Assert

Top 10 Arxiv Papers Today

2.099 Mikeys

#1. The compositionality of neural networks: integrating symbolism and connectionism

Dieuwke Hupkes, Verna Dankers, Mathijs Mul, Elia Bruni

Despite a multitude of empirical studies, little consensus exists on whether neural networks are able to generalise compositionally, a controversy that, in part, stems from a lack of agreement about what it means for a neural model to be compositional. As a response to this controversy, we present a set of tests that provide a bridge between, on the one hand, the vast amount of linguistic and philosophical theory about compositionality and, on the other, the successful neural models of language. We collect different interpretations of compositionality and translate them into five theoretically grounded tests that are formulated on a task-independent level. In particular, we provide tests to investigate (i) if models systematically recombine known parts and rules (ii) if models can extend their predictions beyond the length they have seen in the training data (iii) if models' composition operations are local or global (iv) if models' predictions are robust to synonym substitutions and (v) if models favour rules or exceptions during...

more | pdf | html

Figures

None.

Tweets

BrundageBot: The compositionality of neural networks: integrating symbolism and connectionism. Dieuwke Hupkes, Verna Dankers, Mathijs Mul, and Elia Bruni https://t.co/J7B77ypydw

IntuitMachine: A proposed test to see if connectionist architectures (i.e. deep learning) are capable of the composition found in symbolic systems. https://t.co/N947NoU0VP #ai

omarsar0: This study uses several methods to test the compositionality of neural networks in particular as it relates to language modeling. Models tested: recurrent, convolution, and the recently popular transformer. The notes on linguistic theory are nice! https://t.co/gmySHE8Yyc https://t.co/YGkwpU5VTS

arxivml: "The compositionality of neural networks: integrating symbolism and connectionism", Dieuwke Hupkes, Verna Dankers, … https://t.co/It3Q62RS4t

_dieuwke_: Why? What else? And what does this have to do with compositionality in natural language? For more results, motivation and elaborate discussion, have a look: https://t.co/AqyUZUGHNg!

_dieuwke_: Curious what people may mean when they say a neural network is (not) compositional? And how that relates to linguistics and philosophy literature on compositionality? Check our new paper on compositionality in neural networks: https://t.co/AqyUZUGHNg! https://t.co/Z9bj1FYKiS

_dieuwke_: Why? What else? And what does this have to do with compositionality in natural language? For more results, motivation and elaborate discussion, have a look: https://t.co/AqyUZUGHNg!

SciFi: The compositionality of neural networks: integrating symbolism and connectionism. https://t.co/DlFVf4cGMz

arxiv_cscl: The compositionality of neural networks: integrating symbolism and connectionism https://t.co/K0vPlCD4y2

arxiv_cscl: The compositionality of neural networks: integrating symbolism and connectionism https://t.co/K0vPlCUFpA

arxiv_cscl: The compositionality of neural networks: integrating symbolism and connectionism https://t.co/K0vPlCD4y2

stjaco: The compositionality of neural networks: integrating symbolism and connectionism https://t.co/IPR96bXeyc

KnXChg: RT @arxiv_cscl: The compositionality of neural networks: integrating symbolism and connectionism https://t.co/K0vPlCD4y2

Github

Repository: am-i-compositional
User: i-machine-think
Language: Python

Stargazers: 0
Subscribers: 3

Forks: 0
Open Issues: 0

Youtube

None.

Other stats

Sample Sizes : None.

Authors: 4

Total Words: 21534

Unqiue Words: 4245

2.078 Mikeys

#2. Automated quantum programming via reinforcement learning for combinatorial optimization

Keri A. McKiernan, Erik Davis, M. Sohaib Alam, Chad Rigetti

We develop a general method for incentive-based programming of hybrid quantum-classical computing systems using reinforcement learning, and apply this to solve combinatorial optimization problems on both simulated and real gate-based quantum computers. Relative to a set of randomly generated problem instances, agents trained through reinforcement learning techniques are capable of producing short quantum programs which generate high quality solutions on both types of quantum resources. We observe generalization to problems outside of the training set, as well as generalization from the simulated quantum resource to the physical quantum resource.

more | pdf | html

Figures

None.

