Search Results for author: Emanuele Bastianelli

Found 13 papers, 3 papers with code

Going for GOAL: A Resource for Grounded Football Commentaries

1 code implementation8 Nov 2022 Alessandro Suglia, José Lopes, Emanuele Bastianelli, Andrea Vanzo, Shubham Agarwal, Malvina Nikandrou, Lu Yu, Ioannis Konstas, Verena Rieser

As the course of a game is unpredictable, so are commentaries, which makes them a unique resource to investigate dynamic language grounding.

Moment Retrieval Retrieval

Encoding Syntactic Constituency Paths for Frame-Semantic Parsing with Graph Convolutional Networks

no code implementations26 Nov 2020 Emanuele Bastianelli, Andrea Vanzo, Oliver Lemon

We study the problem of integrating syntactic information from constituency trees into a neural model in Frame-semantic parsing sub-tasks, namely Target Identification (TI), FrameIdentification (FI), and Semantic Role Labeling (SRL).

Semantic Parsing Semantic Role Labeling +1

SLURP: A Spoken Language Understanding Resource Package

1 code implementation EMNLP 2020 Emanuele Bastianelli, Andrea Vanzo, Pawel Swietojanski, Verena Rieser

Spoken Language Understanding infers semantic meaning directly from audio data, and thus promises to reduce error propagation and misunderstandings in end-user applications.

Ranked #3 on Slot Filling on SLURP (using extra training data)

Intent Classification Slot Filling +1

Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games

no code implementations COLING 2020 Alessandro Suglia, Antonio Vergari, Ioannis Konstas, Yonatan Bisk, Emanuele Bastianelli, Andrea Vanzo, Oliver Lemon

However, as shown by Suglia et al. (2020), existing models fail to learn truly multi-modal representations, relying instead on gold category labels for objects in the scene both at training and inference time.


CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning

no code implementations ACL 2020 Alessandro Suglia, Ioannis Konstas, Andrea Vanzo, Emanuele Bastianelli, Desmond Elliott, Stella Frank, Oliver Lemon

To remedy this, we present GROLLA, an evaluation framework for Grounded Language Learning with Attributes with three sub-tasks: 1) Goal-oriented evaluation; 2) Object attribute prediction evaluation; and 3) Zero-shot evaluation.

Attribute Grounded language learning

A Multi-layer LSTM-based Approach for Robot Command Interaction Modeling

no code implementations13 Nov 2018 Martino Mensio, Emanuele Bastianelli, Ilaria Tiddi, Giuseppe Rizzo

As the first robotic platforms slowly approach our everyday life, we can imagine a near future where service robots will be easily accessible by non-expert users through vocal interfaces.

Natural Language Understanding Semantic Parsing

HuRIC: a Human Robot Interaction Corpus

no code implementations LREC 2014 Emanuele Bastianelli, Giuseppe Castellucci, Danilo Croce, Luca Iocchi, Roberto Basili, Daniele Nardi

Recent years show the development of large scale resources (e. g. FrameNet for the Frame Semantics) that supported the definition of several state-of-the-art approaches in Natural Language Processing.

Domain Adaptation Open-Domain Question Answering +1

Knowledge Representation for Robots through Human-Robot Interaction

no code implementations28 Jul 2013 Emanuele Bastianelli, Domenico Bloisi, Roberto Capobianco, Guglielmo Gemignani, Luca Iocchi, Daniele Nardi

The representation of the knowledge needed by a robot to perform complex tasks is restricted by the limitations of perception.

Cannot find the paper you are looking for? You can Submit a new open access paper.