Egoitz Laparra

Exploiting Explicit Annotations and Semantic Types for Implicit Argument Resolution

Following the frame semantics paradigm, we present a novel strategy for solving null-instantiated arguments. Our method learns probability distributions of semantic types for each Frame Element from explicit corpus annotations. These distributions are used to select the most probable missing implicit arguments together with its most probable fillers. We empirically demonstrate that our method outperforms the systems evaluated on the Sem Eval 2010 task 10 dataset.

Document Level Time-anchoring for TimeLine Extraction

This paper investigates the contribution of document level processing of timeanchors for TimeLine event extraction. We developed and tested two different systems. The first one is a baseline system that captures explicit time-anchors. The second one extends the baseline system by also capturing implicit time relations. We have evaluated both approaches in the SemEval 2015 task 4 TimeLine: CrossDocument Event Ordering. We empirically demonstrate that the document-based approach obtains a much more complete time anchoring. Moreover, this approach almost doubles the performance of the systems that participated in the task.

From TimeLines to StoryLines: A preliminary proposal for evaluating narratives

We formulate a proposal that covers a new definition of StoryLines based on the shared data provided by the NewsStory workshop. We re-use the SemEval 2015 Task 4: Timelines dataset to provide a gold-standard dataset and an evaluation measure for evaluating StoryLines extraction systems. We also present a system to explore the feasibility of capturing StoryLines automatically. Finally, based on our initial findings, we also discuss some simple changes that will improve the existing annotations to complete our initial Story-

Predicate Matrix: automatically extending the semantic interoperability between predicate resources

This paper presents a novel approach to improve the interoperability between four semantic resources that incorporate predicate information. Our proposal defines a set of automatic methods for mapping the semantic knowledge included in WordNet, VerbNet, PropBank and FrameNet. We use advanced graph-based word sense disambiguation algorithms and corpus alignment methods to automatically establish the appropriate mappings among their lexical entries and roles. We study different settings for each method using SemLink as a gold-standard for evaluation. The results show that the new approach provides productive and reliable mappings. In fact, the mappings obtained automatically outnumber the set of original mappings in SemLink. Finally, we also present a new version of the Predicate Matrix, a lexical-semantic resource resulting from the integration of the mappings obtained by our automatic methods and SemLink.

Multi-lingual and Cross-lingual timeline extraction

Abstract In this paper we present an approach to extract ordered timelines of events, their participants, locations and times from a set of Multilingual and Cross-lingual data sources. Based on the assumption that event-related information can be recovered from different documents written in different languages, we extend the Cross-document Event Ordering task presented at SemEval 2015 by specifying two new tasks for, respectively, Multilingual and Cross-lingual timeline extraction. We then develop three deterministic algorithms for timeline extraction based on two main ideas. First, we address implicit temporal relations at document level since explicit time-anchors are too scarce to build a wide coverage timeline extraction system. Second, we leverage several multilingual resources to obtain a single, interoperable, semantic representation of events across documents and across languages. The result is a highly competitive system that strongly outperforms the current state-of-the-art. Nonetheless, further analysis of the results reveals that linking the event mentions with their target entities and time-anchors remains a difficult challenge. The systems, resources and scorers are freely available to facilitate its use and guarantee the reproducibility of results.

Semantic Interoperability for Cross-lingual and cross-document Event Detection

We describe a system for event extraction across documents and languages. We developed a framework for the interoperable semantic interpretation of mentions of events, participants, locations and time, as well as the relations between them. Furthermore, we use a common RDF model to represent instances of events and normalised entities and dates. We convert multiple mentions of the same event in English, Spanish and Dutch to a single representation. We thus resolve crossdocument event and entity coreference within a language but also across languages. We tested our system on a Wikinews corpus of 120 English articles that have been manually translated to Spanish and Dutch. We report on the cross-lingual cross-document event and entity extraction comparing the Spanish and Dutch output with respect to English.