Emanuele Bastianelli


pdf bib
CompGuessWhat?!: A Multi-task Evaluation Framework for Grounded Language Learning
Alessandro Suglia | Ioannis Konstas | Andrea Vanzo | Emanuele Bastianelli | Desmond Elliott | Stella Frank | Oliver Lemon
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Approaches to Grounded Language Learning are commonly focused on a single task-based final performance measure which may not depend on desirable properties of the learned hidden representations, such as their ability to predict object attributes or generalize to unseen situations. To remedy this, we present GroLLA, an evaluation framework for Grounded Language Learning with Attributes based on three sub-tasks: 1) Goal-oriented evaluation; 2) Object attribute prediction evaluation; and 3) Zero-shot evaluation. We also propose a new dataset CompGuessWhat?! as an instance of this framework for evaluating the quality of learned neural representations, in particular with respect to attribute grounding. To this end, we extend the original GuessWhat?! dataset by including a semantic layer on top of the perceptual one. Specifically, we enrich the VisualGenome scene graphs associated with the GuessWhat?! images with several attributes from resources such as VISA and ImSitu. We then compare several hidden state representations from current state-of-the-art approaches to Grounded Language Learning. By using diagnostic classifiers, we show that current models’ learned representations are not expressive enough to encode object attributes (average F1 of 44.27). In addition, they do not learn strategies nor representations that are robust enough to perform well when novel scenes or objects are involved in gameplay (zero-shot best accuracy 50.06%).

pdf bib
Imagining Grounded Conceptual Representations from Perceptual Information in Situated Guessing Games
Alessandro Suglia | Antonio Vergari | Ioannis Konstas | Yonatan Bisk | Emanuele Bastianelli | Andrea Vanzo | Oliver Lemon
Proceedings of the 28th International Conference on Computational Linguistics

In visual guessing games, a Guesser has to identify a target object in a scene by asking questions to an Oracle. An effective strategy for the players is to learn conceptual representations of objects that are both discriminative and expressive enough to ask questions and guess correctly. 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. This provides an unnatural performance advantage when categories at inference time match those at training time, and it causes models to fail in more realistic “zero-shot” scenarios where out-of-domain object categories are involved. To overcome this issue, we introduce a novel “imagination” module based on Regularized Auto-Encoders, that learns context-aware and category-aware latent embeddings without relying on category labels at inference time. Our imagination module outperforms state-of-the-art competitors by 8.26% gameplay accuracy in the CompGuessWhat?! zero-shot scenario (Suglia et al., 2020), and it improves the Oracle and Guesser accuracy by 2.08% and 12.86% in the GuessWhat?! benchmark, when no gold categories are available at inference time. The imagination module also boosts reasoning about object properties and attributes.

pdf bib
SLURP: A Spoken Language Understanding Resource Package
Emanuele Bastianelli | Andrea Vanzo | Pawel Swietojanski | Verena Rieser
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

Spoken Language Understanding infers semantic meaning directly from audio data, and thus promises to reduce error propagation and misunderstandings in end-user applications. However, publicly available SLU resources are limited. In this paper, we release SLURP, a new SLU package containing the following: (1) A new challenging dataset in English spanning 18 domains, which is substantially bigger and linguistically more diverse than existing datasets; (2) Competitive baselines based on state-of-the-art NLU and ASR systems; (3) A new transparent metric for entity labelling which enables a detailed error analysis for identifying potential areas of improvement. SLURP is available at https://github.com/pswietojanski/slurp.


pdf bib
Hierarchical Multi-Task Natural Language Understanding for Cross-domain Conversational AI: HERMIT NLU
Andrea Vanzo | Emanuele Bastianelli | Oliver Lemon
Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue

We present a new neural architecture for wide-coverage Natural Language Understanding in Spoken Dialogue Systems. We develop a hierarchical multi-task architecture, which delivers a multi-layer representation of sentence meaning (i.e., Dialogue Acts and Frame-like structures). The architecture is a hierarchy of self-attention mechanisms and BiLSTM encoders followed by CRF tagging layers. We describe a variety of experiments, showing that our approach obtains promising results on a dataset annotated with Dialogue Acts and Frame Semantics. Moreover, we demonstrate its applicability to a different, publicly available NLU dataset annotated with domain-specific intents and corresponding semantic roles, providing overall performance higher than state-of-the-art tools such as RASA, Dialogflow, LUIS, and Watson. For example, we show an average 4.45% improvement in entity tagging F-score over Rasa, Dialogflow and LUIS.


pdf bib
HuRIC: a Human Robot Interaction Corpus
Emanuele Bastianelli | Giuseppe Castellucci | Danilo Croce | Luca Iocchi | Roberto Basili | Daniele Nardi
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)

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. However, the reuse of existing resources in heterogeneous domains such as Human Robot Interaction is not straightforward. The generalization offered by many data driven methods is strongly biased by the employed data, whose performance in out-of-domain conditions exhibit large drops. In this paper, we present the Human Robot Interaction Corpus (HuRIC). It is made of audio files paired with their transcriptions referring to commands for a robot, e.g. in a home environment. The recorded sentences are annotated with different kinds of linguistic information, ranging from morphological and syntactic information to rich semantic information, according to the Frame Semantics, to characterize robot actions, and Spatial Semantics, to capture the robot environment. All texts are represented through the Abstract Meaning Representation, to adopt a simple but expressive representation of commands, that can be easily translated into the internal representation of the robot.


pdf bib
Textual Inference and Meaning Representation in Human Robot Interaction
Emanuele Bastianelli | Giuseppe Castellucci | Danilo Croce | Roberto Basili
Proceedings of the Joint Symposium on Semantic Processing. Textual Inference and Structures in Corpora

pdf bib
UNITOR-HMM-TK: Structured Kernel-based learning for Spatial Role Labeling
Emanuele Bastianelli | Danilo Croce | Roberto Basili | Daniele Nardi
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)