Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userCounterfactual Adversarial Learning with Representation Interpolation
التعلم العدواني المتعارض مع الاستيفاء التمثيل
343
0 0
0.0
(
0
)
Created by
Shamra Editor
Ask ChatGPT about the research
تظهر نماذج التعلم العميق تفضيلات للتركيب الإحصائي بشأن التفكير المنطقي.قد يتم حفظ الارتباطات الزائفة عند وجود تحيز إحصائي في بيانات التدريب، مما يحد بشدة من أداء النموذج بشكل خاص في سيناريوهات البيانات الصغيرة.في هذا العمل، نقدم إطار تدريب عدائي مضاد للأرض (القط) لمعالجة المشكلة من منظور السببية.خاصة، بالنسبة لعينة محددة، تنشئ القط أولا تمثيل مضاد من خلال الاستيفاء الفضائي الكامن بطريقة مخفية، ثم يؤدي ذلك إلى تقليل المخاطر المضادة (CRM) على كل زوج مضاد للأصلية لضبط وزن الخسارة العينة بشكل حيوي، مما يشجع النموذجلاستكشاف التأثير السببي الحقيقي.توضح تجارب واسعة أن القط يحقق تحسين أداء كبير على سوتا عبر المهام المختلفة المصب، بما في ذلك تصنيف الجملة، والاستدلال باللغة الطبيعية والرد على السؤال.
Deep learning models exhibit a preference for statistical fitting over logical reasoning. Spurious correlations might be memorized when there exists statistical bias in training data, which severely limits the model performance especially in small data scenarios. In this work, we introduce Counterfactual Adversarial Training framework (CAT) to tackle the problem from a causality perspective. Particularly, for a specific sample, CAT first generates a counterfactual representation through latent space interpolation in an adversarial manner, and then performs Counterfactual Risk Minimization (CRM) on each original-counterfactual pair to adjust sample-wise loss weight dynamically, which encourages the model to explore the true causal effect. Extensive experiments demonstrate that CAT achieves substantial performance improvement over SOTA across different downstream tasks, including sentence classification, natural language inference and question answering.
References used
https://aclanthology.org/
rate research
Read More
Taxonomies are valuable resources for many applications, but the limited coverage due to the expensive manual curation process hinders their general applicability. Prior works attempt to automatically expand existing taxonomies to improve their cover
age by learning concept embeddings in Euclidean space, while taxonomies, inherently hierarchical, more naturally align with the geometric properties of a hyperbolic space. In this paper, we present HyperExpan, a taxonomy expansion algorithm that seeks to preserve the structure of a taxonomy in a more expressive hyperbolic embedding space and learn to represent concepts and their relations with a Hyperbolic Graph Neural Network (HGNN). Specifically, HyperExpan leverages position embeddings to exploit the structure of the existing taxonomies, and characterizes the concept profile information to support the inference on new concepts that are unseen during training. Experiments show that our proposed HyperExpan outperforms baseline models with representation learning in a Euclidean feature space and achieves state-of-the-art performance on the taxonomy expansion benchmarks.
Generating informative and appropriate responses is challenging but important for building human-like dialogue systems. Although various knowledge-grounded conversation models have been proposed, these models have limitations in utilizing knowledge t
hat infrequently occurs in the training data, not to mention integrating unseen knowledge into conversation generation. In this paper, we propose an Entity-Agnostic Representation Learning (EARL) method to introduce knowledge graphs to informative conversation generation. Unlike traditional approaches that parameterize the specific representation for each entity, EARL utilizes the context of conversations and the relational structure of knowledge graphs to learn the category representation for entities, which is generalized to incorporating unseen entities in knowledge graphs into conversation generation. Automatic and manual evaluations demonstrate that our model can generate more informative, coherent, and natural responses than baseline models.
Large-scale auto-regressive models have achieved great success in dialogue response generation, with the help of Transformer layers. However, these models do not learn a representative latent space of the sentence distribution, making it hard to cont
rol the generation. Recent works have tried on learning sentence representations using Transformer-based framework, but do not model the context-response relationship embedded in the dialogue datasets. In this work, we aim to construct a robust sentence representation learning model, that is specifically designed for dialogue response generation, with Transformer-based encoder-decoder structure. An utterance-level contrastive learning is proposed, encoding predictive information in each context representation for its corresponding response. Extensive experiments are conducted to verify the robustness of the proposed representation learning mechanism. By using both reference-based and reference-free evaluation metrics, we provide detailed analysis on the generated sentences, demonstrating the effectiveness of our proposed model.
Exemplar-Guided Paraphrase Generation (EGPG) aims to generate a target sentence which conforms to the style of the given exemplar while encapsulating the content information of the source sentence. In this paper, we propose a new method with the goal
of learning a better representation of the style and the content. This method is mainly motivated by the recent success of contrastive learning which has demonstrated its power in unsupervised feature extraction tasks. The idea is to design two contrastive losses with respect to the content and the style by considering two problem characteristics during training. One characteristic is that the target sentence shares the same content with the source sentence, and the second characteristic is that the target sentence shares the same style with the exemplar. These two contrastive losses are incorporated into the general encoder-decoder paradigm. Experiments on two datasets, namely QQP-Pos and ParaNMT, demonstrate the effectiveness of our proposed constrastive losses.
Recent progress in pretrained Transformer-based language models has shown great success in learning contextual representation of text. However, due to the quadratic self-attention complexity, most of the pretrained Transformers models can only handle
relatively short text. It is still a challenge when it comes to modeling very long documents. In this work, we propose to use a graph attention network on top of the available pretrained Transformers model to learn document embeddings. This graph attention network allows us to leverage the high-level semantic structure of the document. In addition, based on our graph document model, we design a simple contrastive learning strategy to pretrain our models on a large amount of unlabeled corpus. Empirically, we demonstrate the effectiveness of our approaches in document classification and document retrieval tasks.
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
