Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userAPo-VAE: Text Generation in Hyperbolic Space
APO-VAE: جيل النص في الفضاء القطعي
321
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
غالبا ما تظهر اللغة الطبيعية هيكل هرمي متأصل متأرجلا مع بناء جملة معقدة ودليل. ومع ذلك، تعلم معظم النماذج الإدارية العميقة في أحدث تضمينها فقط في مساحة ناقلات Euclidean، دون محاسبة هذه الملكية الهيكلية للغة. في هذه الورقة، نحقق في جيل النص في مساحة كامنة ضئيلة لتعلم التمثيلات الهرمية المستمرة. يتم تقديم AutoNECODER AUTONICODER AUTONCODER (APO-VAE)، حيث يتم تعريف كل من الخلفية السابقة والتنتهي من المتغيرات الكامنة عبر كرة شاذة عبر التوزيعات العادية ملفوفة. من خلال اعتماد الصيغة البدائية المزدوجة لمخلاص Kullback-Leibler، يتم تقديم إجراء تعلم الخصم لتمكين التدريب النموذجي القوي. توضح تجارب واسعة النمذجة في النمذجة اللغوية ونقل النمط غير المعقول وتوليد استجابة الحوار فعالية نموذج APO-VAE المقترح على VAES في الفضاء الكامن Euclidean، وذلك بفضل قدراته الرائعة في التقاط التسلسلات الهرمية للغة الكامنة في الفضاء القطعي.
Natural language often exhibits inherent hierarchical structure ingrained with complex syntax and semantics. However, most state-of-the-art deep generative models learn embeddings only in Euclidean vector space, without accounting for this structural property of language. In this paper, we investigate text generation in a hyperbolic latent space to learn continuous hierarchical representations. An Adversarial Poincare Variational Autoencoder (APo-VAE) is presented, where both the prior and variational posterior of latent variables are defined over a Poincare ball via wrapped normal distributions. By adopting the primal-dual formulation of Kullback-Leibler divergence, an adversarial learning procedure is introduced to empower robust model training. Extensive experiments in language modeling, unaligned style transfer, and dialog-response generation demonstrate the effectiveness of the proposed APo-VAE model over VAEs in Euclidean latent space, thanks to its superb capabilities in capturing latent language hierarchies in hyperbolic space.
References used
https://aclanthology.org/
rate research
Read More
We propose neural models to generate text from formal meaning representations based on Discourse Representation Structures (DRSs). DRSs are document-level representations which encode rich semantic detail pertaining to rhetorical relations, presuppos
ition, and co-reference within and across sentences. We formalize the task of neural DRS-to-text generation and provide modeling solutions for the problems of condition ordering and variable naming which render generation from DRSs non-trivial. Our generator relies on a novel sibling treeLSTM model which is able to accurately represent DRS structures and is more generally suited to trees with wide branches. We achieve competitive performance (59.48 BLEU) on the GMB benchmark against several strong baselines.
We present an end-to-end neural approach to generate English sentences from formal meaning representations, Discourse Representation Structures (DRSs). We use a rather standard bi-LSTM sequence-to-sequence model, work with a linearized DRS input repr
esentation, and evaluate character-level and word-level decoders. We obtain very encouraging results in terms of reference-based automatic metrics such as BLEU. But because such metrics only evaluate the surface level of generated output, we develop a new metric, ROSE, that targets specific semantic phenomena. We do this with five DRS generation challenge sets focusing on tense, grammatical number, polarity, named entities and quantities. The aim of these challenge sets is to assess the neural generator's systematicity and generalization to unseen inputs.
Recent successes in deep generative modeling have led to significant advances in natural language generation (NLG). Incorporating entities into neural generation models has demonstrated great improvements by assisting to infer the summary topic and t
o generate coherent content. To enhance the role of entity in NLG, in this paper, we aim to model the entity type in the decoding phase to generate contextual words accurately. We develop a novel NLG model to produce a target sequence based on a given list of entities. Our model has a multi-step decoder that injects the entity types into the process of entity mention generation. Experiments on two public news datasets demonstrate type injection performs better than existing type embedding concatenation baselines.
Few-shot table-to-text generation is a task of composing fluent and faithful sentences to convey table content using limited data. Despite many efforts having been made towards generating impressive fluent sentences by fine-tuning powerful pre-traine
d language models, the faithfulness of generated content still needs to be improved. To this end, this paper proposes a novel approach Attend, Memorize and Generate (called AMG), inspired by the text generation process of humans. In particular, AMG (1) attends over the multi-granularity of context using a novel strategy based on table slot level and traditional token-by-token level attention to exploit both the table structure and natural linguistic information; (2) dynamically memorizes the table slot allocation states; and (3) generates faithful sentences according to both the context and memory allocation states. Comprehensive experiments with human evaluation on three domains (i.e., humans, songs, and books) of the Wiki dataset show that our model can generate higher qualified texts when compared with several state-of-the-art baselines, in both fluency and faithfulness.
Providing pretrained language models with simple task descriptions in natural language enables them to solve some tasks in a fully unsupervised fashion. Moreover, when combined with regular learning from examples, this idea yields impressive few-shot
results for a wide range of text classification tasks. It is also a promising direction to improve data efficiency in generative settings, but there are several challenges to using a combination of task descriptions and example-based learning for text generation. In particular, it is crucial to find task descriptions that are easy to understand for the pretrained model and to ensure that it actually makes good use of them; furthermore, effective measures against overfitting have to be implemented. In this paper, we show how these challenges can be tackled: We introduce GenPET, a method for text generation that is based on pattern-exploiting training, a recent approach for combining textual instructions with supervised learning that only works for classification tasks. On several summarization and headline generation datasets, GenPET gives consistent improvements over strong baselines in few-shot settings.
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
