Abstract

It has been shown that transition-based methods can be used for syntactic word ordering and tree linearization, achieving significantly faster speed compared with traditional best-first methods. State-of-the-art transition-based models give competitive results on ab-stract word ordering and unlabeled tree lin-earization, but significantly worse results on labeled tree linearization. We demonstrate that the main cause for the performance bottle-neck is the sparsity of SHIFT transition actions rather than heavy pruning. To address this is-sue, we propose a modification to the standard transition-based feature structure, which reduces feature sparsity and allows look ahead features at a small cost to decoding efficiency.Our model gives the best reported accuracies on all benchmarks, yet still being over 30times faster compared with best-first-search.

Abstract

Community Question Answering (cQA) forums have become a popular medium for soliciting direct answers to specific questions of users from experts or other experienced users on a given topic. However, for a given question, users some-times have to sift through a large number of low-quality or irrelevant answers to find out the answer which satisfies their information need. To alleviate this, the problem of Answer Quality Prediction (AQP) aims to predict the quality of an answer posted in response to a forum question.Current AQP systems either learn models using - a) various hand-crafted features (HCF) or b) use deep learning (DL)techniques which automatically learn the required feature representations.In this paper, we propose a novel approach for AQP known as -“Deep Feature Fusion Network (DFFN)”which leverages the advantages of both hand-crafted features and deep learning based systems. Given a question-answer pair along with its metadata, DFFN independently - a) learns deep features using a Convolutional Neural Network (CNN) and b) computes hand-crafted features using various external resourcesand then combines them using a deep neural network trained to predict the final answer quality. DFFN achieves state-of-the-art performance on the standard SemEval-2015 andSemEval-2016 benchmark datasets and outperforms base-line approaches which individually employ either HCF or DL based techniques alone.

Abstract

Community Question Answering (cQA)services like Yahoo!Answers1, BaiduZhidao2, Quora3, StackOverflow4etc.provide a platform for interaction with experts and help users to obtain precise and accurate answers to their questions.The time lag between the user posting a question and receiving its answer could be reduced by retrieving similar historic questions from the cQA archives.The main challenge in this task is the “lexico-syntactic” gap between the current and the previous questions. In this paper, we pro-pose a novel approach called“Siamese Convolutional Neural Network for cQA(SCQA)”to find the semantic similarity between the current and the archived ques-tions.SCQA consist of twin convolutional neural networks with shared parameters and a contrastive loss function joining them. SCQA learns the similarity metric for question-question pairs by leveraging the question-answer pairs available in cQA forum archives. The model projects semantically similar question pairs nearer to each other and dissimilar question pairs farther away from each other in the semantic space. Experiments on large scale real-life “Yahoo! Answers” dataset reveals that SCQA outperforms current state-of-the-art approaches based on translation models, topic models and deep neural network based models which use non-shared parameters.

Abstract

In this paper we describe an end to end Neural Model for Named Entity Recognition (NER) which is based on Bi-Directional RNN-LSTM. Almost all NER systems for Hindi use Language Specific features and handcrafted rules with gazetteers. Our model is language independent and uses no domain specific features or any handcrafted rules. Our models rely on semantic information in the form of word vectors which are learnt by an unsupervised learning algorithm on an unannotated corpus. Our model attained state of the art performance in both English and Hindi without the use of any morphological analysis or without using gazetteers of any sort.

Abstract

Community Question Answering (cQA) forums have become a popular medium for soliciting answers to specific user questions from experts and experienced users in a given topic. However,for a given question, users sometimes have to sift through a large number of low-quality or irrelevant answers to find out the answer which satisfies their information need. To alleviate this,the problem of Answer Quality Prediction (AQP) aims to predict the quality of an answer posted in response to a forum question. Current AQP systems either learn models using - a) various hand-crafted features (HCF) or b) Deep Learning (DL) techniques which automatically learn the feature representations.In this paper, we propose a novel approach for AQP known as -“Deep Feature Fusion Network(DFFN)”which combines the advantages of both hand-crafted features and deep learning based systems. Given a question-answer pair along with its metadata, a DFFN architecture indepen-dently - a) learns features using the Deep Neural Network (DNN) and b) computes handcrafted features leveraging various external resources and then combines the musing a fully connected neural network trained to predict the quality of the given answer. DFFN is an end-end differen-tiable model and trained as a single system. We propose two different DFFN architectures which vary mainly in the way they model the input question/answer pair - a) DFFN-CNN which uses a Convolutional Neural Network (CNN) and b) DFFN-BLNA which uses a Bi-directional LSTMwith Neural Attention (BLNA). Both these proposed variants of DFFN (DFFN-CNN and DFFN-BLNA) achieve state-of-the-art performance on the standard SemEval-2015 and SemEval-2016benchmark datasets and outperforms baseline approaches which individually employ either HCFor DL based techniques alone.

Abstract

Today, a large amount of audio data is available on the web in the form of audiobooks, podcasts, video lectures, video blogs, news bulletins, etc. In addition, we can effortlessly record and store audio data such as a read, lecture, or impromptu speech on handheld devices. These data are rich in prosody and provide a plethora of voices to choose from, and their availability can significantly reduce the overhead of data preparation and help rapid building of synthetic voices. But, a few problems are associated with readily using this data such as (1) these audio files are generally long, and audio-transcription alignment is memory intensive; (2) precise corresponding transcriptions are unavailable, (3) many times, no transcriptions are available at all; (4) the audio may contain dis-fluencies and non-speech noises, since they are not specifically recorded for building synthetic voices; and (5) if we obtain automatic transcripts, they will not be error free. Earlier works on long audio alignment addressing the first and second issue generally preferred reasonable transcripts and mainly focused on (1) less manual intervention, (2) mispronunciation detection, and (3) segmentation error recovery. In this work, we use a large vocabulary public domain automatic speech recognition (ASR) system to obtain transcripts, followed by confidence measure-based data pruning which together address the five issues with the found data and also ensure the above three points. For proof of concept, we build voices in the English language using an audiobook (read speech) in a female voice from LibriVox and a lecture (spontaneous speech) in a male voice from Coursera, using both reference and hypotheses transcriptions, and evaluate them in terms of intelligibility and naturalness with the help of a perceptual listening test on the Blizzard 2013 corpus.

Abstract

Dynamic resource assignment is a common problem in multi-agent systems. We consider scenarios in which dynamic agents have preferences about assignments and the resources that can be assigned using online auctions. We study the trade-off between the following online auction properties: (i) truthfulness, (ii) expressiveness, (iii) efficiency, and (iv) average case performance. We theoretically and empirically compare four different online auctions: (i) Arrival Priority Serial Dictatorship, (ii) Split Dynamic VCG, (iii) e-Action, and (iv) Online Ranked Competition Auction. The latter is a novel design based on the competitive secretary problem. We show that, in addition to truthfulness and algorithmic efficiency, the degree of competition also plays an important role in selecting the best algorithm for a given context

Abstract

We consider a general crowdsourcing setting with strategic workers whose qualities are unknown and design a multiarmed bandit (MAB) mechanism, CrowdUCB, which is deterministic, regret minimizing, and offers immediate payments to the workers. The problem involves sequentially selecting workers to process tasks in order to maximize the social welfare while learning the qualities of the strategic workers (strategic about their costs). Existing MAB mechanisms are either: (a) deterministic which potentially cause significant loss in social welfare, or (b) randomized which typically lead to high variance in payments. CrowdUCB completely addresses the above problems with the following features: (i) offers deterministic payments, (ii) achieves logarithmic regret in social welfare, (iii) renders allocations more effective by allocating blocks of tasks to a worker instead of a single task, and (iv) offers payment to a worker immediately upon completion of an assigned block of tasks. CrowdUCB is a mechanism with learning that learns the qualities of the workers while eliciting their true costs, irrespective of whether or not the workers know their own qualities. We show that CrowdUCB is ex-post individually rational (EPIR) and ex-post incentive compatible (EPIC) when the workers do not know their own qualities and when they update their beliefs in sync with the requester. When the workers know their own qualities, CrowdUCB is EPIR and ε−EPIC where ε is sub-linear in terms of the number of tasks.

Abstract

Crowdfunding is emerging as a popular means to generate funding from citizens for public projects. This is popularly known as civic crowdfunding. In this paper, we focus on crowdfunding public projects with provision point: these are projects in which contributions must reach a predetermined threshold in order for the project to be provisioned. On web based civic crowdfunding platforms, the success of crowdfunding public projects has been somewhat mixed. In this paper, our objective is to design a mechanism that improves the success of crowdfunding public projects. In particular, we propose a class of mechanisms for crowdfunding platforms with sequentially arriving agents. This class of mechanisms induces an extensive form game for agents arriving on the platform and we show that the game has a non-empty set of sub-game perfect equilibria at which the project is fully funded. We call this new class of mechanisms Provision Point Mechanism with Securities (PPS). The novelty of PPS lies in the use of a prediction market to incentivize agents to contribute in proportion to their true value for the project and to contribute as soon as they arrive at the crowdfunding platform. Different variations of PPS are possible depending on the underlying prediction market. In this paper, we use a cost function (or equivalently, scoring rule) based prediction market; in fact, we specify the requirements that a cost function should satisfy to be used in PPS. We study and compare two specific instances of PPS: (1) Logarithmic Market Scoring Rule based and (2) Quadratic Scoring Rule based. We also discuss the considerations that should guide the choice of the cost function when deploying our mechanism on crowdfunding platforms

Abstract

Motivated by web based marketplaces where the number of bidders in an auction is a small subset of potential bidders, we consider auctions where the auctioneer (seller) wishes to increase her revenue and/or social welfare by expanding the pool of participants. To this end, the seller crowdsources this task by offering a referral bonus to the participants. With the introduction of referrals, a participant can now bid and/or refer other agents to bid. We call our auctions crowdsourced referral auctions since the seller exploits the knowledge that agents have about other potential participants in the crowd. We introduce the notion of price of locality to quantify the loss in social welfare due to restricted (local) access of the seller to potential bidders. We introduce the notion of Crowdsourced Referral Auction Mechanisms (CRAMs), propose two novel versions of CRAMs and study the induced referral game in the canonical context of an auction for selling a single indivisible item. We compare their revenue performance and game theoretic properties and show that both of them outperform the baseline auction without referrals