Tweets

arxiv_org: Automated quantum programming via reinforcement learning for combinatorial optimization. https://t.co/oRFlu6QJJw https://t.co/SwmtWqNqtq

kenjikun__: https://t.co/3CTGZMeGcm 強化学習を使って組合せ最適化問題のより良い解を出すような浅い量子回路を生成する方法を提案した．量子回路を実行する環境としてはシミュレーションと実機を用いた．エージェントとしてはPPO (Proximal Policy Optimization)を用いた QAOAより短い回路がえられた．

arxivml: "Automated quantum programming via reinforcement learning for combinatorial optimization", Keri A． McKiernan, Erik … https://t.co/3jcEn5sMwj

k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization with @braised_babbage, @sohaib_alam, @ChadRigetti code, datasets, models: https://t.co/I73YtZIs7F #QuantumComputing #ReinforcementLearning #optimization

arxiv_cs_LG: Automated quantum programming via reinforcement learning for combinatorial optimization. Keri A. McKiernan, Erik Davis, M. Sohaib Alam, and Chad Rigetti https://t.co/SECujs1PrZ

Memoirs: Automated quantum programming via reinforcement learning for combinatorial optimization. https://t.co/4sov0F4REi

trisetyarso: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

HubBucket: RT @arxiv_org: Automated quantum programming via reinforcement learning for combinatorial optimization. https://t.co/oRFlu6QJJw https://t.c…

matt_reagor: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

stuart_hadfield: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

ChadRigetti: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

snuffkin: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

nalidoust: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

blake_johnson: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

nicolasochem: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

notmgsk: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

fifcsml: RT @arxiv_org: Automated quantum programming via reinforcement learning for combinatorial optimization. https://t.co/oRFlu6QJJw https://t.c…

sohaib_alam: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

braised_babbage: RT @k_mckiern: New paper! https://t.co/p4QZMpHi3p Automated quantum programming via reinforcement learning for combinatorial optimization…

JawaeChan: RT @arxiv_org: Automated quantum programming via reinforcement learning for combinatorial optimization. https://t.co/oRFlu6QJJw https://t.c…

Github

None.

Youtube

None.

Other stats

Sample Sizes : None.

Authors: 4

Total Words: 0

Unqiue Words: 0

2.068 Mikeys

#3. VL-BERT: Pre-training of Generic Visual-Linguistic Representations

Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, Jifeng Dai

We introduce a new pre-trainable generic representation for visual-linguistic tasks, called Visual-Linguistic BERT (VL-BERT for short). VL-BERT adopts the simple yet powerful Transformer model as the backbone, and extends it to take both visual and linguistic embedded features as input. In it, each element of the input is either of a word from the input sentence, or a region-of-interest (RoI) from the input image. It is designed to fit for most of the vision-and-language downstream tasks. To better exploit the generic representation, we pre-train VL-BERT on massive-scale Conceptual Captions dataset with three tasks: masked language modeling with visual clues, masked RoI classification with linguistic clues, and sentence-image relationship prediction. Extensive empirical analysis demonstrates that the pre-training procedure can better align the visual-linguistic clues and benefit the downstream tasks, such as visual question answering, visual commonsense reasoning and referring expression comprehension. It is worth noting...

more | pdf | html

Figures

None.

Tweets

BrundageBot: VL-BERT: Pre-training of Generic Visual-Linguistic Representations. Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei Lu, Furu Wei, and Jifeng Dai https://t.co/eeqrCgbZze

arxiv_in_review: #ICLR2020 VL-BERT: Pre-training of Generic Visual-Linguistic Representations. (arXiv:1908.08530v1 [cs\.CV]) https://t.co/lfDcjcuN0B

arxivml: "VL-BERT: Pre-training of Generic Visual-Linguistic Representations", Weijie Su, Xizhou Zhu, Yue Cao, Bin Li, Lewei… https://t.co/2PSRBL6rsn

Memoirs: VL-BERT: Pre-training of Generic Visual-Linguistic Representations. https://t.co/WDh5Mgf5Jx

arxiv_cscv: VL-BERT: Pre-training of Generic Visual-Linguistic Representations https://t.co/AKQoR6pinr

arxiv_cscv: VL-BERT: Pre-training of Generic Visual-Linguistic Representations https://t.co/AKQoR67GYR

arxiv_cscl: VL-BERT: Pre-training of Generic Visual-Linguistic Representations https://t.co/YjcG15hrIq

arxiv_cscl: VL-BERT: Pre-training of Generic Visual-Linguistic Representations https://t.co/YjcG15z2zY

Github

None.

