Papers by Fotis Jannidis

3 papers
Corpus REDEWIEDERGABE (2020.lrec-1)

Copied to clipboard

Challenge: The corpus REDEWIEDERGABE contains detailed annotations for speech, thought and writing representation (ST&WR) with approximately 490,000 tokens, it is the largest resource of its kind.
Approach: This paper presents corpus REDEWIEDERGABE, a German-language historical corpus with detailed annotations for speech, thought and writing representation (ST&WR).
Outcome: The corpus REDEWIEDERGABE contains 490,000 tokens and is the largest resource of its kind.
Detecting Scenes in Fiction: A new Segmentation Task (2021.eacl-main)

Copied to clipboard

Challenge: Text segmentation is a long standing issue in the area of natural language processing . even modern methods struggle with processing text longer than a couple of sentences or paragraphs .
Approach: They introduce the task of scene segmentation on narrative texts and provide an annotated corpus . they discuss linguistic and narrative properties of the task and provide baseline experiments .
Outcome: The proposed task is very challenging and the results are impressive.
Delta vs. N-Gram Tracing: Evaluating the Robustness of Authorship Attribution Methods (L18-1)

Copied to clipboard

Challenge: a novel authorship attribution method is developed for short texts . delta measures are well-established, but N-gram tracing is not robust enough .
Approach: They propose to use delta measures and N-gram tracing to compare short texts . they find they are highly sensitive to the choice of authors and texts in the corpus .
Outcome: The proposed methods are highly sensitive to the selection of authors and texts in the comparison corpus.

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