Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userMultifaceted Domain-Specific Document Embeddings
تضيحية المستندات المستند متعددة الأوجاس
67
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تتطلب تضمين الوثائق الحالية شركة تدريبية كبيرة ولكنها تفشل في تعلم تمثيلات عالية الجودة عند مواجهة عدد صغير من المستندات الخاصة بالمجال والشروط النادرة. علاوة على ذلك، يقومون بتحويل كل وثيقة إلى متجه تضمين واحد، مما يجعل من الصعب التقاط مفاهيم مختلفة من تشابه الوثيقة أو شرح سبب اعتبار المستندين مماثلة. في هذا العمل، نقترح تشفير المجال الأوجه لدينا، ونهج رواية لتعلم Admeddings متعددة الأوجه للمستندات الخاصة بالمجال. يعتمد ذلك على بنية شبكة عصبية سيامي ويعزز الرسوم البيانية المعرفة لتعزيز المدينات حتى لو كانت بعض عينات التدريب فقط متوفرة. يحدد النموذج أنواعا مختلفة من معرفة المجال وترميزها في أبعاد منفصلة من التضمين، مما يتيح طرق متعددة لإيجاد ومقارنة المستندات ذات الصلة في مساحة المتجهات. نقيم نهجنا على مجموعة بيانات قياسية وتجد أنه يحقق نفس جودة التضمين كطرازات حديثة بينما تتطلب سوى جزء صغير من بيانات التدريب الخاصة بهم فقط. تتوفر تجريبي تفاعلي ومجموعاتنا المصدر ومجموعات بيانات التقييم عبر الإنترنت: https://hpi.de/naumann/s/multifaceted-emberdings و screencast متاح على Youtube: https://youtu.be/hhcsx2clewg
Current document embeddings require large training corpora but fail to learn high-quality representations when confronted with a small number of domain-specific documents and rare terms. Further, they transform each document into a single embedding vector, making it hard to capture different notions of document similarity or explain why two documents are considered similar. In this work, we propose our Faceted Domain Encoder, a novel approach to learn multifaceted embeddings for domain-specific documents. It is based on a Siamese neural network architecture and leverages knowledge graphs to further enhance the embeddings even if only a few training samples are available. The model identifies different types of domain knowledge and encodes them into separate dimensions of the embedding, thereby enabling multiple ways of finding and comparing related documents in the vector space. We evaluate our approach on two benchmark datasets and find that it achieves the same embedding quality as state-of-the-art models while requiring only a tiny fraction of their training data. An interactive demo, our source code, and the evaluation datasets are available online: https://hpi.de/naumann/s/multifaceted-embeddings and a screencast is available on YouTube: https://youtu.be/HHcsX2clEwg
References used
https://aclanthology.org/
rate research
Read More
Information overload has been one of the challenges regarding information from the Internet. It is not a matter of information access, instead, the focus had shifted towards the quality of the retrieved data. Particularly in the news domain, multiple
outlets report on the same news events but may differ in details. This work considers that different news outlets are more likely to differ in their writing styles and the choice of words, and proposes a method to extract sentences based on their key information by focusing on the shared synonyms in each sentence. Our method also attempts to reduce redundancy through hierarchical clustering and arrange selected sentences on the proposed orderBERT. The results show that the proposed unsupervised framework successfully improves the coverage, coherence, and, meanwhile, reduces the redundancy for a generated summary. Moreover, due to the process of obtaining the dataset, we also propose a data refinement method to alleviate the problems of undesirable texts, which result from the process of automatic scraping.
A crucial difference between single- and multi-document summarization is how salient content manifests itself in the document(s). While such content may appear at the beginning of a single document, essential information is frequently reiterated in a
set of documents related to a particular topic, resulting in an endorsement effect that increases information salience. In this paper, we model the cross-document endorsement effect and its utilization in multiple document summarization. Our method generates a synopsis from each document, which serves as an endorser to identify salient content from other documents. Strongly endorsed text segments are used to enrich a neural encoder-decoder model to consolidate them into an abstractive summary. The method has a great potential to learn from fewer examples to identify salient content, which alleviates the need for costly retraining when the set of documents is dynamically adjusted. Through extensive experiments on benchmark multi-document summarization datasets, we demonstrate the effectiveness of our proposed method over strong published baselines. Finally, we shed light on future research directions and discuss broader challenges of this task using a case study.
Presentations are critical for communication in all areas of our lives, yet the creation of slide decks is often tedious and time-consuming. There has been limited research aiming to automate the document-to-slides generation process and all face a c
ritical challenge: no publicly available dataset for training and benchmarking. In this work, we first contribute a new dataset, SciDuet, consisting of pairs of papers and their corresponding slides decks from recent years' NLP and ML conferences (e.g., ACL). Secondly, we present D2S, a novel system that tackles the document-to-slides task with a two-step approach: 1) Use slide titles to retrieve relevant and engaging text, figures, and tables; 2) Summarize the retrieved context into bullet points with long-form question answering. Our evaluation suggests that long-form QA outperforms state-of-the-art summarization baselines on both automated ROUGE metrics and qualitative human evaluation.
In the paper, we deal with the problem of unsupervised text document clustering for the Polish language. Our goal is to compare the modern approaches based on language modeling (doc2vec and BERT) with the classical ones, i.e., TF-IDF and wordnet-base
d. The experiments are conducted on three datasets containing qualification descriptions. The experiments' results showed that wordnet-based similarity measures could compete and even outperform modern embedding-based approaches.
Document-level neural machine translation (NMT) has proven to be of profound value for its effectiveness on capturing contextual information. Nevertheless, existing approaches 1) simply introduce the representations of context sentences without expli
citly characterizing the inter-sentence reasoning process; and 2) feed ground-truth target contexts as extra inputs at the training time, thus facing the problem of exposure bias. We approach these problems with an inspiration from human behavior -- human translators ordinarily emerge a translation draft in their mind and progressively revise it according to the reasoning in discourse. To this end, we propose a novel Multi-Hop Transformer (MHT) which offers NMT abilities to explicitly model the human-like draft-editing and reasoning process. Specifically, our model serves the sentence-level translation as a draft and properly refines its representations by attending to multiple antecedent sentences iteratively. Experiments on four widely used document translation tasks demonstrate that our method can significantly improve document-level translation performance and can tackle discourse phenomena, such as coreference error and the problem of polysemy.
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
