no code implementations • 5 May 2022 • Julia Kiseleva, Ziming Li, Mohammad Aliannejadi, Shrestha Mohanty, Maartje ter Hoeve, Mikhail Burtsev, Alexey Skrynnik, Artem Zholus, Aleksandr Panov, Kavya Srinet, Arthur Szlam, Yuxuan Sun, Marc-Alexandre Côté Katja Hofmann, Ahmed Awadallah, Linar Abdrazakov, Igor Churin, Putra Manggala, Kata Naszadi, Michiel van der Meer, Taewoon Kim
The primary goal of the competition is to approach the problem of how to build interactive agents that learn to solve a task while provided with grounded natural language instructions in a collaborative environment.
Motivated from these two angles, we propose a new task: summarization with graphical elements, and we verify that these summaries are helpful for a critical mass of people.
As a first contribution we present a road map in which we detail the steps that need to be taken towards interactive language modeling.
no code implementations • 13 Oct 2021 • Julia Kiseleva, Ziming Li, Mohammad Aliannejadi, Shrestha Mohanty, Maartje ter Hoeve, Mikhail Burtsev, Alexey Skrynnik, Artem Zholus, Aleksandr Panov, Kavya Srinet, Arthur Szlam, Yuxuan Sun, Katja Hofmann, Michel Galley, Ahmed Awadallah
Starting from a very young age, humans acquire new skills and learn how to solve new tasks either by imitating the behavior of others or by following provided natural language instructions.
In this work, we propose a method for generating CF explanations for GNNs: the minimal perturbation to the input (graph) data such that the prediction changes.
Motivated by our findings, we present ways to mitigate this mismatch in future research on automatic summarization: we propose research directions that impact the design, the development and the evaluation of automatically generated summaries.
This can be done by conditioning the model on additional information.
Our contributions are three-fold: (1) We first present a survey to understand the space of document-centered assistance and the capabilities people expect in this scenario.
Finally, we find that relative positions heads seem integral to summarization performance and persistently remain after pruning.
We investigate whether distributions calculated by different attention heads in a transformer architecture can be used to improve transparency in the task of abstractive summarization.