Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userSGG: Learning to Select, Guide, and Generate for Keyphrase Generation
SGG: تعلم تحديد، توجيه، وإنشاء جيل تسمم
224
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
يمكن تصنيف الأجهزة المحمولة، التي تلخص تماما المواضيع الرفيعة المستوى التي تمت مناقشتها في وثيقة، في عبارة البصرة الحالية التي تظهر صراحة في النص المصدر والفتحية الغائبة التي لا تتطابق مع أي لاحق متجاور ولكنه مرتبط للغاية بالمصدر. معظم نهج توليد مفاتيح المفاتيح الموجودة تولد بمتزامنة خط أساتيجية موجودة وتغيب دون تمييز هذه الفئتين بشكل صريح. في هذه الورقة، يقترح اقتراح نهج محدد (SGG) في التعامل مع توليد الجماهير الموجود والمجابطة الحاضر بشكل منفصل مع آليات مختلفة. على وجه التحديد، SGG هي شبكة عصبية هرمية تتألف من محدد مقرا لها في طبقة منخفضة تتركز على جيل المفتاح الحالي، ومولد موجه في الاختيار في طبقة عالية مخصصة للتغيب عن جيل تسخير الغيام، ووحشية في المنتصف معلومات من محدد للمولد. النتائج التجريبية على أربعة معايير توليد مفاتيح المفاتيح توضح فعالية طرازنا، والتي تتفوق بشكل كبير على خطوط الأساس القوية لكلا الجداول الرائعة الحالية والمغادرة. علاوة على ذلك، فإننا نقدم SGG إلى مهمة توليد العنوان تشير إلى إمكانية قدرتها على مهام توليد اللغة الطبيعية.
Keyphrases, that concisely summarize the high-level topics discussed in a document, can be categorized into present keyphrase which explicitly appears in the source text and absent keyphrase which does not match any contiguous subsequence but is highly semantically related to the source. Most existing keyphrase generation approaches synchronously generate present and absent keyphrases without explicitly distinguishing these two categories. In this paper, a Select-Guide-Generate (SGG) approach is proposed to deal with present and absent keyphrases generation separately with different mechanisms. Specifically, SGG is a hierarchical neural network which consists of a pointing-based selector at low layer concentrated on present keyphrase generation, a selection-guided generator at high layer dedicated to absent keyphrase generation, and a guider in the middle to transfer information from selector to generator. Experimental results on four keyphrase generation benchmarks demonstrate the effectiveness of our model, which significantly outperforms the strong baselines for both present and absent keyphrases generation. Furthermore, we extend SGG to a title generation task which indicates its extensibility in natural language generation tasks.
References used
https://aclanthology.org/
rate research
Read More
Previous existing visual question answering (VQA) systems commonly use graph neural networks(GNNs) to extract visual relationships such as semantic relations or spatial relations. However, studies that use GNNs typically ignore the importance of each
relation and simply concatenate outputs from multiple relation encoders. In this paper, we propose a novel layer architecture that fuses multiple visual relations through an attention mechanism to address this issue. Specifically, we develop a model that uses question embedding and joint embedding of the encoders to obtain dynamic attention weights with regard to the type of questions. Using the learnable attention weights, the proposed model can efficiently use the necessary visual relation features for a given question. Experimental results on the VQA 2.0 dataset demonstrate that the proposed model outperforms existing graph attention network-based architectures. Additionally, we visualize the attention weight and show that the proposed model assigns a higher weight to relations that are more relevant to the question.
Humans make appropriate responses not only based on previous dialogue utterances but also on implicit background knowledge such as common sense. Although neural response generation models seem to produce human-like responses, they are mostly end-to-e
nd and not generating intermediate grounds between a dialogue history and responses. This work aims to study if and how we can train an RG model that talks with itself to generate implicit knowledge before making responses. We further investigate can such models identify when to generate implicit background knowledge and when it is not necessary. Experimental results show that compared with models that directly generate responses given a dialogue history, self-talk models produce better-quality responses according to human evaluation on grammaticality, coherence, and engagingness. And models that are trained to identify when to self-talk further improves the response quality. Analysis on generated implicit knowledge shows that models mostly use the knowledge appropriately in the responses.
Recent years have seen a flourishing of neural keyphrase generation (KPG) works, including the release of several large-scale datasets and a host of new models to tackle them. Model performance on KPG tasks has increased significantly with evolving d
eep learning research. However, there lacks a comprehensive comparison among different model designs, and a thorough investigation on related factors that may affect a KPG system's generalization performance. In this empirical study, we aim to fill this gap by providing extensive experimental results and analyzing the most crucial factors impacting the generalizability of KPG models. We hope this study can help clarify some of the uncertainties surrounding the KPG task and facilitate future research on this topic.
Recent developments in neural networks have led to the advance in data-to-text generation. However, the lack of ability of neural models to control the structure of generated output can be limiting in certain real-world applications. In this study, w
e propose a novel Plan-then-Generate (PlanGen) framework to improve the controllability of neural data-to-text models. Extensive experiments and analyses are conducted on two benchmark datasets, ToTTo and WebNLG. The results show that our model is able to control both the intra-sentence and inter-sentence structure of the generated output. Furthermore, empirical comparisons against previous state-of-the-art methods show that our model improves the generation quality as well as the output diversity as judged by human and automatic evaluations.
Paraphrase generation is a longstanding NLP task that has diverse applications on downstream NLP tasks. However, the effectiveness of existing efforts predominantly relies on large amounts of golden labeled data. Though unsupervised endeavors have be
en proposed to alleviate this issue, they may fail to generate meaningful paraphrases due to the lack of supervision signals. In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with data of weak supervision. Specifically, we tackle the weakly-supervised paraphrase generation problem by: (1) obtaining abundant weakly-labeled parallel sentences via retrieval-based pseudo paraphrase expansion; and (2) developing a meta-learning framework to progressively select valuable samples for fine-tuning a pre-trained language model BART on the sentential paraphrasing task. We demonstrate that our approach achieves significant improvements over existing unsupervised approaches, and is even comparable in performance with supervised state-of-the-arts.
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
