Piek Vossen

Vrije Universiteit Amsterdam | VU · Faculty of Humanities

Inspired by the cognitive science theory of the explicit human memory systems, we have modeled an agent with short-term, episodic, and semantic memory systems, each of which is modeled with a knowledge graph. To evaluate this system and analyze the behavior of this agent, we designed and released our own reinforcement learning agent environment, "t...

We present a new method based on episodic Knowledge Graphs (eKGs) for evaluating (multimodal) conversational agents in open domains. This graph is generated by interpreting raw signals during conversation and is able to capture the accumulation of knowledge over time. We apply structural and semantic analysis of the resulting graphs and translate t...

The paper describes a flexible and modular platform to create multimodal interactive agents. The platform operates through an event-bus on which signals and interpretations are posted in a sequence in time. Different sensors and interpretation components can be integrated by defining their input and output as topics, which results in a logical work...

Inspired by the cognitive science theory, we explicitly model an agent with both semantic and episodic memory systems, and show that it is better than having just one of the two memory systems. In order to show this, we have designed and released our own challenging environment, "the Room", compatible with OpenAI Gym, where an agent has to properly...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

On social media, new forms of communication arise rapidly, many of which are intense, dispersed, and create new communities at a global scale. Such communities can act as distinct information bubbles with their own perspective on the world, and it is difficult for people to find and monitor all these perspectives and relate the different claims mad...

We present EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa, a simple yet expressive scheme of solving the ERC (emotion recognition in conversation) task. By simply prepending speaker names to utterances and inserting separation tokens between the utterances in a dialogue, EmoBERTa can learn intra- and inter- speaker states...

We present EMISSOR: a platform to capture multimodal interactions as recordings of episodic experiences with explicit referential interpretations that also yield an episodic Knowledge Graph (eKG). The platform stores streams of multiple modalities as parallel signals. Each signal is segmented and annotated independently with interpretation. Annotat...

This chapter describes technical approaches that aim to address the challenges involved in finding accurate and up-to-date information. We focus on two challenges: the challenge of finding all relevant information and the challenge of determining the reliability of this information. The chapter examines the potential contributions of current techni...

We define hybrid intelligence (HI) as the combination of human and machine intelligence, augmenting human intellect and capabilities instead of replacing them and achieving goals that were unreachable by either humans or machines. HI is an important new research focus for artificial intelligence, and we set a research agenda for HI by formulating f...

The NIL entities do not have an accessible representation, which means that their identity cannot be established through traditional disambiguation. Consequently, they have received little attention in entity linking systems and tasks so far. Given the non-redundancy of knowledge on NIL entities, the lack of frequency priors, their potentially extr...

This paper presents a model of contextual awareness implemented for a social communicative robot Leolani. Our model starts from the assumption that robots and humans need to establish a common ground about the world they share. This is not trivial as robots make many errors and start with little knowledge. As such, the context in which communicatio...

People and robots make mistakes and should therefore recognize and communicate about their "imperfectness" when they collaborate. In previous work [3, 2], we described a female robot model Leolani(L) that supports open-domain learning through natural language communication, having a drive to learn new information and build social relationships. The...

We describe a model for a robot that learns about the world and her companions through natural language communication. The model supports open-domain learning, where the robot has a drive to learn about new concepts, new friends, and new properties of friends and concept instances. The robot tries to fill gaps, resolve uncertainties and resolve con...

The human mind is a powerful multifunctional knowledge storage and management system that performs generalization, type inference, anomaly detection, stereotyping, and other tasks. A dynamic KR system that appropriately profiles over sparse inputs to provide complete expectations for unknown facets can help with all these tasks. In this paper, we i...

Our state of mind is based on experiences and what other people tell us. This may result in conflicting information, uncertainty, and alternative facts. We present a robot that models relativity of knowledge and perception within social interaction following principles of the theory of mind. We utilized vision and speech capabilities on a Pepper ro...

State-of-the-art entity linkers achieve high accuracy scores with probabilistic methods. However, these scores should be considered in relation to the properties of the datasets they are evaluated on. Until now, there has not been a systematic investigation of the properties of entity linking datasets and their impact on system performance. In this...

Will reading different stories about the same event in the world result in a similar image of the world? Will reading the same story by different people result in a similar proxy for experiencing the story? The answer to both questions is no because language is abstract by definition and relies on our episodic experience to turn a story into a more...

Our state of mind is based on experiences and what other people tell us. This may result in conflicting information, uncertainty, and alternative facts. We present a robot that models relativity of knowledge and perception within social interaction following principles of the theory of mind. We utilized vision and speech capabilities on a Pepper ro...

In this paper, we describe the Circumstantial Event Ontology (CEO), a newly developed ontology for calamity events that models semantic circumstantial relations between event classes, where we define circumstantial as inferred implicit causal relations. The circumstantial relations are inferred from the assertions of the event classes that involve...

This paper describes BiographyNet, a digital humanities project (2012-2016) that brings together researchers from history, computational linguistics and computer science. The project uses data from the Biography Portal of the Netherlands (BPN), which contains approximately 125,000 biographies from a variety of Dutch biographical dictionaries from t...

