Identifying Various Kinds of Event Mentions in K-Parser Output
نویسندگان
چکیده
In this paper we show how our semantic parser (Knowledge Parser or K-Parser) identifies various kinds of event mentions in the input text. The types include recursive (complex) and non recursive event mentions. KParser outputs each event mention in form of an acyclic graph with root nodes as the verbs that drive those events. The children nodes of the verbs represent the entities participating in the events, and their conceptual classes. The on-line demo of the system is available at http://kparser.org
منابع مشابه
تولید درخت بانک سازهای زبان فارسی به روش تبدیل خودکار
Treebanks is one of important and useful resource in Natural Language Processing tasks. Dependency and phrase structures are two famous kinds of treebanks. There have already made many efforts to convert dependency structure to phrase structure. In this paper we study an approach to convert dependency structure to phrase structure because of lack of a big phrase structure Treebank in Persian. A...
متن کاملEmploying Event Inference to Improve Semi-Supervised Chinese Event Extraction
Although semi-supervised model can extract the event mentions matching frequent event patterns, it suffers much from those event mentions, which match infrequent patterns or have no matching pattern. To solve this issue, this paper introduces various kinds of linguistic knowledge-driven event inference mechanisms to semi-supervised Chinese event extraction. These event inference mechanisms can ...
متن کاملGlobal Inference to Chinese Temporal Relation Extraction
Previous studies on temporal relation extraction focus on mining sentence-level information or enforcing coherence on different temporal relation types among various event mentions in the same sentence or neighboring sentences, largely ignoring those discourse-level temporal relations in nonadjacent sentences. In this paper, we propose a discourse-level global inference model to mine those temp...
متن کاملUsing compositional semantics and discourse consistency to improve Chinese trigger identification
Due to the special characteristics and challenges in Chinese language, event extraction in Chinese is much more difficult than that in English. In particular, the state-of-the-art Chinese event extraction systems suffer much from the low recall in trigger identification due to the failure in identifying unknown triggers and the inconsistency in identifying trigger mentions. To resolve these two...
متن کاملمدلسازی توام دادههای بقا و طولی و کاربرد آن در بررسی عوامل موثر بر آسیب حاد کلیوی
Background: In many clinical trials and medical studies, the survival and longitudinal data are collected simultaneously. When these two outcomes are measured from each subject and the survival variable depends on a longitudinal biomarker, using joint modelling of survival and longitudinal outcomes is a proper choice for analyzing the available data. Methods: In this retrospective archiv...
متن کامل