Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models

Horst, Hendrik ter; Hartung, Matthias; Cimiano, Philipp

doi:10.1007/978-3-319-59888-8_15

Cited by 8 publications

(8 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dictionary-based approaches can detect and normalize concept mentions in a single step (Tseytlin et al, 2016;Pafilis et al, 2013), even though postfiltering (Basaldella et al, 2017;Cuzzola et al, 2017) or other strategies are usually required to achieve good performance. Examplebased approaches include probabilistic (Leaman and Lu, 2016) and graphical (Lou et al, 2017;ter Horst et al, 2017) systems for jointly learning NER+NEN in shared or interdependent models. Zhao et al (2019) propose a multi-task-learning set-up for neural NER and NEN with bidirectional feedback, as mentioned earlier.…”

Section: Related Workmentioning

confidence: 99%

UZH@CRAFT-ST: a Sequence-labeling Approach to Concept Recognition

Furrer¹,

Cornelius²,

Rinaldi³

2019

Proceedings of the 5th Workshop on BioNLP Open Shared Tasks

View full text Add to dashboard Cite

As our submission to the CRAFT shared task 2019, we present two neural approaches to concept recognition. We propose two different systems for joint named entity recognition (NER) and normalization (NEN), both of which model the task as a sequence labeling problem. Our first system is a BiLSTM network with two separate outputs for NER and NEN trained from scratch, whereas the second system is an instance of BioBERT fine-tuned on the concept-recognition task. We exploit two strategies for extending concept coverage, ontology pretraining and backoff with a dictionary lookup. Our results show that the backoff strategy effectively tackles the problem of unseen concepts, addressing a major limitation of the chosen design. In the cross-system comparison, BioBERT proves to be a strong basis for creating a concept-recognition system, although some entity types are predicted more accurately by the BiLSTM-based system.

show abstract

Section: Related Workmentioning

confidence: 99%

UZH@CRAFT-ST: a Sequence-labeling Approach to Concept Recognition

Furrer¹,

Cornelius²,

Rinaldi³

2019

Proceedings of the 5th Workshop on BioNLP Open Shared Tasks

View full text Add to dashboard Cite

show abstract

“…The first group joints the ED and EL tasks into one objective function and infers the parameters to automatically leverage their mutual dependency. Luo et al [3] and ter Horst et al [6] modeled these two tasks as a probabilistic factor graph and estimated their parameters based on the gradient descent method. Sil and Yates [18] used a maximum-entropy model to select correct mention-entity pairs by adding the dependent features of NER and EL.…”

Section: Joint Methodsmentioning

confidence: 99%

“…Recently, many researchers have proposed joint methods that couple ED and EL. In one method, their features are designed separately and then integrated into a joint objective function [3], [5], [6]. In another, an interactive architecture is constructed that iteratively exchanges the extracted information between these two tasks [7]- [9].…”

Section: Introductionmentioning

confidence: 99%

Progressive Joint Framework for Chinese Question Entity Discovery and Linking With Question Representations

Lin

Zhang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Chinese question entity discovery and linking (QEDL) may encounter short texts and smallscale annotated datasets, which may invalidate certain machine learning algorithms. In this paper, we propose a progressive joint framework for Chinese QEDL, which leverages the mutual dependency information of these two tasks to enhance the performance with each other. The framework uses the candidate entity generation (CEG) of entity linking to iteratively augment the overall process of entity discovery that consists of mention generation, filtering and merging modules. In mention generation module, to reduce the handcrafted effort of the rule-based entity discovery, we develop a question representation method to generate domain-independent entity discovery rules, and use CEG to check the extracted mentions in priority order. This module can embed extracted mentions into other entity discovery methods as one feature or as extra mentions to alleviate insufficiencies of annotated datasets. The mentions filtering module leverages the joint features of extracted mentions and CEG's entities to build a voting model and filter out low-confidence mentions. Moreover, the mentions merging module merges different patterns' mention-entity pairs and check their corresponding candidate entities with CEG. During entity linking, we incorporate the joint features of questions, extracted mentions and CEG's entities into a ranking model for entity disambiguation. Finally, we conduct experiments on two real datasets and compare our approach with other state-of-the-art methods. The results illustrate that the proposed framework can reduce error accumulation and flexibly combine different entity discovery methods, which significantly improves the performance on small-scale datasets.INDEX TERMS Entity discovery and linking, information extraction, joint method, natural language processing, question representation model.

show abstract

“…In each iteration, a segmentation-explorer and a concept-explorer are consecutively applied in order to generate a set of proposal states. The segmentation explorer (recognition) is able to add a new non-overlapping segmentation 7 , remove an existing segmentation, or apply a synonym replacement to a token within an existing segmentation. The concept-explorer (linking) can assign, change or remove a concept to/from any segmentation.…”

Section: Inferencementioning

confidence: 99%

“…This tutorial ends with Section 5 in which we conclude our proposed approach. Parts of the materials presented here are taken from our previous publications [4,7,8].…”

Section: Introductionmentioning

confidence: 99%

Cold-Start Knowledge Base Population Using Ontology-Based Information Extraction with Conditional Random Fields

Horst

Hartung

Cimiano

2018

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

In this tutorial we discuss how Conditional Random Fields can be applied to knowledge base population tasks. We are in particular interested in the cold-start setting which assumes as given an ontology that models classes and properties relevant for the domain of interest, and an empty knowledge base that needs to be populated from unstructured text. More specifically, cold-start knowledge base population consists in predicting semantic structures from an input document that instantiate classes and properties as defined in the ontology. Considering knowledge base population as structure prediction, we frame the task as a statistical inference problem which aims at predicting the most likely assignment to a set of ontologically grounded output variables given an input document. In order to model the conditional distribution of these output variables given the input variables derived from the text, we follow the approach adopted in Conditional Random Fields. We decompose the cold-start knowledge base population task into the specific problems of entity recognition, entity linking and slot-filling, and show how they can be modeled using Conditional Random Fields.

show abstract

Joint Entity Recognition and Linking in Technical Domains Using Undirected Probabilistic Graphical Models

Cited by 8 publications

References 17 publications

UZH@CRAFT-ST: a Sequence-labeling Approach to Concept Recognition

UZH@CRAFT-ST: a Sequence-labeling Approach to Concept Recognition

Progressive Joint Framework for Chinese Question Entity Discovery and Linking With Question Representations

Cold-Start Knowledge Base Population Using Ontology-Based Information Extraction with Conditional Random Fields

Contact Info

Product

Resources

About