Papers by Matthijs Westera

4 papers
TED-Q: TED Talks and the Questions they Evoke (2020.lrec-1)

Copied to clipboard

Challenge: Evoked questions represent a hitherto unexplored type of linguistic data, promising to open up important new lines of research.
Approach: They propose a method to annotate TED-talks with the questions they evoke and, where available, the answers to these questions.
Outcome: The proposed method is designed to scale up, relying on crowdsourcing by non-expert annotators, with its utility for Natural Language Processing in mind.
Humans Meet Models on Object Naming: A New Dataset and Analysis (2020.coling-main)

Copied to clipboard

Challenge: Existing object naming datasets that use only images with a bounding box are noisy . a human-like model behavior is not stable across domains, a study finds .
Approach: They use MN v2 to verify object naming datasets with dozens of valid names per object . they find that human-like model behavior is not stable across domains .
Outcome: The proposed model confuses people and clothing objects more frequently than humans do.
What do Entity-Centric Models Learn? Insights from Entity Linking in Multi-Party Dialogue (N19-1)

Copied to clipboard

Challenge: a recent study suggests that models that incorporate a bias towards learning entity representations are not effective at modeling entities.
Approach: They propose to use two entity-centric models for a referential task . they show they outperform the state of the art and do better on lower frequency entities .
Outcome: The proposed models outperform the state of the art on a referential task . they do better on lower frequency entities than a counterpart model not entity-centric .
Similarity or deeper understanding? Analyzing the TED-Q dataset of evoked questions (2020.coling-main)

Copied to clipboard

Challenge: TED-Q datasets are annotated with the questions they implicitly evoke, based on a dataset of TED talks . we test whether relation between a discourse and questions it evokes is one of similarity or association .
Approach: They construct a binary classification task from TED-Q and fit a BERT-based classifier alongside models based on different notions of similarity.
Outcome: The proposed classifier outperforms similarity-based models in the TED-Q dataset.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations