arXiv subjects

William Yang Wang

Publications and source records attributed to William Yang Wang.

278 records · Page 16Linked to original sources

arXiv2018

Video Captioning via Hierarchical Reinforcement Learning

Video captioning is the task of automatically generating a textual description of the actions in a video. Although previous work (e.g. sequence-to-sequence model) has shown promising results in abstracting a coarse description of a short video, it is still very challenging to caption a video containing multiple fine-grained actions with a detailed description. This paper aims to address the challenge by proposing a novel hierarchical reinforcement learning framework for video captioning, where a high-level Manager module learns to design sub-goals and a low-level Worker module recognizes the primitive actions to fulfill the sub-goal. With this compositional framework to reinforce video captioning at different levels, our approach significantly outperforms all the baseline methods on a newly introduced large-scale dataset for fine-grained video captioning. Furthermore, our non-ensemble model has already achieved the state-of-the-art results on the widely-used MSR-VTT dataset.

cs.CV↗

arXiv2018

IcoRating: A Deep-Learning System for Scam ICO Identification

Cryptocurrencies (or digital tokens, digital currencies, e.g., BTC, ETH, XRP, NEO) have been rapidly gaining ground in use, value, and understanding among the public, bringing astonishing profits to investors. Unlike other money and banking systems, most digital tokens do not require central authorities. Being decentralized poses significant challenges for credit rating. Most ICOs are currently not subject to government regulations, which makes a reliable credit rating system for ICO projects necessary and urgent. In this paper, we introduce IcoRating, the first learning--based cryptocurrency rating system. We exploit natural-language processing techniques to analyze various aspects of 2,251 digital currencies to date, such as white paper content, founding teams, Github repositories, websites, etc. Supervised learning models are used to correlate the life span and the price change of cryptocurrencies with these features. For the best setting, the proposed system is able to identify scam ICO projects with 0.83 precision. We hope this work will help investors identify scam ICOs and attract more efforts in automatically evaluating and analyzing ICO projects.

cs.CL↗

arXiv2017

TFW, DamnGina, Juvie, and Hotsie-Totsie: On the Linguistic and Social Aspects of Internet Slang

Slang is ubiquitous on the Internet. The emergence of new social contexts like micro-blogs, question-answering forums, and social networks has enabled slang and non-standard expressions to abound on the web. Despite this, slang has been traditionally viewed as a form of non-standard language -- a form of language that is not the focus of linguistic analysis and has largely been neglected. In this work, we use UrbanDictionary to conduct the first large-scale linguistic analysis of slang and its social aspects on the Internet to yield insights into this variety of language that is increasingly used all over the world online. We begin by computationally analyzing the phonological, morphological and syntactic properties of slang. We then study linguistic patterns in four specific categories of slang namely alphabetisms, blends, clippings, and reduplicatives. Our analysis reveals that slang demonstrates extra-grammatical rules of phonological and morphological formation that markedly distinguish it from the standard form shedding insight into its generative patterns. Next, we analyze the social aspects of slang by studying subject restriction and stereotyping in slang usage. Analyzing tens of thousands of such slang words reveals that the majority of slang on the Internet belongs to two major categories: sex and drugs. We also noted that not only is slang usage not immune to prevalent social biases and prejudices but also reflects such biases and stereotypes more intensely than the standard variety.

cs.CL↗

arXiv2017

Learning to Explain Non-Standard English Words and Phrases

We describe a data-driven approach for automatically explaining new, non-standard English expressions in a given sentence, building on a large dataset that includes 15 years of crowdsourced examples from UrbanDictionary.com. Unlike prior studies that focus on matching keywords from a slang dictionary, we investigate the possibility of learning a neural sequence-to-sequence model that generates explanations of unseen non-standard English expressions given context. We propose a dual encoder approach---a word-level encoder learns the representation of context, and a second character-level encoder to learn the hidden representation of the target non-standard expression. Our model can produce reasonable definitions of new non-standard English expressions given their context with certain confidence.

