Filters








57,848 Hits in 4.6 sec

Learning Implicit Text Generation via Feature Matching [article]

Inkit Padhi, Pierre Dognin, Ke Bai, Cicero Nogueira dos Santos, Vijil Chenthamarakshan, Youssef Mroueh, Payel Das
2020 arXiv   pre-print
Generative feature matching network (GFMN) is an approach for training implicit generative models for images by performing moment matching on features from pre-trained neural networks.  ...  Our experimental results show the effectiveness of the proposed method, SeqGFMN, for three distinct generation tasks in English: unconditional text generation, class-conditional text generation, and unsupervised  ...  Introduction Generative feature matching networks (GFMNs) (dos Santos et al., 2019) has been recently proposed for learning implicit generative models by performing moment matching on features from pre-trained  ... 
arXiv:2005.03588v2 fatcat:r4t4iakxfbfjdidnogjme2gj6i

Learning Implicit Text Generation via Feature Matching

Inkit Padhi, Pierre Dognin, Ke Bai, Cícero Nogueira dos Santos, Vijil Chenthamarakshan, Youssef Mroueh, Payel Das
2020 Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics   unpublished
Generative feature matching network (GFMN) is an approach for training implicit generative models for images by performing moment matching on features from pre-trained neural networks.  ...  Our experimental results show the effectiveness of the proposed method, Se-qGFMN, for three distinct generation tasks in English: unconditional text generation, classconditional text generation, and unsupervised  ...  Introduction Generative feature matching networks (GFMNs) (dos Santos et al., 2019) has been recently proposed for learning implicit generative models by performing moment matching on features from pre-trained  ... 
doi:10.18653/v1/2020.acl-main.354 fatcat:63ehjn6n3nf6zbyrrbbj75z3qy

Learning Effective Representations for Person-Job Fit by Feature Fusion [article]

Junshu Jiang and Songyun Ye and Wei Wang and Jingran Xu and Xiaosheng Luo
2020 arXiv   pre-print
In this paper, we propose to learn comprehensive and effective representations of the candidates and job posts via feature fusion.  ...  job post) and then learn features for them.  ...  The learned representations are then compared to generate a matching score.  ... 
arXiv:2006.07017v1 fatcat:n52ge7nygzdqdblnqoukd5qt2m

Poisson Factorization Models for Spatiotemporal Retrieval

Eliezer de Souza da Silva, Dirk Ahlers
2017 Proceedings of the 11th Workshop on Geographic Information Retrieval - GIR'17  
The inclusion of thematic and location features in a joint factorization model allows location to be modeled as a first-class feature and can improve a range of tasks in geographic information retrieval  ...  New retrieval models promise deeper integration of multiple features and sources of information.  ...  A general easier applicability also makes it easier to model more implicit features, have the option to explicitly model features (e.g. count data: term frequency, click data, etc.), and provides a principled  ... 
doi:10.1145/3155902.3155912 dblp:conf/gir/SilvaA17 fatcat:zrca3zetgzfxhgngfsjd5iedby

Automatic Extraction of Causal Relations from Natural Language Texts: A Comprehensive Survey [article]

Nabiha Asghar
2016 arXiv   pre-print
Machines are now expected to learn generic causal extraction rules from labelled data with minimal supervision, in a domain independent-manner.  ...  Automatic extraction of cause-effect relationships from natural language texts is a challenging open problem in Artificial Intelligence.  ...  STATISTICAL & MACHINE LEARNING TECHNIQUES The need to make use of a large amount of labelled, domain-and-type-independent, textual data and to extract implicit patterns in text automatically meant that  ... 
arXiv:1605.07895v1 fatcat:mpu3bxvuwrhzvl7psaz3xx56ay

Learning Implicit Temporal Alignment for Few-shot Video Classification [article]

Songyang Zhang, Jiale Zhou, Xuming He
2021 arXiv   pre-print
To train our model, we develop a multi-task loss for learning video matching, leading to video features with better generalization.  ...  To address this, we propose a novel matching-based few-shot learning strategy for video sequences in this work.  ...  channel and temporal context of a video, leading to an implicit alignment effect in matching. • We adopt a multi-task learning strategy for few-shot video classification that improves model generalization  ... 
arXiv:2105.04823v1 fatcat:tthebmigibf7rirkt52uvna4ee

Development of Fashion Product Retrieval and Recommendations Model Based on Deep Learning

Jaechoon Jo, Seolhwa Lee, Chanhee Lee, Dongyub Lee, Heuiseok Lim
2020 Electronics  
However, the text-based search method has limitations because of the nature of the fashion industry, in which design is a very important factor.  ...  Therefore, we developed an intelligent fashion technique based on deep learning for efficient fashion product searches and recommendations consisting of a Sketch-Product fashion retrieval model and vector-based  ...  The implicit user fashion profiling collects learning data in two manners: filtering by professionals and data collection from general users.  ... 
doi:10.3390/electronics9030508 fatcat:kmffxze2zbemfhqwxcioksveui

Semantic Image Synthesis via Adversarial Learning [article]

