Analysing Semantic Resources for Coreference Resolution

Author(s):  
Thiago Lima ◽  
Sandra Collovini ◽  
Ana Leal ◽  
Evandro Fonseca ◽  
Xiaoxuan Han ◽  
...  
2014 ◽  
Author(s):  
Mariana S. C. Almeida ◽  
Miguel B. Almeida ◽  
André F. T. Martins

Author(s):  
Abhinav Kumar ◽  
Jillian Aurisano ◽  
Barbara Di Eugenio ◽  
Andrew Johnson ◽  
Abeer Alsaiari ◽  
...  

Author(s):  
Yufei Li ◽  
Xiaoyong Ma ◽  
Xiangyu Zhou ◽  
Pengzhen Cheng ◽  
Kai He ◽  
...  

Abstract Motivation Bio-entity Coreference Resolution focuses on identifying the coreferential links in biomedical texts, which is crucial to complete bio-events’ attributes and interconnect events into bio-networks. Previously, as one of the most powerful tools, deep neural network-based general domain systems are applied to the biomedical domain with domain-specific information integration. However, such methods may raise much noise due to its insufficiency of combining context and complex domain-specific information. Results In this paper, we explore how to leverage the external knowledge base in a fine-grained way to better resolve coreference by introducing a knowledge-enhanced Long Short Term Memory network (LSTM), which is more flexible to encode the knowledge information inside the LSTM. Moreover, we further propose a knowledge attention module to extract informative knowledge effectively based on contexts. The experimental results on the BioNLP and CRAFT datasets achieve state-of-the-art performance, with a gain of 7.5 F1 on BioNLP and 10.6 F1 on CRAFT. Additional experiments also demonstrate superior performance on the cross-sentence coreferences. Supplementary information Supplementary data are available at Bioinformatics online.


2003 ◽  
Vol 9 (3) ◽  
pp. 281-306 ◽  
Author(s):  
ANDREI POPESCU-BELIS

In this paper, we describe a system for coreference resolution and emphasize the role of evaluation for its design. The goal of the system is to group referring expressions (identified beforehand in narrative texts) into sets of coreferring expressions that correspond to discourse entities. Several knowledge sources are distinguished, such as referential compatibility between a referring expression and a discourse entity, activation factors for discourse entities, size of working memory, or meta-rules for the creation of discourse entities. For each of them, the theoretical analysis of its relevance is compared to scores obtained through evaluation. After looping through all knowledge sources, an optimal behavior is chosen, then evaluated on test data. The paper also discusses evaluation measures as well as data annotation, and compares the present approach to others in the field.


2020 ◽  
Vol 16 (3) ◽  
pp. 419-438
Author(s):  
Ting Wu

AbstractThe development of new media enlarges the repertoire of semantic resources in creating a discourse. Apart from language, visual and sound symbols can all become semantic sources, and a synergy of different modality and symbols can be used to complete argumentative reasoning and evaluation. In the framework of multimodal argumentation and appraisal theory, this study conducted quantitative and multimodal discourse analysis on a new media discourse Building a community of shared future for humankind and found that visual symbols can independently fulfill both reasoning and evaluation in the argumentative discourse. An interplay of multiple modalities constructs a multi-layered semantic source, with verbal subtitles as a frame and a sound system designed to reinforce the theme and mood. In addition, visual modality is implicit in constructing the stance and evaluation of the discourse, with the verbal mode playing the role of “anchoring,” i.e. providing explicit explanation. A synergy of visual, acoustic, and verbal modalities could effectively transmit conceptual, interpersonal, and discursive meanings, but the persuasive result with the audience from different cultural backgrounds might be mixed.


Sign in / Sign up

Export Citation Format

Share Document