One major limitation to the applicability of Reinforcement Learning (RL) to many practical domains is the large number of samples required to learn an optimal policy. To address this problem and improve learning efficiency, we consider a linear hierarchy of abstraction layers of the Markov Decision...
04b Atto di convegno in volume
-
-
This extended abstract summarizes our recent work in which we study a dynamic Controlled Query Evaluation method over Description Logic ontologies.
-
Sequential Recommender Systems (SRSs) are a popular type of recommender system that leverages user history to predict the next item of interest. However, the presence of noise in user interactions, stemming from account sharing, inconsistent preferences, or accidental clicks, can significantly...
-
Behavioural Cloning is a Machine Learning method concerning how a machine attempts to autonomously mimic the actions of a human, or in general a complex controller, performing a given task. This work innovatively exploits Behavioural Cloning in support of Pediatric Neurorehabilitation. In...
-
We consider an agent acting to fulfil tasks in a nondeterministic environment. When a strategy that fulfills the task regardless of how the environment acts does not exist, the agent should at least avoid adopting strategies that prevent from fulfilling its task. Best-effort synthesis captures this...
-
Sharing, discovering, and integrating data is a crucial task and poses many challenging spots and open research direction. Data owners need to know what data consumers want and data consumers need to find datasets that are satisfactory for their tasks. Several data market platforms, or data...
-
In practical settings, classification datasets are obtained through a labelling process that is usually done by humans. Labels can be noisy as they are obtained by aggregating the different individual labels assigned to the same sample by multiple and possibly disagreeing, annotators. The inter-...
-
In this paper, we examine the current state-of-the-art in AMR parsing, which relies on ensemble strategies by merging multiple graph predictions. Our analysis reveals that the present models often violate AMR structural constraints. To address this issue, we develop a validation method, and show...
-
This paper introduces a novel aligner for Abstract Meaning Representation (AMR) graphs that can scale cross-lingually, and is thus capable of aligning units and spans in sentences of different languages. Our approach leverages modern Transformer-based parsers, which inherently encode alignment...
-
Abstract Meaning Representation (AMR) is a Semantic Parsing formalism that aims at providing a semantic graph abstraction representing a given text. Current approaches are based on autoregressive language models such as BART or T5, fine-tuned through Teacher Forcing to obtain a linearized version...