Recognising entities in a text and linking them to an external resource is a vital step in creating a structured resource (e.g. a knowledge base) from text. This allows semantic querying over a dataset, for example selecting all politicians or football players. However, traditional named entity recognition systems only distinguish a limited number...

Over the past years, several challenges and calls for research projects have pointed out the dire need for pushing natural language interfaces. In this context, the importance of Semantic Web data as a premier knowledge source is rapidly increasing. But we are still far from having accurate natural language interfaces that allow handling complex in...

Automatic image description systems are commonly trained and evaluated on large image description datasets. Recently, researchers have started to collect such datasets for languages other than English. An unexplored question is how different these datasets are from English and, if there are any differences, what causes them to differ. This paper pr...

The task of entity linking (EL) is often perceived as an algorithmic problem, where the novelty of systems lies in the decision making process, while the knowledge is relatively fixed. As a consequence, we lack an understanding about the importance and the relevance of diverse knowledge types in EL. However, knowledge and relevance are crucial: fol...

A Road Map to Intelligent Entity Linking

Many entity recognition approaches classify recognised entities into a limited set of coarse-grained entity types. However, for deeper natural language analysis and end-user tasks, fine-grained entity types are more useful. For example, while standard named entity recognition may determine that an entity is a person knowing whether that entity is a...

In this paper we describe a method to detect event descrip- tions in different news articles and to model the semantics of events and their components using RDF representations. We compare these descriptions to solve a cross-document event coreference task. Our com- ponent approach to event semantics defines identity and granularity of events at di...

Current Word Sense Disambiguation systems show an extremely poor performance on low frequent senses, which is mainly caused by the difference in sense distributions between training and test data. The main focus in tackling this problem has been on acquiring more data or selecting a single predominant sense and not necessarily on the meta propertie...

Semantic text processing faces the challenge of defining the relation between lexical expressions and the world to which they make reference within a period of time. It is unclear whether the current test sets used to evaluate disambiguation tasks are representative for the full complexity considering this time-anchored relation, resulting in seman...

Semantic text processing faces the challenge of defining the relation between lexical expressions and the world to which they make reference within a period of time. It is unclear whether the current test sets used to evaluate disambiguation tasks are representative for the full complexity considering this time-anchored relation, resulting in seman...

Entities and events in the world have no frequency, but our communication about them and the words we use to refer to them do have a strong frequency profile. Language expressions and their meanings follow a Zipfian distribution, featuring a small amount of very frequent observations and a very long tail of low frequent observations. Since our NLP...

In this article, we describe a system that . reads news articles in four different languages and detects what happened, who is involved, where and when. This event-centric information is represented as episodic situational knowledge on individuals in an interoperable RDF format that allows for reasoning on the implications of the events. Our system...

Humanities scholars agree that the visualization of their data should bring order and insight, reveal patterns and provide leads for new research questions. However, simple two-dimensional visualizations are often too static and too generic to meet these needs. Visualization tools for the humanities should be able to deal with the observer dependen...

We describe a novel modular system for cross-lingual event extraction for English, Spanish,, Dutch and Italian texts. The system consists of a ready-to-use modular set of advanced multilingual Natural Language Processing (NLP) tools. The pipeline integrates modules for basic NLP processing as well as more advanced tasks such as cross-lingual Named...

Knowledge graphs have gained increasing popularity in the past couple of years, thanks to their adoption in everyday search engines. Typically, they consist of fairly static and encyclopedic facts about persons and organizations–e.g. a celebrity’s birth date, occupation and family members–obtained from large repositories such as Freebase or Wikiped...

In this paper we present an approach to Word Sense Disambiguation based on Topic Modeling (LDA). Our approach consists of two different steps, where first a binary classifier is applied to decide whether the most frequent sense applies or not, and then another classifier deals with the non most frequent sense cases. An exhaustive evaluation is perf...

We present in this paper our submission to task 13 of SemEval2015, which makes use of background information and external resources (DBpedia and Wikipedia) to automatically disambiguate texts. Our approach follows two routes for disambiguation: one route is proposed by a state–of–the–art WSD system, and the other one by the predominant sense inform...

In this paper, we present a rich contex-tual perspective on the lexicon and back-ground knowledge for the purpose of deep semantic parsing. In the project Under-standing Language By machine 1 , we ad-dress various aspects of semantics in rela-tion to i.) reference to entities and event in-stances, ii.) modeling of author and reader perspectives. Le...

Word Sense Disambiguation is still an unsolved problem in Natural Language Processing. We claim that most approaches do not model the context correctly, by relying too much on the local context (the words surrounding the word in question), or on the most frequent sense of a word. In order to provide evidence for this claim, we conducted an in-depth...

We present an analysis of a high-level semantic task, the construction of cross-document event timelines from SemEval 2015 Task 4: TimeLine, to trace down errors to the components of our pipeline system. Event timeline extraction requires many different Natural Language Processing tasks among which entity and event detection, coreference resolution...

Using clues from event semantics to solve coreference, we present an “event template” approach to cross-document event coreference resolution on news articles. The approach uses a pairwise model, in which event information is compared along five semantically motivated slots of an event template. The templates, filled in on the sentence level for ev...