October 16, 2019

1817 words 9 mins read

Paper Group NANR 31

Paper Group NANR 31

Praaline: An Open-Source System for Managing, Annotating, Visualising and Analysing Speech Corpora. Sampling Algebraic Varieties for Robust Camera Autocalibration. Chain of Reasoning for Visual Question Answering. Acoustic Word Disambiguation with Phonogical Features in Danish ASR. A Japanese Corpus for Analyzing Customer Loyalty Information. On th …

Praaline: An Open-Source System for Managing, Annotating, Visualising and Analysing Speech Corpora

Title Praaline: An Open-Source System for Managing, Annotating, Visualising and Analysing Speech Corpora
Authors George Christodoulides
Abstract In this system demonstration we present the latest developments of Praaline, an open-source software system for constituting and managing, manually and automatically annotating, visualising and analysing spoken language and multimodal corpora. We review the system{'}s functionality and design architecture, present current use cases and directions for future development.
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-4019/
PDF https://www.aclweb.org/anthology/P18-4019
PWC https://paperswithcode.com/paper/praaline-an-open-source-system-for-managing
Repo
Framework

Sampling Algebraic Varieties for Robust Camera Autocalibration

Title Sampling Algebraic Varieties for Robust Camera Autocalibration
Authors Danda Pani Paudel, Luc Van Gool
Abstract This paper addresses the problem of robustly autocalibrating a moving camera with constant intrinsics. The proposed calibration method uses the Branch-and-Bound (BnB) search paradigm to maximize the consensus of the polynomials. These polynomials are parameterized by the entries of, either the Dual Image of Absolute Conic (DIAC) or the Plane-at-Infinity (PaI). During the BnB search, we exploit the theory of sampling algebraic varieties, to test the positivity of any polynomial within a parameter’s interval, i.e. outliers with certainty. The search process explores the space of exact parameters (i.e the entries of DIAC or PaI), benefits from the solution of a local method, and converges to the solution satisfied by the largest number of polynomials. Given many polynomials on the sought parameters (with possibly overwhelmingly many from outlier measurements), their consensus for calibration is searched for two cases: simplified Kruppa’s equations and Modulus constraints, expressed in DIAC and PaI, resp. Our approach yields outstanding results in terms of robustness and optimality.
Tasks Calibration
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Danda_Pani_Paudel_Sampling_Algebraic_Varieties_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Danda_Pani_Paudel_Sampling_Algebraic_Varieties_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/sampling-algebraic-varieties-for-robust
Repo
Framework

Chain of Reasoning for Visual Question Answering

Title Chain of Reasoning for Visual Question Answering
Authors Chenfei Wu, Jinlai Liu, Xiaojie Wang, Xuan Dong
Abstract Reasoning plays an essential role in Visual Question Answering (VQA). Multi-step and dynamic reasoning is often necessary for answering complex questions. For example, a question “What is placed next to the bus on the right of the picture?” talks about a compound object “bus on the right,” which is generated by the relation <bus, on the right of, picture>. Furthermore, a new relation including this compound object <sign, next to, bus on the right> is then required to infer the answer. However, previous methods support either one-step or static reasoning, without updating relations or generating compound objects. This paper proposes a novel reasoning model for addressing these problems. A chain of reasoning (CoR) is constructed for supporting multi-step and dynamic reasoning on changed relations and objects. In detail, iteratively, the relational reasoning operations form new relations between objects, and the object refining operations generate new compound objects from relations. We achieve new state-of-the-art results on four publicly available datasets. The visualization of the chain of reasoning illustrates the progress that the CoR generates new compound objects that lead to the answer of the question step by step.
Tasks Question Answering, Relational Reasoning, Visual Question Answering
Published 2018-12-01
URL http://papers.nips.cc/paper/7311-chain-of-reasoning-for-visual-question-answering
PDF http://papers.nips.cc/paper/7311-chain-of-reasoning-for-visual-question-answering.pdf
PWC https://paperswithcode.com/paper/chain-of-reasoning-for-visual-question
Repo
Framework

Acoustic Word Disambiguation with Phonogical Features in Danish ASR

Title Acoustic Word Disambiguation with Phonogical Features in Danish ASR
Authors Andreas S{\o}eborg Kirkedal
Abstract Phonological features can indicate word class and we can use word class information to disambiguate both homophones and homographs in automatic speech recognition (ASR). We show Danish st{\o}d can be predicted from speech and used to improve ASR. We discover which acoustic features contain the signal of st{\o}d, how to use these features to predict st{\o}d and how we can make use of st{\o}d and st{\o}dpredictive acoustic features to improve overall ASR accuracy and decoding speed. In the process, we discover acoustic features that are novel to the phonetic characterisation of st{\o}d.
Tasks Speech Recognition
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-5803/
PDF https://www.aclweb.org/anthology/W18-5803
PWC https://paperswithcode.com/paper/acoustic-word-disambiguation-with-phonogical
Repo
Framework