Hao Dong, Simiao Yu, Chao Wu, Yike Guo
2017 arXiv   pre-print
To achieve this, we proposed an end-to-end neural architecture that leverages adversarial learning to automatically learn implicit loss functions, which are optimized to fulfill the aforementioned two  ...  ; 2) maintaining other image features that are irrelevant to the text description.  ...  We utilize adversarial learning to automatically learn implicit loss functions for this image synthesis task.  ... 
arXiv:1707.06873v1 fatcat:64xw3rnf7nc7zig5unzi74dfpa

Design of a generic, open platform for machine learning-assisted indexing and clustering of articles in PubMed, a biomedical bibliographic database

Neil R. Smalheiser, Aaron M. Cohen
2018 Data and Information Management  
Here, we propose and describe the design of a generic platform for biomedical text mining, which can serve as a shared resource for machine learning projects and as a public repository for their outputs  ...  A common approach is to define positive and negative training examples, extract features from article metadata, and use machine learning algorithms.  ...  Features are the results that are generated when an NLP tool or machine learning model processes a passage or corpus of text.  ... 
doi:10.2478/dim-2018-0004 pmid:30766970 pmcid:PMC6372120 fatcat:as7kyymugbdmvhornk6g6yypla

Implicit Deep Latent Variable Models for Text Generation

Le Fang, Chunyuan Li, Jianfeng Gao, Wen Dong, Changyou Chen
2019 Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)  
In this paper, we advocate sample-based representations of variational distributions for natural language, leading to implicit latent features, which can provide flexible representation power compared  ...  Deep latent variable models (LVM) such as variational auto-encoder (VAE) have recently played an important role in text generation.  ...  It facilitates learning via training an auxiliary dual function.  ... 
doi:10.18653/v1/d19-1407 dblp:conf/emnlp/FangLGDC19 fatcat:7ycevustibf7pcaifq4pvpvbkm

Neural Article Pair Modeling for Wikipedia Sub-article Matching [article]

Muhao Chen, Changping Meng, Gang Huang, Carlo Zaniolo
2018 arXiv   pre-print
The proposed model adopts a hierarchical learning structure that combines multiple variants of neural document pair encoders with a comprehensive set of explicit features.  ...  A large crowdsourced dataset is created to support the evaluation and feature extraction for the task.  ...  This indicates that the implicit semantic features are critical for characterizing the matching of main and sub-articles.  ... 
arXiv:1807.11689v2 fatcat:iq4bktx3frcvfmqez65dfv7d24

Stance in Replies and Quotes (SRQ): A New Dataset For Learning Stance in Twitter Conversations [article]

Ramon Villa-Cox, Sumeet Kumar, Matthew Babcock, Kathleen M. Carley
2020 arXiv   pre-print
Because of this, models trained on one event do not generalize to other events.  ...  Moreover, we include many baseline models for learning the stance in conversations and compare the performance of various models.  ...  The same text cleaning step was performed before generating features for all embeddings described in the paper.  ... 
arXiv:2006.00691v2 fatcat:sic7axqheracjc7lnptzob77ai

A Survey of Implicit Discourse Relation Recognition [article]

Wei Xiang, Bang Wang
2022 arXiv   pre-print
The task of implicit discourse relation recognition (IDRR) is to detect implicit relation and classify its sense between two text segments without a connective.  ...  Although sometimes a connective exists in raw texts for conveying relations, it is more often the cases that no connective exists in between two text segments but some implicit relation does exist in between  ...  feature space; (2) re-sampling: modifying the distribution of relation sense in explicit to match the distribution over implicit relations.  ... 
arXiv:2203.02982v1 fatcat:ubublxw2fnfdpexgw4jslj76tm

CLIP-Forge: Towards Zero-Shot Text-to-Shape Generation [article]

Aditya Sanghi and Hang Chu and Joseph G. Lambourne and Ye Wang and Chin-Yi Cheng and Marco Fumero and Kamal Rahimi Malekshan
2022 arXiv   pre-print
While significant recent progress has been made in text-to-image generation, text-to-shape generation remains a challenging problem due to the unavailability of paired text and shape data at a large scale  ...  We present a simple yet effective method for zero-shot text-to-shape generation that circumvents such data scarcity.  ...  For 67% of the image pairs, the crowd workers identified the images generated by the text containing the attribute or sub-category as best matching the description.  ... 
arXiv:2110.02624v2 fatcat:zb4nyevqjjgzxd3cbiibxz3rwi

Leveraging Hierarchical Deep Semantics to Classify Implicit Discourse Relations via Mutual Learning Method [chapter]

Xiaohan She, Ping Jian, Pengcheng Zhang, Heyan Huang
2016 Lecture Notes in Computer Science  
This paper presents a mutual learning method using hierarchical deep semantics for the classification of implicit discourse relations in English.  ...  To relieve this problem, we propose a mutual learning neural model which makes use of multilevel semantic information together, including the distribution of implicit discourse relations, the semantics  ...  Zhou et al. (2010) [15] , in other way, use language model, which helps the implicit relation recognition via an additional feature, to predict implicit discourse connectives rather than the relation  ... 
doi:10.1007/978-3-319-50496-4_29 fatcat:ngnd3brc2vfbvmcbdimpv7xwjq
« Previous Showing results 1 — 15 out of 57,848 results