Stergos Afantenos

• Phd
• Professor (Associate) at Toulouse Institute of Computer Science Research

Analogical proportions hold between 4 items a, b, c, d insofar as we can consider that "a is to b as c is to d". Such proportions are supposed to obey postulates, from which one can derive Boolean or numerical models that relate vector-based representations of items making a proportion. One basic postulate is the preservation of the proportion by p...

Analogical proportions hold between 4 items a, b, c, d insofar as we can consider that “a is to b as c is to d”. Such proportions are supposed to obey postulates, from which one can derive Boolean or numerical models that relate vector-based representations of items making a proportion. One basic postulate is the preservation of the proportion by p...

Parsing of argumentative structures has become a very active line of research in recent years. Like discourse parsing or any other natural language task that requires prediction of linguistic structures, most approaches choose to learn a local model and then perform global decoding over the local probability distributions, often imposing constraint...

In this paper we propose a novel Deep Reinforcement Learning (DRL) algorithm that uses the concept of “action-dependent state features”, and exploits it to approximate the Q-values locally, employing a deep neural network with parallel Long Short Term Memory (LSTM) components, each one responsible for computing an action-related Q-value. As such, a...

Parsing of argumentative structures has become a very active line of research in recent years. Like discourse parsing or any other natural language task that requires prediction of linguistic structures, most approaches choose to learn a local model and then perform global decoding over the local probability distributions, often imposing constraint...

In this paper we report on the efforts of three projects to annotate texts and dialogues with discourse structure. We provide a theoretical discussion of various alternatives and then present our approach to discourse structure annotation, along with some applications of the resources that we have developed.

This paper presents a knowledge base containing triples involving pairs of verbs associated with semantic or discourse relations. The relations in these triples are marked by discourse connectors between two adjacent instances of the verbs in the triple in the large French corpus, frWaC. We detail several measures that evaluate the relevance of the...

Despite the central role that argumentation plays in human communication, the computational linguistics community has paid relatively little attention in proposing a methodology for automatically identifying arguments and their relations in texts. Argumentation is intimately related with discourse structure, since an argument often spans more than...

Several discourse annotated corpora now exist for NLP. But they use different, not easily comparable annotation schemes: are the structures these schemes describe incompatible , incomparable, or do they share interpre-tations? In this paper, we relate three types of discourse annotation used in corpora or discourse parsing: (i) RST, (ii) SDRT, and...

This paper presents a novel approach to document-based discourse analysis by performing a global A* search over the space of possible structures while optimizing a global criterion over the set of potential coherence relations. Existing approaches to discourse analysis have so far relied on greedy search strategies or restricted themselves to sente...

We describe a dialogue model and an implemented annotation scheme for a pilot corpus of annotated online chats concerning bargaining negotiations in the game The Settlers of Catan. We will use this model and data to analyze how conversations proceed in the absence of strong forms of cooperativity, where agents have diverging motives. Here we concen...

We describe the Annodis corpus of discourse structures for French. The corpus joins two perspectives on discourse on a variety of textual genres: a bottom-up approach and a top-down approach. The bottom-up view builds incrementally a structure from elementary discourse units, while the top-down view focuses on the selective annotation of multi-leve...

This paper describes the ANNODIS ressource, a corpus of written French enriched with several markups, including a manual annotation of discourse structures. The resource is original in that it offers a diversified corpus representing several text types, and two annotations based on different approaches to discourse organisation. As well as a descri...

This paper describes the ANNODIS ressource, a corpus of written French enriched with several markups, including a manual annotation of discourse structures. The resource is original in that it offers a diversified corpus representing several text types, and two annotations based on different approaches to discourse organisation. As well as a descri...

In this paper, we address the problem of detecting deriveation and co-derivation relationships between pairs of news articles in French. We use the fingerprinting framework widely used in the related works, and we experiment several descriptors selected for their singularity:-grams hapax, named entities, nominal compounds and discourse connectives....

The Right Frontier Constraint (RFC), as a constraint on the attachment of new constituents to an existing discourse structure, has important implications for the interpretation of anaphoric elements in discourse and for Machine Learning (ML) approaches to learning discourse structures. In this paper we provide strong empirical support for SDRT's ve...

Automatically detecting discourse segments is an important preliminary step towards full discourse parsing. Previous research on discourse segmentation have relied on the assumption that elementary discourse units (EDUs) in a document always form a linear sequence (i.e., they can never be nested). Unfortunately, this assumption turns out to be too...

