Variants Of Tree Similarity In A Question Answering Task
نویسنده
چکیده
The results of experiments on the application of a variety of distance measures to a question-answering task are reported. Variants of tree-distance are considered, including whole-vs-sub tree, node weighting, wild cards and lexical emphasis. We derive string-distance as a special case of tree-distance and show that a particular parameterisation of tree-distance outperforms the string-distance measure.
منابع مشابه
ConvKN at SemEval-2016 Task 3: Answer and Question Selection for Question Answering on Arabic and English Fora
We describe our system, ConvKN, participating to the SemEval-2016 Task 3 “Community Question Answering”. The task targeted the reranking of questions and comments in real-life web fora both in English and Arabic. ConvKN combines convolutional tree kernels with convolutional neural networks and additional manually designed features including text similarity and thread specific features. For the ...
متن کاملGender-oriented Commonalities among Canadian and Iranian Englishes: An Analysis of Yes/No Question Variants
This study investigatesvariability in English yes/no questions as well as the commonalities among yes/no question variants produced by members of two different varieties of English: Canadian English native speakers and Iranian EFL learners.Further, it probes the role of gender in theEnglish yes/no question variants produced by Canadian English native speakers and those produced by Iranian EFL l...
متن کاملRéponse à des tests de compréhension
This paper presents an adaptation of an existing question answering system for a machine reading task. The proposed method for selecting correct answers relies on textual entailment recognition between hypotheses and texts. The specificities of this method are the generation of hypotheses by parse tree modification and the evaluation of several distance criteria, adapted to take into account te...
متن کاملMappSent at IJCNLP-2017 Task 5: A Textual Similarity Approach Applied to Multi-choice Question Answering in Examinations
In this paper we present MappSent, a textual similarity approach that we applied to the multi-choice question answering in exams shared task. MappSent has initially been proposed for question-toquestion similarity (Hazem et al., 2017). In this work, we present the results of two adaptations of MappSent for the question answering task on the English dataset.
متن کاملECNU at SemEval-2016 Task 3: Exploring Traditional Method and Deep Learning Method for Question Retrieval and Answer Ranking in Community Question Answering
This paper describes the system we submitted to the task 3 (Community Question Answering) in SemEval 2016, which contains three subtasks, i.e., Question-Comment Similarity (subtask A), Question-Question Similarity (subtask B), and Question-External Comment Similarity (subtask C). For subtask A, we employed three different methods to rank question-comment pair, i.e., supervised model using tradi...
متن کامل