Youtube

None.

Other stats

Sample Sizes : None.

Authors: 7

Total Words: 0

Unqiue Words: 0

2.061 Mikeys

#4. More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation

Yunguan Fu, Maria R. Robu, Bongjin Koo, Crispin Schneider, Stijn van Laarhoven, Danail Stoyanov, Brian Davidson, Matthew J. Clarkson, Yipeng Hu

Improving a semi-supervised image segmentation task has the option of adding more unlabelled images, labelling the unlabelled images or combining both, as neither image acquisition nor expert labelling can be considered trivial in most clinical applications. With a laparoscopic liver image segmentation application, we investigate the performance impact by altering the quantities of labelled and unlabelled training data, using a semi-supervised segmentation algorithm based on the mean teacher learning paradigm. We first report a significantly higher segmentation accuracy, compared with supervised learning. Interestingly, this comparison reveals that the training strategy adopted in the semi-supervised algorithm is also responsible for this observed improvement, in addition to the added unlabelled data. We then compare different combinations of labelled and unlabelled data set sizes for training semi-supervised segmentation networks, to provide a quantitative example of the practically useful trade-off between the two data planning...

more | pdf | html

Figures

None.

Tweets

arxiv_org: More unlabelled data or label more data? A study on semi-supervised laparoscopic image se... https://t.co/92rdqAHP2W https://t.co/mVvz8lX6zm

arxivml: "More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation", Yunguan Fu, … https://t.co/KaiiV79I1g

mathpluscode: Proud of my latest research on laparoscopic image segmentation. We showed that independent of an increase in unlabelled data, the semi-supervised training strategy improves the segmentation accuracy. Accepted for the @miccai2019 MIL3ID workshop, https://t.co/zoCvsJIqTt. https://t.co/VPGHnvHR4E

arxiv_cs_LG: More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation. Yunguan Fu, Maria R. Robu, Bongjin Koo, Crispin Schneider, Stijn van Laarhoven, Danail Stoyanov, Brian Davidson, Matthew J. Clarkson, and Yipeng Hu https://t.co/YIfBNx9nB2

StatsPapers: More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation. https://t.co/ItH0NVRNI0

arxiv_cscv: More unlabelled data or label more data? A study on semi-supervised laparoscopic image segmentation https://t.co/kdbuVlX7qX

Rosenchild: RT @arxiv_org: More unlabelled data or label more data? A study on semi-supervised laparoscopic image se... https://t.co/92rdqAHP2W https:/…

HubBucket: RT @arxiv_org: More unlabelled data or label more data? A study on semi-supervised laparoscopic image se... https://t.co/92rdqAHP2W https:/…

jaialkdanel: RT @arxiv_org: More unlabelled data or label more data? A study on semi-supervised laparoscopic image se... https://t.co/92rdqAHP2W https:/…

udmrzn: RT @arxiv_org: More unlabelled data or label more data? A study on semi-supervised laparoscopic image se... https://t.co/92rdqAHP2W https:/…

JawaeChan: RT @arxiv_org: More unlabelled data or label more data? A study on semi-supervised laparoscopic image se... https://t.co/92rdqAHP2W https:/…

junsukchoe: RT @arxiv_org: More unlabelled data or label more data? A study on semi-supervised laparoscopic image se... https://t.co/92rdqAHP2W https:/…

Github

None.

Youtube

None.

Other stats

Sample Sizes : None.

Authors: 9

Total Words: 0

Unqiue Words: 0

2.06 Mikeys

#5. Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning

Jyoti Aneja, Harsh Agrawal, Dhruv Batra, Alexander Schwing

Diverse and accurate vision+language modeling is an important goal to retain creative freedom and maintain user engagement. However, adequately capturing the intricacies of diversity in language models is challenging. Recent works commonly resort to latent variable models augmented with more or less supervision from object detectors or part-of-speech tags. Common to all those methods is the fact that the latent variable either only initializes the sentence generation process or is identical across the steps of generation. Both methods offer no fine-grained control. To address this concern, we propose Seq-CVAE which learns a latent space for every word position. We encourage this temporal latent space to capture the 'intention' about how to complete the sentence by mimicking a representation which summarizes the future. We illustrate the efficacy of the proposed approach to anticipate the sentence continuation on the challenging MSCOCO dataset, significantly improving diversity metrics compared to baselines while performing on par...

more | pdf | html

Figures

None.

