Inferring Implicit Event Locations from Context with Distributional Similarities
نویسندگان
چکیده
Automatic event location extraction from text plays a crucial role in many applications such as infectious disease surveillance and natural disaster monitoring. The fundamental limitation of previous work such as SpaceEval is the limited scope of extraction, targeting only at locations that are explicitly stated in a syntactic structure. This leads to missing a lot of implicit information inferable from context in a document, which amounts to nearly 40% of the entire location information. To overcome this limitation for the first time, we present a system that infers the implicit event locations from a given document. Our system exploits distributional semantics, based on the hypothesis that if two events are described by similar expressions, it is likely that they occur in the same location. For example, if “A bomb exploded causing 30 victims” and “many people died from terrorist attack in Boston” are reported in the same document, it is highly likely that the bomb exploded in Boston. Our system shows good performance of a 0.58 F1-score, where state-of-the-art classifiers for intra-sentential spatiotemporal relations achieve around 0.60 F1-scores.
منابع مشابه
On the contribution of word embeddings to temporal relation classification
Temporal relation classification is a challenging task, especially when there are no explicit markers to characterise the relation between temporal entities. This occurs frequently in intersentential relations, whose entities are not connected via direct syntactic relations making classification even more difficult. In these cases, resorting to features that focus on the semantic content of the...
متن کاملA Hierarchical Semantics-Aware Distributional Similarity Scheme
The context type and similarity calculation are two essential features of a distributional similarity scheme (DSS). In this paper, we propose a hierarchical semanticaware DSS that exploits semantic relation words as extra context information to guide the similarity calculation. First, we define and extract five types of semantic relations, and then develop relation-based similarities from the d...
متن کاملA Contextual Framework for Reasoning on Events
In this paper we investigate the contextualized representation of events. In particular, we re-interpret the formalization of events and situations adopted in the NewsReader Event and Situation Ontology (ESO) according to the notions of context and module proposed in the Contextualized Knowledge Repositories (CKR) framework. This contextualized formalization sets the basis for exploiting logica...
متن کاملInferring (k, l)-context-sensitive probabilistic context-free grammars using hierarchical Pitman-Yor processes
Motivated by the idea of applying nonparametric Bayesian models to dual approaches for distributional learning, we define (k, l)-context-sensitive probabilistic context-free grammars (PCFGs) using hierarchical Pitman-Yor processes (PYPs). The data sparseness problem that occurs when inferring context-sensitive probabilities for rules is handled by the smoothing effect of hierarchical PYPs. Many...
متن کاملA Bayesian Method for Robust Estimation of Distributional Similarities
Existing word similarity measures are not robust to data sparseness since they rely only on the point estimation of words’ context profiles obtained from a limited amount of data. This paper proposes a Bayesian method for robust distributional word similarities. The method uses a distribution of context profiles obtained by Bayesian estimation and takes the expectation of a base similarity meas...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2017