Do you want to publish a course? Click here

A New Approach to Overgenerating and Scoring Abstractive Summaries

نهج جديد للمغادرة وتسجيل ملخصات الجماعة

287   0   0   0.0 ( 0 )
 Publication date 2021
and research's language is English
 Created by Shamra Editor




Ask ChatGPT about the research

We propose a new approach to generate multiple variants of the target summary with diverse content and varying lengths, then score and select admissible ones according to users' needs. Abstractive summarizers trained on single reference summaries may struggle to produce outputs that achieve multiple desirable properties, i.e., capturing the most important information, being faithful to the original, grammatical and fluent. In this paper, we propose a two-staged strategy to generate a diverse set of candidate summaries from the source text in stage one, then score and select admissible ones in stage two. Importantly, our generator gives a precise control over the length of the summary, which is especially well-suited when space is limited. Our selectors are designed to predict the optimal summary length and put special emphasis on faithfulness to the original text. Both stages can be effectively trained, optimized and evaluated. Our experiments on benchmark summarization datasets suggest that this paradigm can achieve state-of-the-art performance.



References used
https://aclanthology.org/
rate research

Read More

We present a generic method to compute thefactual accuracy of a generated data summarywith minimal user effort. We look at the prob-lem as a fact-checking task to verify the nu-merical claims in the text. The verification al-gorithm assumes that the data used to generatethe text is available. In this paper, we describehow the proposed solution has been used toidentify incorrect claims about basketball tex-tual summaries in the context of the AccuracyShared Task at INLG 2021.
The present paper summarizes an attempt we made to meet a shared task challenge on grounding machine-generated summaries of NBA matchups (https://github.com/ehudreiter/accuracySharedTask.git). In the first half, we discuss methods and in the second, we report results, together with a discussion on what feature may have had an effect on the performance.
The plea to prevent or stop human rights violations and save the civilian population from an imminent danger, for a state or group of states to intervene in the internal affairs of another state without its consent, is not new. The first roots of thi s idea go back several centuries, and we have witnessed in all times attempts to legitimize interventions in the internal affairs of countries in the name of protecting the rights of minorities, protecting subjects, protecting the population and human rights, protecting civilians, and for this purpose, the concepts of "just war" were invented, respectively, “Intervention in the name of humanity”, “the right to intervene, the duty to intervene,” the last of which is the principle of the “responsibility to protect,” which aims to protect civilians from the most international crimes that violate human rights without prejudice to the sovereignty of states. The naming of these concepts are the variable. Almost the same to the point of congruence; Because it revolved around the same goal, which is to moralize and, if possible, legal, military interventions in other countries.
We propose using a multilabel probing task to assess the morphosyntactic representations of multilingual word embeddings. This tweak on canonical probing makes it easy to explore morphosyntactic representations, both holistically and at the level of individual features (e.g., gender, number, case), and leads more naturally to the study of how language models handle co-occurring features (e.g., agreement phenomena). We demonstrate this task with multilingual BERT (Devlin et al., 2018), training probes for seven typologically diverse languages: Afrikaans, Croatian, Finnish, Hebrew, Korean, Spanish, and Turkish. Through this simple but robust paradigm, we verify that multilingual BERT renders many morphosyntactic features simultaneously extractable. We further evaluate the probes on six held-out languages: Arabic, Chinese, Marathi, Slovenian, Tagalog, and Yoruba. This zero-shot style of probing has the added benefit of revealing which cross-linguistic properties a language model recognizes as being shared by multiple languages.
In the sixth edition of the WMT Biomedical Task, we addressed a total of eight language pairs, namely English/German, English/French, English/Spanish, English/Portuguese, English/Chinese, English/Russian, English/Italian, and English/Basque. Further, our tests were composed of three types of textual test sets. New to this year, we released a test set of summaries of animal experiments, in addition to the test sets of scientific abstracts and terminologies. We received a total of 107 submissions from 15 teams from 6 countries.

suggested questions

comments
Fetching comments Fetching comments
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا