Generated Abstracts for TAC 2011
نویسندگان
چکیده
We have begun work on a framework for abstractive summarization and decided to focus first on a text generation module. In our submitted system, sentences are generated from the syntactic parse of the original sentences. The summaries are written entirely from automatically generated sentences, as well as generated date and location modifiers when appropriate. The evaluation shows above-average performance in the content metric Pyramid, and low scores in linguistic quality.
منابع مشابه
University of Essex at the TAC 2011 MultiLingual Summarisation Pilot
We present the results of our Arabic and English runs at the TAC 2011 Multilingual summarisation (MultiLing) task. We participated with centroid-based clustering for multidocument summarisation. The automatically generated Arabic and English summaries were evaluated by human participants and by two automatic evaluation metrics, ROUGE and AutoSummENG. The results are compared with the other syst...
متن کاملAnalysis of Transcriptome Complexity via RNA-Seq in Normal and Failing Murine Hearts
RNA purification, library preparation and Illumina sequencing Left ventricular tissues were collected from male C57BL/6 mice after 1 week (hypertrophy stage, HY) and 8 weeks post trans-aortic constriction (TAC) procedure (heart failure stage, HF), respectively, and their corresponding Sham controls (Sham-HY, Sham-HF). Doppler velocity measurements of right and left carotid arteries were obtaine...
متن کاملKey Lexical Chunks in Applied Linguistics Article Abstracts
In any discourse domain, certain chunks are particularly frequent and deserve attention by the novice to be initiated and by the expert to maintain a sense of community. To make a relevant contribution to the awareness about applied linguistics texts and discourse, this study attempted to develop lists of lexical chunks frequently used in the abstracts of applied linguistics journals. The abstr...
متن کاملBLLIP at TAC 2011: A General Summarization System for a Guided Summarization Task
The TAC1 update summarization task is a shared task in which peer systems summarize a collection of documents, and then summarize a second set of documents assuming the user has already read the first set of documents. In the 2010 and 2011 versions of this task, the summaries additionally are “guided” to include certain aspects for pre-defined categories. For example, if the category of the doc...
متن کاملUsing Unsupervised System with least linguistic features for TAC-AESOP Task
We consider AESOP Task as Topic based evaluation of information content. Means at first stage, we identify the topics covered in given model/reference summary and calculate their importance. At the next stage, we calculate the information coverage in test / machine generated summary, w.r.t. every identified topic. We use the local importance of words in calculation of importance of topics. From...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2011