Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userInference Time Style Control for Summarization
السيطرة على نمط الوقت الاستدلال للتخصيص
245
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
كيفية إنشاء ملخصات من أنماط مختلفة دون مطالبة كوربورا في الأساليب المستهدفة، أو تدريب نماذج منفصلة؟نقدم أساليب رواية يمكن نشرها أثناء فك التشفير الموجز على أي نموذج تلخيص مقرها المحولات المدرب مسبقا.(1) تعديل حالة وحدة فك التشفير يعدل على الفور حالات فك الترميز النهائية مع هدنات النمط المدربين خارجيا، لإثارة تحسين الإخراج مقابل نمط مستهدف.(2) تنبؤ وحدة الكلمة تقييد استخدام كلمة لفرض عنصر تحكم جذاب قوي أثناء التوليد.في تجارب تلخص مع التحكم في البساطة، يجد التقييم التلقائي والقضاة البشري نماذجنا المنتجة للنواتج بلغات أبسط بينما لا تزال مفيدة.ونحن نولد أيضا عناوين الأخبار مع العديد من الميول الإيديولوجية، والتي يمكن تمييزها من قبل البشر مع احتمال معقول.
How to generate summaries of different styles without requiring corpora in the target styles, or training separate models? We present two novel methods that can be deployed during summary decoding on any pre-trained Transformer-based summarization model. (1) Decoder state adjustment instantly modifies decoder final states with externally trained style scorers, to iteratively refine the output against a target style. (2) Word unit prediction constrains the word usage to impose strong lexical control during generation. In experiments of summarizing with simplicity control, automatic evaluation and human judges both find our models producing outputs in simpler languages while still informative. We also generate news headlines with various ideological leanings, which can be distinguished by humans with a reasonable probability.
References used
https://aclanthology.org/
rate research
Read More
In this paper, we aim to address the challenges surrounding the translation of ancient Chinese text: (1) The linguistic gap due to the difference in eras results in translations that are poor in quality, and (2) most translations are missing the cont
extual information that is often very crucial to understanding the text. To this end, we improve upon past translation techniques by proposing the following: We reframe the task as a multi-label prediction task where the model predicts both the translation and its particular era. We observe that this helps to bridge the linguistic gap as chronological context is also used as auxiliary information. We validate our framework on a parallel corpus annotated with chronology information and show experimentally its efficacy in producing quality translation outputs. We release both the code and the data for future research.
Natural Language Inference (NLI) has garnered significant attention in recent years; however, the promise of applying NLI breakthroughs to other downstream NLP tasks has remained unfulfilled. In this work, we use the multiple-choice reading comprehen
sion (MCRC) and checking factual correctness of textual summarization (CFCS) tasks to investigate potential reasons for this. Our findings show that: (1) the relatively shorter length of premises in traditional NLI datasets is the primary challenge prohibiting usage in downstream applications (which do better with longer contexts); (2) this challenge can be addressed by automatically converting resource-rich reading comprehension datasets into longer-premise NLI datasets; and (3) models trained on the converted, longer-premise datasets outperform those trained using short-premise traditional NLI datasets on downstream tasks primarily due to the difference in premise lengths.
Learning a good latent representation is essential for text style transfer, which generates a new sentence by changing the attributes of a given sentence while preserving its content. Most previous works adopt disentangled latent representation learn
ing to realize style transfer. We propose a novel text style transfer algorithm with entangled latent representation, and introduce a style classifier that can regulate the latent structure and transfer style. Moreover, our algorithm for style transfer applies to both single-attribute and multi-attribute transfer. Extensive experimental results show that our method generally outperforms state-of-the-art approaches.
Due to large number of entities in biomedical knowledge bases, only a small fraction of entities have corresponding labelled training data. This necessitates entity linking models which are able to link mentions of unseen entities using learned repre
sentations of entities. Previous approaches link each mention independently, ignoring the relationships within and across documents between the entity mentions. These relations can be very useful for linking mentions in biomedical text where linking decisions are often difficult due mentions having a generic or a highly specialized form. In this paper, we introduce a model in which linking decisions can be made not merely by linking to a knowledge base entity but also by grouping multiple mentions together via clustering and jointly making linking predictions. In experiments on the largest publicly available biomedical dataset, we improve the best independent prediction for entity linking by 3.0 points of accuracy, and our clustering-based inference model further improves entity linking by 2.3 points.
Text style can reveal sensitive attributes of the author (e.g. age and race) to the reader, which can, in turn, lead to privacy violations and bias in both human and algorithmic decisions based on text. For example, the style of writing in job applic
ations might reveal protected attributes of the candidate which could lead to bias in hiring decisions, regardless of whether hiring decisions are made algorithmically or by humans. We propose a VAE-based framework that obfuscates stylistic features of human-generated text through style transfer, by automatically re-writing the text itself. Critically, our framework operationalizes the notion of obfuscated style in a flexible way that enables two distinct notions of obfuscated style: (1) a minimal notion that effectively intersects the various styles seen in training, and (2) a maximal notion that seeks to obfuscate by adding stylistic features of all sensitive attributes to text, in effect, computing a union of styles. Our style-obfuscation framework can be used for multiple purposes, however, we demonstrate its effectiveness in improving the fairness of downstream classifiers. We also conduct a comprehensive study on style-pooling's effect on fluency, semantic consistency, and attribute removal from text, in two and three domain style transfer.
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
