Hate speech detection: Challenges and solutions.

As online content continues to grow, so does the spread of hate speech. We identify and examine challenges faced by online automatic approaches for hate speech detection in text. Among these difficulties are subtleties in language, differing definitions on what constitutes hate speech, and limitations of data availability for training and testing of these systems. Furthermore, many recent approaches suffer from an interpretability problem-that is, it can be difficult to understand why the systems make the decisions that they do. We propose a multi-view SVM approach that achieves near state-of-the-art performance, while being simpler and producing more easily interpretable decisions than neural methods. We also discuss both technical and practical challenges that remain for this task.

Passage relevance models for genomics search.

We present a passage relevance model for integrating syntactic and semantic evidence of biomedical concepts and topics using a probabilistic graphical model. Component models of topics, concepts, terms, and document are represented as potential functions within a Markov Random Field. The probability of a passage being relevant to a biologist's information need is represented as the joint distribution across all potential functions. Relevance model feedback of top ranked passages is used to improve distributional estimates of query concepts and topics in context, and a dimensional indexing strategy is used for efficient aggregation of concept and term statistics. By integrating multiple sources of evidence including dependencies between topics, concepts, and terms, we seek to improve genomics literature passage retrieval precision. Using this model, we are able to demonstrate statistically significant improvements in retrieval precision using a large genomics literature corpus.

A dimensional retrieval model for integrating semantics and statistical evidence in context for genomics literature search.

We present a dimensional information retrieval model for combining concept-based semantics and term statistics within multiple levels of document context to identify concise, variable length passages of text that answer a user query. Our results demonstrate improved search results in the presence of varying levels of semantic evidence, and higher performance using retrieval functions that combine document, as well as sentence and passage level information. Experimental results are promising. When ranking documents based on the most relevant extracted passages, the results exceed the state-of-the-art by 15.28% as assessed by the TREC 2005 Genomics track collection of 4.5 million MEDLINE citations.

Efficacy and safety of the Healthtronics LithoTron lithotripter.

PURPOSE: To evaluate our experience with the LithoTron lithotripter (Healthtronics, Atlanta, GA), a dry portable system that utilizes a spark-gap electrode as an energy source. PATIENTS AND METHODS: We prospectively evaluated the first 312 treatments performed on 199 men and 99 women with an average age of 43.5 years (range 4 months-80 years), over a 25-month period between May 1999 and June 2001. Of the 468 stones treated, 136 were located in the ureter, 52 in the renal pelvis or ureteropelvic junction, and 230 in the kidney; the sites of 50 were not specified in our database. The average stone size was 8.0 mm (range 1-40 mm). Follow-up included a plain (KUB) film, CT scan, or intravenous urogram (IVU) and was available for 256 patients. "Stone free" was defined as no fragments visible on postoperative images. The mean radiographic follow-up was 74 days (range 0-866 days). Data collection was initially done manually by data sheets, but a Web-based medical database application was developed in order to enter, store, retrieve, and analyze the data more efficiently. RESULTS: The average number of shocks delivered per renal unit was 2689 at 25.8 kV. Seventy-five percent of the procedures were performed with intravenous sedation. Two thirds (169/256) of the patients were rendered stone free with one treatment. According to size, 71% (209/294) of stones <1 cm, 57% (39/68) of stones between 1.0 and 1.5 cm, and 22% (8/36) of stones >1.5 cm were eliminated. There were 23 patients who required further treatment; from the available data, 18 of them are currently stone free. Perioperative complications occurred in 6 patients (2%). No patient had worsening renal function or new-onset hypertension. The effectiveness quotient was 59.3%. CONCLUSION: The LithoTron lithotripter is satisfactory for stones <1 cm.