Tweets

BrundageBot: Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning. Jyoti Aneja, Harsh Agrawal, Dhruv Batra, and Alexander Schwing https://t.co/OiveCQyKXK

arxivml: "Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning", Jyoti Aneja, Harsh Agrawal, … https://t.co/2y1MO0bGqf

StatsPapers: Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning. https://t.co/POo18z8uVP

arxiv_cscv: Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning https://t.co/aIbW4Syhw5

arxiv_cscv: Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning https://t.co/aIbW4SPSnD

arxiv_cscl: Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning https://t.co/qtC2wMy9aU

arxiv_cscl: Sequential Latent Spaces for Modeling the Intention During Diverse Image Captioning https://t.co/qtC2wMPK2s

Github

None.

Youtube

None.

Other stats

Sample Sizes : None.

Authors: 4

Total Words: 0

Unqiue Words: 0

2.06 Mikeys

#6. ViCo: Word Embeddings from Visual Co-occurrences

Tanmay Gupta, Alexander Schwing, Derek Hoiem

We propose to learn word embeddings from visual co-occurrences. Two words co-occur visually if both words apply to the same image or image region. Specifically, we extract four types of visual co-occurrences between object and attribute words from large-scale, textually-annotated visual databases like VisualGenome and ImageNet. We then train a multi-task log-bilinear model that compactly encodes word "meanings" represented by each co-occurrence type into a single visual word-vector. Through unsupervised clustering, supervised partitioning, and a zero-shot-like generalization analysis we show that our word embeddings complement text-only embeddings like GloVe by better representing similarities and differences between visual concepts that are difficult to obtain from text corpora alone. We further evaluate our embeddings on five downstream applications, four of which are vision-language tasks. Augmenting GloVe with our embeddings yields gains on all tasks. We also find that random embeddings perform comparably to learned embeddings...

more | pdf | html

Figures

None.

Tweets

BrundageBot: ViCo: Word Embeddings from Visual Co-occurrences. Tanmay Gupta, Alexander Schwing, and Derek Hoiem https://t.co/RFVPCPQQEy

arxivml: "ViCo: Word Embeddings from Visual Co-occurrences", Tanmay Gupta, Alexander Schwing, Derek Hoiem https://t.co/ZTor7QoRhE

tanmay2099: Need a break from BERTmania? Checkout ViCo -- multi-sense word embeddings from visual (as opposed to textual) co-occurrences. Work done in collaboration with @HoiemDerek and @alexschwing at @IllinoisCS. To be presented at ICCV 2019! https://t.co/ieT0BHTXbk

arxiv_cscv: ViCo: Word Embeddings from Visual Co-occurrences https://t.co/iY04LVqvJx

arxiv_cscv: ViCo: Word Embeddings from Visual Co-occurrences https://t.co/iY04LVI6B5

arxiv_cscl: ViCo: Word Embeddings from Visual Co-occurrences https://t.co/4h4xR1CRTn

arxiv_cscl: ViCo: Word Embeddings from Visual Co-occurrences https://t.co/4h4xR1UsKV

arxiv_cscl: ViCo: Word Embeddings from Visual Co-occurrences https://t.co/4h4xR1CRTn

Github

None.

Youtube

None.

Other stats

Sample Sizes : None.

Authors: 3

Total Words: 0

Unqiue Words: 0

2.057 Mikeys

#7. Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks

Dominique Beaini, Sofiane Achiche, Alexandre Duperré, Maxime Raison

Current saliency methods require to learn large scale regional features using small convolutional kernels, which is not possible with a simple feed-forward network. Some methods solve this problem by using segmentation into superpixels while others downscale the image through the network and rescale it back to its original size. The objective of this paper is to show that saliency convolutional neural networks (CNN) can be improved by using a Green's function convolution (GFC) to extrapolate edges features into salient regions. The GFC acts as a gradient integrator, allowing to produce saliency features from thin edge-like features directly inside the CNN. Hence, we propose the gradient integration and sum (GIS) layer that combines the edges features with the saliency features. Using the HED and DSS architecture, we demonstrated that adding a GIS layer near the network's output allows to reduce the sensitivity to the parameter initialization and overfitting, thus improving the repeatability of the training. By adding a GIS layer...

