University of Houston @ CL-SciSumm 2017: Positional language Models, Structural Correspondence Learning and Textual Entailment
نویسندگان
چکیده
This paper introduces the methods employed by University of Houston team participating in the CL-SciSumm 2017 Shared Task at BIRNDL 2017 to identify reference spans in a reference document given sentences from citing papers. The following approaches were investigated: structural correspondence learning, positional language models, and textual entailment. In addition, we refined our methods from BIRNDL 2016. Furthermore, we analyzed the results of each method to find the best performing system.
منابع مشابه
University of Mannheim @ CLSciSumm-17: Citation-Based Summarization of Scientific Articles Using Semantic Textual Similarity
The number of publications is rapidly growing and it is essential to enable fast access and analysis of relevant articles. In this paper, we describe a set of methods based on measuring semantic textual similarity, which we use to semantically analyze and summarize publications through other publications that cite them. We report the performance of our approach in the context of the third CL-Sc...
متن کاملWING-NUS at CL-SciSumm 2017: Learning from Syntactic and Semantic Similarity for Citation Contextualization
We present here system report for our model submitted for shared task on Computational Linguistic Scientific-document Summarization (CL-SciSumm) 2017. We hypothesize that search and retrieval based techniques are sub-optimal for learning complex relation likes provenance. State-of-the-art information retrieval techniques using term frequency inverted document frequency (TF-IDF) to capture surfa...
متن کاملUoW: NLP techniques developed at the University of Wolverhampton for Semantic Similarity and Textual Entailment
This paper presents the system submitted by University of Wolverhampton for SemEval-2014 task 1. We proposed a machine learning approach which is based on features extracted using Typed Dependencies, Paraphrasing, Machine Translation evaluation metrics, Quality Estimation metrics and Corpus Pattern Analysis. Our system performed satisfactorily and obtained 0.711 Pearson correlation for the sema...
متن کاملLocal Graph Matching with Active Learning for Recognizing Inference in Text at NTCIR-10
This paper describes the textual entailment system developped at Dublin City University for participation in the textual entailment task in NTCIR-10. Our system is a local graph matching-based system with active learning: we explore reducing the unknown words and unknown namedentities, incorporating meaning in parentheses / rhetorical expressions / semantic roles, and employing text understandi...
متن کاملTextFlow: A Text Similarity Measure based on Continuous Sequences
Text similarity measures are used in multiple tasks such as plagiarism detection, information ranking and recognition of paraphrases and textual entailment. While recent advances in deep learning highlighted further the relevance of sequential models in natural language generation, existing similarity measures do not fully exploit the sequential nature of language. Examples of such similarity m...
متن کامل