Bryan Rink | University of Texas at Dallas (original) (raw)

Papers by Bryan Rink

We present a novel approach to the problem of multilingual conceptual metaphor recognition. Our a... more We present a novel approach to the problem of multilingual conceptual metaphor recognition. Our approach extends recent work in conceptual metaphor discovery by combining a complex methodology for facet-based concept induction with a distributional vector space model of lin-guistic and conceptual metaphor. In the evaluation of our system in English, Spanish, Russian, and Farsi, we experiment with several state-of-the-art vector space models and demonstrate a clear benefit to the fine-grained concept representation that forms the basis of our methodology for conceptual metaphor recognition. 1

Radiology reports often contain findings about the condition of a patient which should be acted u... more Radiology reports often contain findings about the condition of a patient which should be acted upon quickly. These actionable findings in a radiology report can be automatically detected to ensure that the referring physician is notified about such findings and to provide feedback to the radiologist that further action has been taken. In this paper we investigate a method for detecting actionable findings of appendicitis in radiology reports. The method identifies both individual assertions regarding the presence of appendicitis and other findings related to appendicitis using syntactic dependency patterns. All relevant individual statements from a report are collectively considered to determine whether the report is consistent with appendicitis. Evaluation on a corpus of 400 radiology reports annotated by two expert radiologists showed that our approach achieves a precision of 91%, a recall of 83%, and an F1-measure of 87%.

This paper describes the updated system created by the University of Texas at Dallas for content-... more This paper describes the updated system created by the University of Texas at Dallas for content-based medical record retrieval submitted to the TREC 2012 Medical Records Track. Our system updates our work from the previous year by building a structured query for each cohort that captures the patient’s age, gen-der, hospital status, and medical assertion information. Further, all keywords that encode any medical phe-nomena from the query are recursively decomposed before being expanded using knowledge from UMLS, SNOMED, Wikipedia, and PubMed co-occurrences. An initial ranking of hospital visits is then obtained using BM25 relevance on an interpolation of these

Int. J. Comput. Linguistics Appl., 2015

In this work, we describe a supervised cross-lingual methodology for detecting novel and conventi... more In this work, we describe a supervised cross-lingual methodology for detecting novel and conventionalized metaphors that derives generalized semantic patterns from a collection of metaphor annotations. For this purpose, we model each metaphor annotation as an abstract tuple – (source, target, relation, metaphoricity) – that packages a metaphoricity judgement with a relational grounding of the source and target lexical units in text. From these annotations, we derive a set of semantic patterns using a three-step process. First, we employ several generalized representations of the target using a variety of WordNet information and representative domain terms. Then, we generalize relations using a rule-based, pseudo-semantic role labeling. Finally, we generalize the source by partitioning a semantic hierarchy (defined by the target and the relation) into metaphoric and non-metaphoric regions so as to optimally account for the evidence in the annotated data. Experiments show that by vary...

Relational similarity is essential to analogical reasoning. Automatically determining the degree ... more Relational similarity is essential to analogical reasoning. Automatically determining the degree to which a pair of words belongs to a semantic relation (relational similarity) is greatly improved by considering the selectional preferences of the relation. To determine selectional preferences, we induced semantic classes through a Latent Dirichlet Allocation (LDA) method that operates on dependency parse contexts of single words. When assigning relational similarities to pairs of words, if the agreement of selectional preferences is considered alone, a correlation of 0.334 is obtained against the manual ranking outperforming the previously best reported score of 0.229.

