Publications

What is a Publication?
1687 Publications visible to you, out of a total of 1687

Abstract (Expand)

The CODI-CRAC 2022 Shared Task on Anaphora Resolution in Dialogues is the second edition of an initiative focused on detecting different types of anaphoric relations in conversations of different kinds. Using five conversational datasets, four of which have been newly annotated with a wide range of anaphoric relations: identity, bridging references and discourse deixis, we defined multiple tasks focusing individually on these key relations. The second edition of the shared task maintained the focus on these relations and used the same datasets as in 2021, but new test data were annotated, the 2021 data were checked, and new subtasks were added. In this paper, we discuss the annotation schemes, the datasets, the evaluation scripts used to assess the system performance on these tasks, and provide a brief summary of the participating systems and the results obtained across 230 runs from three teams, with most submissions achieving significantly better results than our baseline methods.

Authors: Juntao Yu, Sopan Khosla, Ramesh Manuvinakurike, Lori Levin, Vincent Ng, Massimo Poesio, Michael Strube, Carolyn Rosé

Date Published: 17th Oct 2022

Publication Type: InProceedings

Abstract (Expand)

Abstract Analysing large numbers of brain samples can reveal minor, but statistically and biologically relevant variations in brain morphology that provide critical insights into animal behaviour,into animal behaviour, ecology and evolution. So far, however, such analyses have required extensive manual effort, which considerably limits the scope for comparative research. Here we used micro-CT imaging and deep learning to perform automated analyses of 3D image data from 187 honey bee and bumblebee brains. We revealed strong inter-individual variations in total brain size that are consistent across colonies and species, and may underpin behavioural variability central to complex social organisations. In addition, the bumblebee dataset showed a significant level of lateralization in optic and antennal lobes, providing a potential explanation for reported variations in visual and olfactory learning. Our fast, robust and user-friendly approach holds considerable promises for carrying out large-scale quantitative neuroanatomical comparisons across a wider range of animals. Ultimately, this will help address fundamental unresolved questions related to the evolution of animal brains and cognition. Author Summary Bees, despite their small brains, possess a rich behavioural repertoire and show significant variations among individuals. In social bees this variability is key to the division of labour that maintains their complex social organizations, and has been linked to the maturation of specific brain areas as a result of development and foraging experience. This makes bees an ideal model for understanding insect cognitive functions and the neural mechanisms that underlie them. However, due to the scarcity of comparative data, the relationship between brain neuro-architecture and behavioural variance remains unclear. To address this problem, we developed an AI-based approach for automated analysis of brain images and analysed an unprecedentedly large dataset of honey bee and bumblebee brains. Through this process, we were able to identify previously undescribed anatomical features that correlate with known behaviours, supporting recent evidence of lateralized behaviour in foraging and pollination. Our method is open-source, easily accessible online, user-friendly, fast, accurate, and robust to different species, enabling large-scale comparative analyses across the animal kingdom. This includes investigating the impact of external stressors such as environmental pollution and climate change on cognitive development, helping us understand the mechanisms underlying the cognitive abilities of animals and the implications for their survival and adaptation.

Authors: Philipp D. Lösel, Coline Monchanin, Renaud Lebrun, Alejandra Jayme, Jacob Relle, Jean-Marc Devaud, Vincent Heuveline, Mathieu Lihoreau

Date Published: 17th Oct 2022

Publication Type: Journal

Abstract

Not specified

Authors: Chloé Braud, Christian Hardmeier, Junyi Jessy Li, Sharid Loaciga, Michael Strube, Amir Zeldes

Date Published: 16th Oct 2022

Publication Type: Proceedings

Abstract (Expand)

Coreference resolution is a key step in natural language understanding. Developments in coreference resolution are mainly focused on improving the performance on standard datasets annotated for coreference resolution. However, coreference resolution is an intermediate step for text understanding and it is not clear how these improvements translate into downstream task performance. In this paper, we perform a thorough investigation on the impact of coreference resolvers in multiple settings of community-based question answering task, i.e., answer selection with long answers. Our settings cover multiple text domains and encompass several answer selection methods. We first inspect extrinsic evaluation of coreference resolvers on answer selection by using coreference relations to decontextualize individual sentences of candidate answers, and then annotate a subset of answers with coreference information for intrinsic evaluation. The results of our extrinsic evaluation show that while there is a significant difference between the performance of the rule-based system vs. state-of-the-art neural model on coreference resolution datasets, we do not observe a considerable difference on their impact on downstream models. Our intrinsic evaluation shows that (i) resolving coreference relations on less-formal text genres is more difficult even for trained annotators, and (ii) the values of linguistic-agnostic coreference evaluation metrics do not correlate with the impact on downstream data.

Authors: Haixia Chai, Nafise Sadat Moosavi, Iryna Gurevych, Michael Strube

Date Published: 16th Oct 2022

Publication Type: InProceedings

Abstract

Not specified

Authors: Aysel Ahadova, Johannes Witt, Saskia Haupt, Richard Gallon, Robert Hüneburg, Jacob Nattermann, Sanne ten Broeke, Lena Bohaumilitzky, Alejandro Hernandez‐Sanchez, Mauro Santibanez‐Koref, Michael S. Jackson, Maarit Ahtiainen, Kirsi Pylvänäinen, Katarina Andini, Vince Kornel Grolmusz, Gabriela Möslein, Mev Dominguez‐Valentin, Pål Møller, Daniel Fürst, Rolf Sijmons, Gillian M. Borthwick, John Burn, Jukka‐Pekka Mecklin, Vincent Heuveline, Magnus von Knebel Doeberitz, Toni Seppälä, Matthias Kloor

Date Published: 14th Oct 2022

Publication Type: Journal

Abstract

Not specified

Authors: Debabrata Dey, Ariane Nunes-Alves, Rebecca C. Wade, Gideon Schreiber

Date Published: 1st Oct 2022

Publication Type: Journal

Abstract

Not specified

Authors: O. Vaduvescu, A. Aznar Macias, T. G. Wilson, T. Zegmott, F. M. Pérez Toledo, M. Predatu, R. Gherase, V. Pinter, F. Pozo Nunez, K. Ulaczyk, I. Soszyński, P. Mróz, M. Wrona, P. Iwanek, M. Szymanski, A. Udalski, F. Char, H. Salas Olave, G. Aravena-Rojas, A. C. Vergara, C. Saez, E. Unda-Sanzana, B. Alcalde, A. de Burgos, D. Nespral, R. Galera-Rosillo, N. J. Amos, J. Hibbert, A. López-Comazzi, J. Oey, M. Serra-Ricart, J. Licandro, M. Popescu

Date Published: 1st Oct 2022

Publication Type: Journal

Powered by
(v.1.16.0)
Copyright © 2008 - 2024 The University of Manchester and HITS gGmbH