Comparative or evaluative questions are the non-factoid class of questions that contain comparati... more Comparative or evaluative questions are the non-factoid class of questions that contain comparative or evaluative keywords, which may or may not be directly quantifiable. This entails the need for extraction of comparative and evaluative features, identification of semantic meaning of those features and converting them to quantifiable criteria before data can be obtained from the source text. This paper presents the study of the comparative or evaluative questions along with a rule based approach to syntactically extract and semantically analyze comparative or evaluative features, and give a basic idea to generate the answer.
The article presents the experiments carried out as part of the participation in the main task of... more The article presents the experiments carried out as part of the participation in the main task of QA4MRE@CLEF 2011. We have submitted total five unique runs in the main task: two runs from systems based on Answer Validation (AV) machine reading techniques, one run from systems based on Question Answering (QA) techniques while the last two runs are hybrid systems where the decision is taken based on the outputs from the AV and QA based systems. In the AV system, we first combine the question and each answer option to form the Hypothesis (H). Stop words are removed from each H and query words are identified to retrieve the most relevant sentences from the associated document using Lucene. Relevant sentences are retrieved from the associated document based on the TF-IDF of the matching query words along with n-gram overlap of the sentence with the H. Each retrieved sentence defines the Text T. Each T-H pair is assigned a ranking score in the AV system that works on textual entailment p...
Role of Fine Needle Aspiration Biopsy in Cytological Diagnosis of Vertebral Tuberculosis
Summary: Fine needle aspiration biopsy monitored with computerized tomography was used for the di... more Summary: Fine needle aspiration biopsy monitored with computerized tomography was used for the diagnosis of vertebral tuberculosis in 42 patients. The diagnosis was confirmed by culture or Ziehl-Neelsen staining of the smear in 38 of the 42 patients. Cytological examination of aspirated material revealed collections of epithelioid cells, scattered multinucleated Langhans giant cells and necrosis. In the remaining four patients, sputum for acid-fast bacilli was positive and the patients were being treated for pulmonary tuberculosis. All the patients responded to conservative therapy, There were no complications related to the needle biopsy and an operative biopsy was, thus, avoided. Fine needle aspiration biopsy is a safe and quick diagnostic procedure with high accuracy in the hands of trained cytopathologists. It should be practised in all diagnostic centres of our country, even for suspected vertebral tuberculosis
Comparative or Evaluative questions are categorized as non-factoid questions where user asked to ... more Comparative or Evaluative questions are categorized as non-factoid questions where user asked to compare between entities (for comparative) based on some criteria and constraints or asked to evaluate certain criteria of the entities (for Evaluative). The answers of this type questions can't be directly lifted from the underline document collection rather answers are hidden. To answer the Comparative or Evaluative questions system must have potentiality to understand the comparative evaluative expression and user needs. This paper contains trivial approach to give answer of Comparative or Evaluation questions.
Comparative & Evaluative QA system in tourism domain
ABSTRACT Comparative or Evaluative questions are categorized as non-factoid questions where user ... more ABSTRACT Comparative or Evaluative questions are categorized as non-factoid questions where user asked to compare between entities (for comparative) based on some criteria and constraints or asked to evaluate certain criteria of the entities (for Evaluative). The answers of this type questions can't be directly lifted from the underline document collection rather answers are hidden. To answer the Comparative or Evaluative questions system must have potentiality to understand the comparative evaluative expression and user needs. This paper contains trivial approach to give answer of Comparative or Evaluation questions.
Objective. To demonstrate proof of concept for a smart phone-empowered community health worker (C... more Objective. To demonstrate proof of concept for a smart phone-empowered community health worker (CHW) model of care for breast health promotion, clinical breast examination (CBE), and patient navigation in rural Bangladesh. Methods. This study was a randomized controlled trial; July 1 to October 31, 2012, 30 CHWs conducted door-to-door interviews of women aged 25 and older in Khulna Division. Only women who disclosed a breast symptom were offered CBE. Arm A: smart phone with applications to guide interview, report data, show motivational video, and offer appointment for women with an abnormal CBE. Arm B: smart phone/applications identical to Arm A plus CHW had training in "patient navigation" to address potential barriers to seeking care. Arm C: control arm (no smart phone; same interview recorded on paper). Outcomes are presented as the "adherence" (to advice regarding a clinic appointment) for women with an abnormal CBE. This study was approved by Women's College Hospital Research Ethics Board (Toronto, Ontario, Canada) and district government officials (Khulna, Bangladesh). Funded by Grand Challenges Canada. Results. In 4 months, 22,337 women were interviewed; <1% declined participation, and 556 women had an abnormal CBE. Control group CHWs completed fewer interviews, had inferior data quality, and identified significantly fewer women with abnormal breast exams compared with CHWs in arms A and B. Arm B had the highest adherence.
The article presents the experiments carried out as part of the participation in the main task of... more The article presents the experiments carried out as part of the participation in the main task of QA4MRE@CLEF 2011. We have submitted total five unique runs in the main task: two runs from systems based on Answer Validation (AV) machine reading techniques, one run from systems based on Question Answering (QA) techniques while the last two runs are hybrid systems where the decision is taken based on the outputs from the AV and QA based systems. In the AV system, we first combine the question and each answer option to form the Hypothesis (H). Stop words are removed from each H and query words are identified to retrieve the most relevant sentences from the associated document using Lucene. Relevant sentences are retrieved from the associated document based on the TF-IDF of the matching query words along with n-gram overlap of the sentence with the H. Each retrieved sentence defines the Text T. Each T-H pair is assigned a ranking score in the AV system that works on textual entailment principle. The answer option for which the T-H pair gets the maximum score is selected as the possible answer. The two unique runs differ in the way in which the relevant sentences are retrieved from the associated document. The second system is based on Question Answering (QA) technique. Each question along with each answer option generates the possible answer patterns. Each sentence in the associated document is assigned an inference score with respect to each answer pattern. The sentence that receives the highest inference score corresponding to the answer patterns is identified as the relevant sentence in the document and the corresponding answer option is selected as the answer to the given question.
Uploads
Papers by Bidhan Pal