Soccer is one of the most popular sports globally, and the amount of soccer-related content
worldwide, including video footage, audio commentary, team/player statistics, scores, and …

Recent video+ language datasets cover domains where the interaction is highly structured,
such as instructional videos, or where the interaction is scripted, such as TV shows. Both of …

In this paper, we address the problem of how an interactive agent (such as a robot) can
present information to an audience and adapt the presentation according to the feedback it …

Data-to-text generation is usually defined into two parts: planning how to order and structure
the information, and generating a text grammatically correct and fluent, that is faithful to the …

Since its launch in 2012, Wikidata has grown to become the largest open knowledge base
(KB), containing more than 100 million data items and over 6 million registered users …

We present a new task for multimodal information extraction: identify the players or teams
that possess the ball in each play of an American football game. We also introduce BAPO, a …

La generación de texto dejó de ser del dominio exclusivo de los humanos hace años. Hoy
en día, existen sistemas de generación de lenguaje natural que escriben resúmenes de …

Soccer dominates the global sports market, and viewers' interest in watching videos of
soccer matches is ramping up. Globally, there is a huge and constantly increasing amount of …

Despite increasing amounts of data and ever improving natural language techniques, work
on automated journalism is still relatively scarce. Reporting news requires significant …

Text generation tasks see rapid growth during recent years. It aims to generate human-
readable text for describing some given input data enabling more interpretability for …