Journal of the American Medical Informatics Association, 2013

Objective To provide a natural language processing method for the automatic recognition of events... more Objective To provide a natural language processing method for the automatic recognition of events, temporal expressions, and temporal relations in clinical records. Materials and Methods A combination of supervised, unsupervised, and rule-based methods were used. Supervised methods include conditional random fields and support vector machines. A flexible automated feature selection technique was used to select the best subset of features for each supervised task. Unsupervised methods include Brown clustering on several corpora, which result in our method being considered semisupervised. Results On the 2012 Informatics for Integrating Biology and the Bedside (i2b2) shared task data, we achieved an overall event F1-measure of 0.8045, an overall temporal expression F1-measure of 0.6154, an overall temporal link detection F1-measure of 0.5594, and an end-to-end temporal link detection F1-measure of 0.5258. The most competitive system was our event recognition method, which ranked third out of the 14 participants in the event task. Discussion Analysis reveals the event recognition method has difficulty determining which modifiers to include/exclude in the event span. The temporal expression recognition method requires significantly more normalization rules, although many of these rules apply only to a small number of cases. Finally, the temporal relation recognition method requires more advanced medical knowledge and could be improved by separating the single discourse relation classifier into multiple, more targeted component classifiers. Conclusions Recognizing events and temporal expressions can be achieved accurately by combining supervised and unsupervised methods, even when only minimal medical knowledge is available. Temporal normalization and temporal relation recognition, however, are far more dependent on the modeling of medical knowledge.

… of DUC'06, 2006

In this paper, we describe how Lan-guage Computer Corporation's GISTEX-TER question-directed... more In this paper, we describe how Lan-guage Computer Corporation's GISTEX-TER question-directed summarization sys-tem combines multiple strategies for ques-tion decomposition and summary genera-tion in order to produce summary-length answers to complex questions. In addi- ...

This paper presents a generative model for the automatic discovery of relations between entities ... more This paper presents a generative model for the automatic discovery of relations between entities in electronic medical records. The model discovers relation instances and their types by determining which context tokens express the relation. Additionally, the valid semantic classes for each type of relation are determined. We show that the model produces clusters of relation trigger words which better correspond with manually annotated relations than several existing clustering techniques. The discovered relations reveal some of the implicit semantic structure present in patient records.

Lecture Notes in Computer Science, 2014

The Florida AI Research Society Conference, 2010

... Relations Bryan Rink, Cosmin Adrian Bejan, and Sanda Harabagiu Human Language Technology Rese... more ... Relations Bryan Rink, Cosmin Adrian Bejan, and Sanda Harabagiu Human Language Technology Research Institute The University of Texas at Dallas Richardson, Texas 75080, USA {bryan,ady,sanda}@hlt.utdallas.edu Abstract ...

Identification, Investigation and Resolution, 2011

Journal of The American Medical Informatics Association, 2011

Objective A supervised machine learning approach to discover relations between medical problems, ... more Objective A supervised machine learning approach to discover relations between medical problems, treatments, and tests mentioned in electronic medical records. Materials and Methods A single Support Vector Machine (SVM) classifier was used to identify relations between concepts and to assign their semantic type. Several resources such as Wikipedia, WordNet, General Inquirer, and a relation similarity metric inform the classifier. Results The techniques reported in this paper were evaluated in the 2010 i2b2 Challenge and obtained the highest F1 score for the relation extraction task. When gold standard data for concepts and assertions were available the F1 was 73.7, precision was 72.0, and recall was 75.3. F1 is defined as 2*Precision*Recall/(Precision+Recall). Alternatively, when concepts and assertions were discovered automatically we obtain an F1 score 48.4, precision was 57.6, and recall was 41.7. Discussion Although a rich set of features was developed for the classifiers presented in this paper, little knowledge mining was performed from medical ontologies such as those found in UMLS . Future studies should incorporate features extracted from such knowledge sources, which we expect to further improve the results.

We introduce a new system for recognizing textual entailment (known as GROUNDHOG) which utilizes ... more We introduce a new system for recognizing textual entailment (known as GROUNDHOG) which utilizes a classification-based approach to combine lexico-semantic information derived from text processing applications with a large collection of paraphrases acquired automatically from the WWW. Trained on 200,000 examples of textual entailment extracted from newswire corpora, our system managed to classify more than 75% of the pairs in the 2006 PASCAL RTE Test Set correctly.