more | pdf | html

Figures

Tweets

BrundageBot: Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks. Dominique Beaini, Sofiane Achiche, Alexandre Duperré, and Maxime Raison https://t.co/IctwizHzKt

arxivml: "Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks", Dominique Beaini, Sofian… https://t.co/wymUZvQlxO

Memoirs: Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks. https://t.co/hUyiPOdMGz

arxiv_cscv: Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks https://t.co/RPwL6XUqzN

arxiv_cscv: Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks https://t.co/RPwL6XCPbd

dirackuma: @momiji_fullmoon https://t.co/wh54b4raGw 文字化け…

disigandalf: RT @arxiv_cscv: Deep Green Function Convolution for Improving Saliency in Convolutional Neural Networks https://t.co/RPwL6XUqzN

Github

None.

Youtube

None.

Other stats

Sample Sizes : None.

Authors: 4

Total Words: 7846

Unqiue Words: 2066

2.057 Mikeys

#8. Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation

Alfio Gliozzo, Michael R. Glass, Sarthak Dash, Mustafa Canim

In this paper, we propose a fully automated system to extend knowledge graphs using external information from web-scale corpora. The designed system leverages a deep learning based technology for relation extraction that can be trained by a distantly supervised approach. In addition to that, the system uses a deep learning approach for knowledge base completion by utilizing the global structure information of the induced KG to further refine the confidence of the newly discovered relations. The designed system does not require any effort for adaptation to new languages and domains as it does not use any hand-labeled data, NLP analytics and inference rules. Our experiments, performed on a popular academic benchmark demonstrate that the suggested system boosts the performance of relation extraction by a wide margin, reporting error reductions of 50%, resulting in relative improvement of up to 100%. Also, a web-scale experiment conducted to extend DBPedia with knowledge from Common Crawl shows that our system is not only scalable but...

more | pdf | html

Figures

Tweets

arxiv_org: Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and... https://t.co/DgCt5UR7vo https://t.co/jL19zQCEIl

BrundageBot: Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation. Alfio Gliozzo, Michael R. Glass, Sarthak Dash, and Mustafa Canim https://t.co/2zukydGiLf

arxivml: "Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation", Alfio Gliozz… https://t.co/DsD6m7K2nQ

arxiv_cscl: Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation https://t.co/OBOkZsIKXH

arxiv_cscl: Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation https://t.co/OBOkZt0lPf

arxiv_cscl: Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation https://t.co/OBOkZsIKXH

HubBucket: RT @arxiv_org: Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and... https://t.co/DgCt5UR7vo https://…

RexDouglass: RT @arxiv_org: Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and... https://t.co/DgCt5UR7vo https://…

RexDouglass: RT @arxiv_cscl: Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and Validation https://t.co/OBOkZt0lPf

fifcsml: RT @arxiv_org: Populating Web Scale Knowledge Graphs using Distantly Supervised Relation Extraction and... https://t.co/DgCt5UR7vo https://…

Github

None.

Youtube

None.

Other stats

Sample Sizes : None.

Authors: 4

Total Words: 6197

Unqiue Words: 1952

2.054 Mikeys

#9. Deep Reinforcement Learning for Foreign Exchange Trading

Chun-Chieh Wang, Yun-Cheng Tsai

Reinforcement learning can interact with the environment and is suitable for applications in decision control systems. Therefore, we used the reinforcement learning method to establish a foreign exchange transaction, avoiding the long-standing problem of unstable trends in deep learning predictions. In the system design, we optimized the Sure-Fire statistical arbitrage policy, set three different actions, encoded the continuous price over a period of time into a heat-map view of the Gramian Angular Field (GAF) and compared the Deep Q Learning (DQN) and Proximal Policy Optimization (PPO) algorithms. To test feasibility, we analyzed three currency pairs, namely EUR/USD, GBP/USD, and AUD/USD. We trained the data in units of four hours from 1 August 2018 to 30 November 2018 and tested model performance using data between 1 December 2018 and 31 December 2018. The test results of the various models indicated that favorable investment performance was achieved as long as the model was able to handle complex and random processes and the...

more | pdf | html

Figures

None.

