Alessandra Cervone

Alessandra Cervone
Università degli Studi di Trento | UNITN · Department of Information Engineering and Computer Science

PhD Student

About

35
Publications
2,984
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
163
Citations
Citations since 2017
31 Research Items
161 Citations
2017201820192020202120222023010203040
2017201820192020202120222023010203040
2017201820192020202120222023010203040
2017201820192020202120222023010203040
Additional affiliations
September 2016 - present
Università degli Studi di Trento
Position
  • PhD Student
November 2013 - February 2014
The University of Edinburgh
Position
  • Intern
February 2012 - February 2013
University of Pavia
Position
  • academic tutor
Education
September 2014 - September 2015
The University of Edinburgh
Field of study
  • Computer Science
February 2013 - August 2013
Freie Universität Berlin
Field of study
  • Linguistics
September 2008 - April 2014
University of Pavia
Field of study
  • Linguistics

Publications

Publications (35)
Preprint
The tasks of humor understanding and generation are challenging and subjective even for humans, requiring commonsense and real-world knowledge to master. Puns, in particular, add the challenge of fusing that knowledge with the ability to interpret lexical-semantic ambiguity. In this paper, we present the ExPUNations (ExPUN) dataset, in which we aug...
Preprint
Full-text available
Users interacting with voice assistants today need to phrase their requests in a very specific manner to elicit an appropriate response. This limits the user experience, and is partly due to the lack of reasoning capabilities of dialogue platforms and the hand-crafted rules that require extensive labor. One possible way to improve user experience a...
Preprint
Full-text available
In recent years, large pretrained models have been used in dialogue systems to improve successful task completion rates. However, lack of reasoning capabilities of dialogue platforms make it difficult to provide relevant and fluent responses, unless the designers of a conversational experience spend a considerable amount of time implementing these...
Preprint
Personal Narratives (PN) - recollections of facts, events, and thoughts from one's own experience - are often used in everyday conversations. So far, PNs have mainly been explored for tasks such as valence prediction or emotion classification (i.e. happy, sad). However, these tasks might overlook more fine-grained information that could nevertheles...
Preprint
Full-text available
In this work, we investigate the human perception of coherence in open-domain dialogues. In particular, we address the problem of annotating and modeling the coherence of next-turn candidates while considering the entire history of the dialogue. First, we create the Switchboard Coherence (SWBD-Coh) corpus, a dataset of human-human spoken dialogues...
Preprint
Full-text available
We are interested in the problem of understanding personal narratives (PN) - spoken or written - recollections of facts, events, and thoughts. In PN, emotion carriers are the speech or text segments that best explain the emotional state of the user. Such segments may include entities, verb or noun phrases. Advanced automatic understanding of PNs re...
Preprint
Full-text available
The increase in the prevalence of mental health problems has coincided with a growing popularity of health related social networking sites. Regardless of their therapeutic potential, On-line Support Groups (OSGs) can also have negative effects on patients. In this work we propose a novel methodology to automatically verify the presence of therapeut...
Conference Paper
With an ever-increasing amount of information and ever-more-hectic lifestyles, many people rely on news briefs to stay up to date. Consequently, the reliance on single-source media narratives can lead to a biased and narrow perception of the world. Conversational interfaces, as a medium for delivering news stories, can help to address this problem...
Preprint
Full-text available
Natural Language Understanding (NLU) models are typically trained in a supervised learning framework. In the case of intent classification, the predicted labels are predefined and based on the designed annotation schema while the labelling process is based on a laborious task where annotators manually inspect each utterance and assign the correspon...
Preprint
Full-text available
Automated prediction of valence, one key feature of a person's emotional state, from individuals' personal narratives may provide crucial information for mental healthcare (e.g. early diagnosis of mental diseases, supervision of disease course, etc.). In the Interspeech 2018 ComParE Self-Assessed Affect challenge, the task of valence prediction was...
Preprint
Full-text available
Current approaches to Natural Language Generation (NLG) focus on domain-specific, task-oriented dialogs (e.g. restaurant booking) using limited ontologies (up to 20 slot types), usually without considering the previous conversation context. Furthermore, these approaches require large amounts of data for each domain, and do not benefit from examples...
Conference Paper
Full-text available
Automatic evaluation models for open-domain conversational agents either correlate poorly with human judgment or require expensive annotations on top of conversation scores. In this work we investigate the feasibility of learning evaluation models without relying on any further annotations besides conversation-level human ratings. We use a dataset...
Preprint
Full-text available
Automatic evaluation models for open-domain conversational agents either correlate poorly with human judgment or require expensive annotations on top of conversation scores. In this work we investigate the feasibility of learning evaluation models without relying on any further annotations besides conversation-level human ratings. We use a dataset...
Preprint
Full-text available
Coherence across multiple turns is a major challenge for state-of-the-art dialogue models. Arguably the most successful approach to automatically learning text coherence is the entity grid, which relies on modelling patterns of distribution of entities across multiple sentences of a text. Originally applied to the evaluation of automatic summaries...
Preprint
Full-text available
Dialogue Act (DA) tagging is crucial for spoken language understanding systems, as it provides a general representation of speakers' intents, not bound to a particular dialogue system. Unfortunately, publicly available data sets with DA annotation are all based on different annotation schemes and thus incompatible with each other. Moreover, their s...
Conference Paper
Full-text available
Dialogue Act (DA) tagging is crucial for spoken language understanding systems, as it provides a general representation of speakers' intents, not bound to a particular dialogue system. Unfortunately , publicly available data sets with DA annotation are all based on different annotation schemes and thus incompatible with each other. Moreover, their...
Conference Paper
Full-text available
The phenomenon of reported speech – whereby we quote the words, thoughts and opinions of others, or recount past dialogue – is widespread in conversational speech. Detecting such quotations automatically has numerous applications: for example , in enhancing automatic transcription or spoken language understanding applications. However, the task is...
Conference Paper
Full-text available
In this work we present a methodology for the annotation of Attri-bution Relations (ARs) in speech which we apply to create a pilot corpus of spo-ken informal dialogues. This represents the first step towards the creation of a re-source for the analysis of ARs in speech and the development of automatic extrac-tion systems. Despite its relevance for...

Network

Cited By

Projects

Projects (3)
Project
A conversational agent is a software that is able to answer specific or generic users requests, to interact and to help accomplish his or her goals. These goals maybe explicitly defined as in the case of an artificial intelligent agent helping users plan for a vacation trip. In other cases goals may not have been clearly defined as in a problem solving task or in a socially entertaining robot interaction. The complexity of this system varies a lot and include the ability to process a multimodal human inputs, acoustic scene sensors and processing massive amount of data. We have been developing technology for such agents — spoken dialog systems for telephone, desktop browsers, smartphones, social bots and consumer robots since the early nineties. Demos @ http://sisl.disi.unitn.it/conversational-machines-with-partially-observable-markov-decision-processes/ Publications @ http://sisl.disi.unitn.it/publications/
Project
The basic assumption is the activation of neural networks. The neural networks of patients suffering from symptoms are dominantly problem-oriented. Via therapy, problem-oriented networks should be overwritten by solution-oriented networks. Mobile Voice Feedback shall provide visual feedback in real-time about the network that is currently activated. This feature can be used as biofeedback in web- and mobile-based interventions. Also it can be used in therapeutic settings to evaluate the time spent in solution and problem-oriented networks.
Archived project
Advance current research in conversational A.I.