Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAn Exploratory Study on Long Dialogue Summarization: What Works and What's Next
دراسة استكشافية حول تلخيص الحوار الطويلة: ما الذي يعمل وما هو التالي
630
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يلخص الحوار يساعد القراء على التقاط المعلومات البارزة من محادثات طويلة في الاجتماعات والمقابلات والمسلسلات التلفزيونية. ومع ذلك، فإن حوالات العالم الحقيقي تشكل تحديا كبيرا لنماذج التلخيص الحالية، حيث يتجاوز طول الحوار عادة حدود المدخلات التي تفرضها النماذج المدربة مسبقا القائمة على المحولات، والطبيعة التفاعلية للحوالات هي المعلومات ذات الصلة أكثر تعتمد على السياق وقدر موزعة من المقالات الإخبارية. في هذا العمل، نقوم بإجراء دراسة شاملة حول تلخيص الحوار الطويل من خلال التحقيق في ثلاث استراتيجيات للتعامل مع مشكلة الإدخال المطول وتحديد موقع المعلومات ذات الصلة: (1) نماذج المحولات الموسعة مثل Longformer، (2) استرداد نماذج خط أنابيب العديد من طرق استرجاع الحوار النطق، و (3) نماذج ترميز الحوار الهرمي مثل HMNet. نتائجنا التجريبية على ثلاث مجموعات بيانات حوار طويلة (QMSUM، MediaSum، Searscreen) تبين أن نماذج خط أنابيب الاسترداد - بعد ذلك، تسفر عن أفضل أداء. نوضح أيضا أنه يمكن تحسين جودة الملخص مع نموذج استرجاع أقوى وأحيث محاكاة بيانات الملخصات الخارجية المناسبة.
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series. However, real-world dialogues pose a great challenge to current summarization models, as the dialogue length typically exceeds the input limits imposed by recent transformer-based pre-trained models, and the interactive nature of dialogues makes relevant information more context-dependent and sparsely distributed than news articles. In this work, we perform a comprehensive study on long dialogue summarization by investigating three strategies to deal with the lengthy input problem and locate relevant information: (1) extended transformer models such as Longformer, (2) retrieve-then-summarize pipeline models with several dialogue utterance retrieval methods, and (3) hierarchical dialogue encoding models such as HMNet. Our experimental results on three long dialogue datasets (QMSum, MediaSum, SummScreen) show that the retrieve-then-summarize pipeline models yield the best performance. We also demonstrate that the summary quality can be further improved with a stronger retrieval model and pretraining on proper external summarization datasets.
References used
https://aclanthology.org/
rate research
Read More
Entity Linking (EL) systems have achieved impressive results on standard benchmarks mainly thanks to the contextualized representations provided by recent pretrained language models. However, such systems still require massive amounts of data -- mill
ions of labeled examples -- to perform at their best, with training times that often exceed several days, especially when limited computational resources are available. In this paper, we look at how Named Entity Recognition (NER) can be exploited to narrow the gap between EL systems trained on high and low amounts of labeled data. More specifically, we show how and to what extent an EL system can benefit from NER to enhance its entity representations, improve candidate selection, select more effective negative samples and enforce hard and soft constraints on its output entities. We release our software -- code and model checkpoints -- at https://github.com/Babelscape/ner4el.
In the last few years, several methods have been proposed to build meta-embeddings. The general aim was to obtain new representations integrating complementary knowledge from different source pre-trained embeddings thereby improving their overall qua
lity. However, previous meta-embeddings have been evaluated using a variety of methods and datasets, which makes it difficult to draw meaningful conclusions regarding the merits of each approach. In this paper we propose a unified common framework, including both intrinsic and extrinsic tasks, for a fair and objective meta-embeddings evaluation. Furthermore, we present a new method to generate meta-embeddings, outperforming previous work on a large number of intrinsic evaluation benchmarks. Our evaluation framework also allows us to conclude that previous extrinsic evaluations of meta-embeddings have been overestimated.
The introduction of pre-trained transformer-based contextualized word embeddings has led to considerable improvements in the accuracy of graph-based parsers for frameworks such as Universal Dependencies (UD). However, previous works differ in various
dimensions, including their choice of pre-trained language models and whether they use LSTM layers. With the aims of disentangling the effects of these choices and identifying a simple yet widely applicable architecture, we introduce STEPS, a new modular graph-based dependency parser. Using STEPS, we perform a series of analyses on the UD corpora of a diverse set of languages. We find that the choice of pre-trained embeddings has by far the greatest impact on parser performance and identify XLM-R as a robust choice across the languages in our study. Adding LSTM layers provides no benefits when using transformer-based embeddings. A multi-task training setup outputting additional UD features may contort results. Taking these insights together, we propose a simple but widely applicable parser architecture and configuration, achieving new state-of-the-art results (in terms of LAS) for 10 out of 12 diverse languages.
The ability to generate clarification questions i.e., questions that identify useful missing information in a given context, is important in reducing ambiguity. Humans use previous experience with similar contexts to form a global view and compare it
to the given context to ascertain what is missing and what is useful in the context. Inspired by this, we propose a model for clarification question generation where we first identify what is missing by taking a difference between the global and the local view and then train a model to identify what is useful and generate a question about it. Our model outperforms several baselines as judged by both automatic metrics and humans.
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
tions between speakers, and dynamic role changes of speakers as the dialogue evolves. Many of such challenges result in complex coreference links. Therefore, in this work, we investigate different approaches to explicitly incorporate coreference information in neural abstractive dialogue summarization models to tackle the aforementioned challenges. Experimental results show that the proposed approaches achieve state-of-the-art performance, implying it is useful to utilize coreference information in dialogue summarization. Evaluation results on factual correctness suggest such coreference-aware models are better at tracing the information flow among interlocutors and associating accurate status/actions with the corresponding interlocutors and person mentions.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