Tweets

arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

peisuke: ほう。 https://t.co/lGrAP38qzz

arxivml: "Deep Reinforcement Learning for Foreign Exchange Trading", Chun-Chieh Wang, Yun-Cheng Tsai https://t.co/GpbOUTr3m4

arxiv_cs_LG: Deep Reinforcement Learning for Foreign Exchange Trading. Chun-Chieh Wang and Yun-Cheng Tsai https://t.co/VAKGQqgsmT

SciFi: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/gcftM8TJVV

udmrzn: RT @arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

muktabh: RT @arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

fullNam35087976: RT @arxivml: "Deep Reinforcement Learning for Foreign Exchange Trading", Chun-Chieh Wang, Yun-Cheng Tsai https://t.co/GpbOUTr3m4

puneethmishra: RT @arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

jajaldo: RT @arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

dannyehb: RT @arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

ml_unam: RT @arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

fifcsml: RT @arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

HomoSapienLCY: RT @arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

MozejkoMarcin: RT @arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

Sam09lol: RT @arxiv_org: Deep Reinforcement Learning for Foreign Exchange Trading. https://t.co/erZz0R9w47 https://t.co/DIhiLSWrLP

Github

None.

Youtube

None.

Other stats

Sample Sizes : None.

Authors: 2

Total Words: 0

Unqiue Words: 0

2.053 Mikeys

#10. Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning

Ningyu Zhang, Shumin Deng, Zhanlin Sun, Jiaoyan Chen, Wei Zhang, Huajun Chen

Relation extraction aims to extract relational facts from sentences. Previous models mainly rely on manually labeled datasets, seed instances or human-crafted patterns, and distant supervision. However, the human annotation is expensive, while human-crafted patterns suffer from semantic drift and distant supervision samples are usually noisy. Domain adaptation methods enable leveraging labeled data from a different but related domain. However, different domains usually have various textual relation descriptions and different label space (the source label space is usually a superset of the target label space). To solve these problems, we propose a novel model of relation-gated adversarial learning for relation extraction, which extends the adversarial based domain adaptation. Experimental results have shown that the proposed approach outperforms previous domain adaptation methods regarding partial domain adaptation and can improve the accuracy of distance supervised relation extraction through fine-tuning.

more | pdf | html

Figures

None.

Tweets

BrundageBot: Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning. Ningyu Zhang, Shumin Deng, Zhanlin Sun, Jiaoyan Chen, Wei Zhang, and Huajun Chen https://t.co/hG3KO1Dx1v

arxiv_in_review: #AAAI2020 Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning. (arXiv:1908.08507v1 [cs\.LG]) https://t.co/3QeQGg7RlQ

arxivml: "Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning", Ningyu Zhang, Shumin Deng, Zha… https://t.co/mkaqr7tNTA

StatsPapers: Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning. https://t.co/q6rxjvxx4J

arxiv_cscl: Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning https://t.co/fZUQfGLypG

arxiv_cscl: Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning https://t.co/fZUQfGtX16

arxiv_cscl: Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning https://t.co/fZUQfGLypG

RexDouglass: RT @arxiv_cscl: Transfer Learning for Relation Extraction via Relation-Gated Adversarial Learning https://t.co/fZUQfGtX16

Github

None.

Youtube

None.

Other stats

Sample Sizes : None.

Authors: 6

Total Words: 0

Unqiue Words: 0

About

Assert is a website where the best academic papers on arXiv (computer science, math, physics), bioRxiv (biology), BITSS (reproducibility), EarthArXiv (earth science), engrXiv (engineering), LawArXiv (law), PsyArXiv (psychology), SocArXiv (social science), and SportRxiv (sport research) bubble to the top each day.

Papers are scored (in real-time) based on how verifiable they are (as determined by their Github repos) and how interesting they are (based on Twitter).

To see top papers, follow us on twitter @assertpub_ (arXiv), @assert_pub (bioRxiv), and @assertpub_dev (everything else).

To see beautiful figures extracted from papers, follow us on Instagram.

Tracking 177,899 papers.