cs.CL↗

arXiv2017

Deep Residual Learning for Weakly-Supervised Relation Extraction

Deep residual learning (ResNet) is a new method for training very deep neural networks using identity map-ping for shortcut connections. ResNet has won the ImageNet ILSVRC 2015 classification task, and achieved state-of-the-art performances in many computer vision tasks. However, the effect of residual learning on noisy natural language processing tasks is still not well understood. In this paper, we design a novel convolutional neural network (CNN) with residual learning, and investigate its impacts on the task of distantly supervised noisy relation extraction. In contradictory to popular beliefs that ResNet only works well for very deep networks, we found that even with 9 layers of CNNs, using identity mapping could significantly improve the performance for distantly-supervised relation extraction.

cs.CL↗

arXiv2017

"Liar, Liar Pants on Fire": A New Benchmark Dataset for Fake News Detection

Automatic fake news detection is a challenging problem in deception detection, and it has tremendous real-world political and social impacts. However, statistical approaches to combating fake news has been dramatically limited by the lack of labeled benchmark datasets. In this paper, we present liar: a new, publicly available dataset for fake news detection. We collected a decade-long, 12.8K manually labeled short statements in various contexts from PolitiFact.com, which provides detailed analysis report and links to source documents for each case. This dataset can be used for fact-checking research as well. Notably, this new dataset is an order of magnitude larger than previously largest public fake news datasets of similar type. Empirically, we investigate automatic fake news detection based on surface-level linguistic patterns. We have designed a novel, hybrid convolutional neural network to integrate meta-data with text. We show that this hybrid approach can improve a text-only deep learning model.

cs.CL↗

arXiv2014

Efficient Inference and Learning in a Large Knowledge Base: Reasoning with Extracted Information using a Locally Groundable First-Order Probabilistic Logic

One important challenge for probabilistic logics is reasoning with very large knowledge bases (KBs) of imperfect information, such as those produced by modern web-scale information extraction systems. One scalability problem shared by many probabilistic logics is that answering queries involves "grounding" the query---i.e., mapping it to a propositional representation---and the size of a "grounding" grows with database size. To address this bottleneck, we present a first-order probabilistic language called ProPPR in which that approximate "local groundings" can be constructed in time independent of database size. Technically, ProPPR is an extension to stochastic logic programs (SLPs) that is biased towards short derivations; it is also closely related to an earlier relational learning algorithm called the path ranking algorithm (PRA). We show that the problem of constructing proofs for this logic is related to computation of personalized PageRank (PPR) on a linearized version of the proof space, and using on this connection, we develop a proveably-correct approximate grounding scheme, based on the PageRank-Nibble algorithm. Building on this, we develop a fast and easily-parallelized weight-learning algorithm for ProPPR. In experiments, we show that learning for ProPPR is orders magnitude faster than learning for Markov logic networks; that allowing mutual recursion (joint learning) in KB inference leads to improvements in performance; and that ProPPR can learn weights for a mutually recursive program with hundreds of clauses, which define scores of interrelated predicates, over a KB containing one million entities.

cs.AI↗

arXiv2013

Programming with Personalized PageRank: A Locally Groundable First-Order Probabilistic Logic

In many probabilistic first-order representation systems, inference is performed by "grounding"---i.e., mapping it to a propositional representation, and then performing propositional inference. With a large database of facts, groundings can be very large, making inference and learning computationally expensive. Here we present a first-order probabilistic language which is well-suited to approximate "local" grounding: every query $Q$ can be approximately grounded with a small graph. The language is an extension of stochastic logic programs where inference is performed by a variant of personalized PageRank. Experimentally, we show that the approach performs well without weight learning on an entity resolution task; that supervised weight-learning improves accuracy; and that grounding time is independent of DB size. We also show that order-of-magnitude speedups are possible by parallelizing learning.

cs.AI↗