A Study of Anaphoric Expressions in Human Produced Scientific Abstracts

نویسنده

  • Constantin Orasan
چکیده

One of the main reasons for having low quality automatic extracts is the presence of dangling anaphors. This paper analyses the referential expressions in a corpus of human written scientific summaries and tries to identify ways for improving the quality of automatic extracts. By recording the distance between the anaphoric expressions and their referents we noticed that humans do not use an aggregation-like process to avoid the dangling anaphors. The small number of anaphoric pronouns noticed in the summaries suggests that inclusion of a pronominal anaphora resolution module in a summarisation system is not necessary, but one which resolves referential noun phrases should be included given the large number of anaphoric noun phrases. These ideas were reiterated by investigating computer produced extracts.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

What kind of problems do protein interactions raise for anaphora resolution? - A preliminary analysis

In this preliminary study, we analyzed the kind of anaphoric expressions that occur in expressions describing protein interactions found in biological text. We also studied the impact of anaphora resolution on protein interaction extraction, when an off-the-shelf anaphoric resolver (i.e., not one specially developed for this domain) is used, and looking at full texts as well as abstracts. Our r...

متن کامل

Lexical Bundles in English Abstracts of Research Articles Written by Iranian Scholars: Examples from Humanities

This paper investigates a special type of recurrent expressions, lexical bundles, defined as a sequence of three or more words that co-occur frequently in a particular register (Biber et al., 1999). Considering the importance of this group of multi-word sequences in academic prose, this study explores the forms and syntactic structures of three- and four-word bundles in English abstracts writte...

متن کامل

EFL Learners' Sensitivity to Linguistic and Discourse Factors in the Process of Anaphoric Resolution

The readers' ability to integrate current information with given information has been considered as an important component of reading comprehension process. One aspect of this integration process involves anaphoric resolution. The purpose of this study is to investigate the process of anaphoric resolution, focusing on inferential rigidity of different types of anaphoric ties. Ninety EFL learner...

متن کامل

ارزیابی نقادانه چکیده مقالات کنگره‌های پرستاری و مامایی ایران طی سال‌های 93-1389

Background & Aim: One of the most important ways of scientific promotion of congresses is to evaluate abstract of articles and getting feedback from them. This study aimed to evaluate abstract of articles presented in the nursing and midwifery congresses during 2010-2015 from different aspects. Methods: This is a descriptive/cross-sectional study which conducted on all abstracts presented in...

متن کامل

The Anaphoric Expressions of Chinese Algebraic Word Problem

Discourse and anaphora analysis can be very important for intelligent human-computer interface. To study the discourse and anaphora issues of Chinese, Chinese algebraic word problem is a good test-bed. This paper classifies anaphoric expressions into four classes: zero anaphora, reflexives, personal pronouns, and pronominal noun phrases. We analyze algebraic word problem through the four classe...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 2002