Document Level Time-anchoring for TimeLine Extraction

Laparra, Egoitz; Aldabe, Itziar; Rigau, Germán

doi:10.3115/v1/p15-2059

Cited by 10 publications

(9 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The SemEval 2015 Task 4 TimeLine: Cross‐document event ordering (Minard et al., ) introduced benchmark datasets for multi‐document timeline extraction. System results vary from 7.12 to 14.31 F1 (Caselli, Fokkens, Morante, & Vossen, ; Laparra, Aldabe, & Rigau, ). These results highlight the complexity of the task as it combines event co‐reference with temporal processing.…”

Section: Reconstructing Storylinesmentioning

confidence: 99%

How Concrete Do We Get Telling Stories?

Vossen

Caselli²,

Cybulska

2018

Topics in Cognitive Science

View full text Add to dashboard Cite

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 concrete mental movie. Since our episodic knowledge differs, also the mental movie will be different. Language leaves out details, and this becomes specifically clear when building machines that read texts to represent events and to establish event relations across mentions, such as co-reference, causality, subevents, scripts, timelines, and storylines. There is a lot of information and knowledge on the event that is not in the text but is needed to reconstruct these relations and understand the story. Machines lack this knowledge and experience and likewise make explicit what it takes to understand stories from text. In this paper, we report on experiments to automatically model event descriptions and instances across different news articles. We will show that event information is scattered over the text but also varies a lot in the degree it abstracts from details, which makes establishing event identity and relations extremely difficult. The variation in granularity of event descriptions seems to vary with pragmatic communicative strategies and defines the problem at different levels of complexity.

show abstract

Section: Reconstructing Storylinesmentioning

confidence: 99%

How Concrete Do We Get Telling Stories?

Vossen

Caselli²,

Cybulska

2018

Topics in Cognitive Science

View full text Add to dashboard Cite

show abstract

“…BTE performs timeline extraction by combining the output of a NLP pipeline for both English and Spanish. The baseline system is then improved in section 6.2 by applying the algorithm presented in Laparra et al (2015) to perform document level time-anchoring (DLT). While both BTE and DLT can be used for multilingual timeline extraction, their performance in the cross-lingual setting is not as good as in the English and Multilingual tasks.…”

Section: Automatic Cross-lingual Timeline Extractionmentioning

confidence: 99%

“…In Laparra et al (2015) we devised a simple strategy to capture implicit time-anchors while maintaining the coherence of the temporal information in the document. The rationale behind the algorithm shown in Algorithm 1 is that, by default, the events of a specific entity that appear in a document tend to occur at the same time as previous events involving the same entity (unless explicitly stated).…”

Section: Dlt: Document Level Time-anchoringmentioning

confidence: 99%

“…We present a deterministic approach that obtains, by far, the best results on the main Track A of SemEval 2015 task 4. Our deterministic approach is fledged out via three different timeline extraction systems which extend an initial version presented in Laparra et al (2015). To guarantee reproducibility of results we also make publicly available the systems, datasets and scripts used to perform the evaluations 3 .…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi-lingual and Cross-lingual timeline extraction

Laparra

Agerri

Aldabe

et al. 2017

Knowledge-Based Systems

Self Cite

View full text Add to dashboard Cite

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.

show abstract

“…This way, we create a simple system which merges automatically extracted TimeLines. To build the TimeLines, we use the system which currently obtains the best results in Track A (Laparra et al, 2015). The system follows a three step process to detect events, time-anchors and to sort the events according to their time-anchors.…”

Section: Example Of a System-runmentioning

confidence: 99%

Proceedings of the First Workshop on Computing News Storylines

Caselli

Erp

Minard

et al. 2015

View full text Add to dashboard Cite

at the heart of information sharing. Ever since people began to share their experiences, they have connected them to form narratives. The study of storytelling and the field of literary theory called narratology have developed complex frameworks and models related to various aspects of narrative such as plots structures, narrative embeddings, characters' perspectives, reader response, point of view, narrative voice, narrative goals, and many others. These notions from narratology have been applied mainly in Artificial Intelligence and to model formal semantic approaches to narratives (e.g. Plot Units developed by Lehnert (1981)). In recent years, computational narratology has qualified as an autonomous field of study and research. Narrative has been the focus of a number of workshops and conferences (AAAI Symposia, Interactive Storytelling Conference (ICIDS), Computational Models of Narrative). Furthermore, reference annotation schemes for narratives have been proposed (NarrativeML by Mani (2013)). The majority of the previous work on narratives and narrative structures have mainly focused on the analysis of fictitious texts. However, modern day news reports still reflect this narrative structure, but they have proven difficult for automatic tools to summarise, structure, or connect to other reports. This difficulty is partly rooted in the fact that most text processing tools focus on extracting relatively simple structures from the local lexical environment, and concentrate on the document as a unit or on even smaller units such as sentences or phrases, rather than cross-document connections. However, current information needs demand a move towards multidimensional and distributed representations which take into account the connections between all relevant elements involved in a "story". Additionally, most work on cross-document temporal processing focuses on linear timelines, i.e. representations of chronologically ordered events in time (for instance, the Event Narrative Event Chains by Chambers (2011), or the SemEval 2015 Task 4: Cross Document TimeLines by ). Storylines, though, are more complex, and must take into account temporal, causal and subjective dimensions. How storylines should be represented and annotated, how they can be extracted automatically, and how they can be evaluated are open research questions in the NLP and AI communities. The workshop aimed to bring together researchers from different communities working on representing and extracting narrative structures in news, a text genre which is highly used in NLP but which has received little attention with respect to narrative structure, representation and analysis. Currently, advances in NLP technology have made it feasible to look beyond scenario-driven, atomic extraction of events from single documents and work towards extracting story structures from multiple documents, while these documents are published over time as news streams. Policy makers, NGOs, information specialists (such as journalists and librarians) and others are increasingl...

show abstract

Document Level Time-anchoring for TimeLine Extraction

Cited by 10 publications

References 18 publications

How Concrete Do We Get Telling Stories?

How Concrete Do We Get Telling Stories?

Multi-lingual and Cross-lingual timeline extraction

Proceedings of the First Workshop on Computing News Storylines

Contact Info

Product

Resources

About