau, Jaap Kamps
Our results contribute to our understanding of (black-box) neural rankers relative to (well-understood) traditional rankers, help understand the particular experimental setting of MS-Marco-based test collections.
no code implementations • LREC 2020 • Lennart Kerkvliet, Jaap Kamps, Maarten Marx
We show that it is straightforward to train a state of the art named entity tagger (spaCy) to recognize political actors in Dutch parliamentary proceedings with high accuracy.
no code implementations • ICLR Workshop LLD 2019 • Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf
Training labels are expensive to obtain and may be of varying quality, as some may be from trusted expert labelers while others might be from heuristics or other sources of weak supervision such as crowd-sourcing.
1 code implementation • 12 Oct 2018 • Hosein Azarbonyad, Mostafa Dehghani, Tom Kenter, Maarten Marx, Jaap Kamps, Maarten de Rijke
For measuring topical diversity of text documents, our HiTR approach improves over the state-of-the-art measured on PubMed dataset.
no code implementations • 21 Jun 2018 • Mostafa Dehghani, Jaap Kamps
To this end, we introduce "fidelity-weighted learning" (FWL), a semi-supervised student-teacher approach for training deep neural networks using weakly-labeled data.
1 code implementation • 30 Nov 2017 • Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps
In this paper, we propose a method for training neural networks when we have a large set of data with weak labels and a small amount of data with true labels.
1 code implementation • 15 Nov 2017 • Hosein Azarbonyad, Mostafa Dehghani, Kaspar Beelen, Alexandra Arkut, Maarten Marx, Jaap Kamps
We propose an approach for detecting semantic shifts between different viewpoints--broadly defined as a set of texts that share a specific metadata feature, which can be a time-period, but also a social entity such as a political party.
no code implementations • ICLR 2018 • Mostafa Dehghani, Arash Mehrjou, Stephan Gouws, Jaap Kamps, Bernhard Schölkopf
To this end, we propose "fidelity-weighted learning" (FWL), a semi-supervised student-teacher approach for training deep neural networks using weakly-labeled data.
no code implementations • 1 Nov 2017 • Mostafa Dehghani, Aliaksei Severyn, Sascha Rothe, Jaap Kamps
Thus we avoid that the weight updates computed from noisy labels harm the quality of the target network model.
no code implementations • 24 Jul 2017 • Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten de Rijke
Deep neural networks have become a primary tool for solving problems in many fields.
1 code implementation • 28 Apr 2017 • Mostafa Dehghani, Hamed Zamani, Aliaksei Severyn, Jaap Kamps, W. Bruce Croft
Our experiments indicate that employing proper objective functions and letting the networks to learn the input representation based on weakly supervised data leads to impressive performance, with over 13% and 35% MAP improvements over the BM25 model on the Robust and the ClueWeb collections.
Ranked #8 on Ad-Hoc Information Retrieval on TREC Robust04 (MAP metric)
no code implementations • 2 Sep 2016 • Mostafa Dehghani, Hosein Azarbonyad, Jaap Kamps, Maarten Marx
Extracting separable models of hierarchical entities requires us to take their relative position into account and to consider the different types of dependencies in the hierarchy.
no code implementations • 6 Sep 2015 • Alex Olieman, Jaap Kamps, Maarten Marx, Arjan Nusselder
The current state-of-the-art Entity Linking (EL) systems are geared towards corpora that are as heterogeneous as the Web, and therefore perform sub-optimally on domain-specific corpora.