يأتي تلخيص الحوار مع تحديات خاصة به على عكس تلخيص الأخبار أو المقالات العلمية. في هذا العمل، نستكشف أربعة تحديات مختلفة لهذه المهمة: التعامل مع أجزاء من الحوار والتمييز بين المتحدثين المتعددين، وفهم النفي، والمنطق حول الوضع، وفهم اللغة غير الرسمية.
باستخدام نموذج لغة متسلسل مدرب مسبقا، نستكشف محل استبدال اسم المتكلم، وإبراز نطاق النفي، والتعلم المتعدد المهام مع المهام ذات الصلة، وإحصاء البيانات داخل المجال.تظهر تجاربنا أن تقنياتنا المقترحة تحسن أداء الملخصات، وتتفوق على نظم أساسية قوية.
Dialogue summarization comes with its own peculiar challenges as opposed to news or scientific articles summarization. In this work, we explore four different challenges of the task: handling and differentiating parts of the dialogue belonging to multiple speakers, negation understanding, reasoning about the situation, and informal language understanding. Using a pretrained sequence-to-sequence language model, we explore speaker name substitution, negation scope highlighting, multi-task learning with relevant tasks, and pretraining on in-domain data. Our experiments show that our proposed techniques indeed improve summarization performance, outperforming strong baselines.
References used
https://aclanthology.org/
Improving Transformer efficiency has become increasingly attractive recently. A wide range of methods has been proposed, e.g., pruning, quantization, new architectures and etc. But these methods are either sophisticated in implementation or dependent
Summarizing conversations via neural approaches has been gaining research traction lately, yet it is still challenging to obtain practical solutions. Examples of such challenges include unstructured information exchange in dialogues, informal interac
This paper introduces MediaSum, a large-scale media interview dataset consisting of 463.6K transcripts with abstractive summaries. To create this dataset, we collect interview transcripts from NPR and CNN and employ the overview and topic description
Dialogue summarization has drawn much attention recently. Especially in the customer service domain, agents could use dialogue summaries to help boost their works by quickly knowing customer's issues and service progress. These applications require s
Dialogue summarization is a long-standing task in the field of NLP, and several data sets with dialogues and associated human-written summaries of different styles exist. However, it is unclear for which type of dialogue which type of summary is most