Speaking a language and achieving proficiency in another one is a highly complex process which requires the acquisition of various kinds of knowledge, declarative and procedural (skills), like the learning of words, rules or patterns and their connection to communicative goals (intentions), the usual starting point. In order to help the learner acq...

L'objectif de la démonstration est d'une part de faire un retour d'expérience sur la solution logicielle Apache UIMA comme infrastructure de développement d'applications distribuées de TAL, et d'autre part de présenter les développements réalisés par l'équipe TALN du LINA pour permettre à la communauté de s'approprier ce « framework ».

Dans cet article nous nous intéressons au problème de la détection de réutilisation de texte. Plus particulièrement, étant donné un document original et un ensemble de documents candidats — thématiquement similaires au premier — nous cherchons à classer ceux qui sont dérivés du document original et ceux qui ne le sont pas. Nous abordons le problème...

In this paper we present the first step in a larger series of experiments for the induction of predicate/argument structures. The structures that we are inducing are very similar to the conceptual structures that are used in Frame Semantics (such as FrameNet). Those structures are called messages and they were previously used in the context of a mu...

In this paper we present the first step in a larger series of experiments for the induction of predicate/ argument structures. The structures that we are inducing are very similar to the conceptual structures that are used in Frame Semantics (such as FrameNet). Those structures are called messages and they were previously used in the context of a m...

In this paper we present a fresh look at the problem of summarizing evolving events from multiple sources. After a discussion concerning the nature of evolving events we introduce a distinction between linearly and non-linearly evolving events. We present then a general methodology for the automatic creation of summaries from evolving events. At it...

Speaking a language and achieving proficiency in another one is a highly complex process which requires the acquisition of various kinds of knowledge and skills, like the learning of words, rules and patterns and their connection to communicative goals (intentions), the usual starting point. To help the learner to acquire these skills we propose an...

Speaking a language and achieving proficiency in another one is a highly complex process which requires the acquisition of various kinds of knowledge and skills, like the learning of words, rules and patterns and their connection to communicative goals (intentions), the usual starting point. To help the learner to acquire these skills we propose an...

Despite its importance, the task of summarizing evolving events has received small attention by researchers in the field of multi-document summariztion. In a previous paper (Afantenos et al. 2007) we have presented a methodology for the automatic summarization of documents, emitted by multiple sources, which describe the evolution of an event. At t...

In this paper we present a fresh look at the problem of summarizing evolving events from multiple sources. After a discussion concerning the nature of evolving events we introduce a distinction between linearly and non-linearly evolving events. We present then a general methodology for the automatic creation of summaries from evolving events. At it...

In this PhD work we present a fresh look at the problem of summarizing evolving events from multiple sources. After a discussion concerning the nature of evolving events we introduce a distinction be-tween linearly and non-linearly evolving events. We present then a gen-eral methodology for the automatic creation of summaries from evolving events....

We present an approach for summarization from multiple documents which report on events that evolve through time, taking into account the different document sources. We distinguish the evolution of an event into linear and non-linear. According to our approach, each document is represented by a collection of messages which are then used in order to...

This paper examines the summarization of events that evolve through time. It discusses different types of evolution taking into account the time in which the incidents of an event are happening and the different sources reporting on the specific event. It proposes an approach for multi-document summarization which employs ``messages'' for represent...

Objective: The aim of this paper is to survey the recent work in medical documents summarization. Background: During the last decade, documents summarization got increasing attention by the AI research community. More recently it also attracted the interest of the medical research community as well, due to the enormous growth of information that is...

The aim of this paper is to survey the recent work in medical documents summarization. During the last decade, documents summarization got increasing attention by the AI research community. More recently it also attracted the interest of the medical research community as well, due to the enormous growth of information that is available to the physi...

We examine a method for the creation of multi-document evolving summaries, i.e. summaries of events that evolve through time. We distinguishsuch summaries into linear and non-linear. In this paper we focus in summariesthat evolve linearly. In order to tackle the problem we introduce thenotion of cross-document relations which connect some simple st...

This paper presents a methodology for summarization from multiple documents which are about a specific topic. It is based on the specification and identification of the cross-document relations that occur among textual elements within those documents. Our methodology involves the specification of the topic-specific entities, the messages conveyed f...

The problem that this article is dealing with is that of Pattern Matching. We are seeking for an effcient algorithm that, given a pattern and a string of characters, will determine whether the string matches the pattern or not. In our quest we are going to encounter elements from the theory of regular languages and automata. We begin by presenting...

this report.