A Japanese Corpus for Analyzing Customer Loyalty Information

Title A Japanese Corpus for Analyzing Customer Loyalty Information
Authors Yiou Wang, Takuji Tahara
Abstract
Tasks Opinion Mining, Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1421/
PDF https://www.aclweb.org/anthology/L18-1421
PWC https://paperswithcode.com/paper/a-japanese-corpus-for-analyzing-customer
Repo
Framework

On the Relation between Linguistic Typology and (Limitations of) Multilingual Language Modeling

Title On the Relation between Linguistic Typology and (Limitations of) Multilingual Language Modeling
Authors Daniela Gerz, Ivan Vuli{'c}, Edoardo Maria Ponti, Roi Reichart, Anna Korhonen
Abstract A key challenge in cross-lingual NLP is developing general language-independent architectures that are equally applicable to any language. However, this ambition is largely hampered by the variation in structural and semantic properties, i.e. the typological profiles of the world{'}s languages. In this work, we analyse the implications of this variation on the language modeling (LM) task. We present a large-scale study of state-of-the art n-gram based and neural language models on 50 typologically diverse languages covering a wide variety of morphological systems. Operating in the full vocabulary LM setup focused on word-level prediction, we demonstrate that a coarse typology of morphological systems is predictive of absolute LM performance. Moreover, fine-grained typological features such as exponence, flexivity, fusion, and inflectional synthesis are borne out to be responsible for the proliferation of low-frequency phenomena which are organically difficult to model by statistical architectures, or for the meaning ambiguity of character n-grams. Our study strongly suggests that these features have to be taken into consideration during the construction of next-level language-agnostic LM architectures, capable of handling morphologically complex languages such as Tamil or Korean.
Tasks Language Modelling
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1029/
PDF https://www.aclweb.org/anthology/D18-1029
PWC https://paperswithcode.com/paper/on-the-relation-between-linguistic-typology
Repo
Framework

The First 100 Days: A Corpus Of Political Agendas on Twitter

Title The First 100 Days: A Corpus Of Political Agendas on Twitter
Authors Nathan Green, Septina Larasati
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1441/
PDF https://www.aclweb.org/anthology/L18-1441
PWC https://paperswithcode.com/paper/the-first-100-days-a-corpus-of-political
Repo
Framework

An Information-Providing Closed-Domain Human-Agent Interaction Corpus

Title An Information-Providing Closed-Domain Human-Agent Interaction Corpus
Authors Jelte van Waterschoot, Guillaume Dubuisson Duplessis, Lorenzo Gatti, Merijn Bruijnes, Dirk Heylen
Abstract
Tasks Information Retrieval
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1435/
PDF https://www.aclweb.org/anthology/L18-1435
PWC https://paperswithcode.com/paper/an-information-providing-closed-domain-human
Repo
Framework

Cyclegen: Cyclic consistency based product review generator from attributes

Title Cyclegen: Cyclic consistency based product review generator from attributes
Authors Vasu Sharma, Harsh Sharma, Ankita Bishnu, Labhesh Patel
Abstract In this paper we present an automatic review generator system which can generate personalized reviews based on the user identity, product identity and designated rating the user wishes to allot to the review. We combine this with a sentiment analysis system which performs the complimentary task of assigning ratings to reviews based purely on the textual content of the review. We introduce an additional loss term to ensure cyclic consistency of the sentiment rating of the generated review with the conditioning rating used to generate the review. The introduction of this new loss term constraints the generation space while forcing it to generate reviews adhering better to the requested rating. The use of {`}soft{'} generation and cyclic consistency allows us to train our model in an end to end fashion. We demonstrate the working of our model on product reviews from Amazon dataset. |
Tasks Sentiment Analysis, Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6552/
PDF https://www.aclweb.org/anthology/W18-6552
PWC https://paperswithcode.com/paper/cyclegen-cyclic-consistency-based-product
Repo
Framework

Derivative Estimation in Random Design

Title Derivative Estimation in Random Design
Authors Yu Liu, Kris De Brabanter
Abstract We propose a nonparametric derivative estimation method for random design without having to estimate the regression function. The method is based on a variance-reducing linear combination of symmetric difference quotients. First, we discuss the special case of uniform random design and establish the estimator’s asymptotic properties. Secondly, we generalize these results for any distribution of the dependent variable and compare the proposed estimator with popular estimators for derivative estimation such as local polynomial regression and smoothing splines.
Tasks
Published 2018-12-01
URL http://papers.nips.cc/paper/7604-derivative-estimation-in-random-design
PDF http://papers.nips.cc/paper/7604-derivative-estimation-in-random-design.pdf
PWC https://paperswithcode.com/paper/derivative-estimation-in-random-design
Repo
Framework

Evaluation of Automatic Formant Trackers

Title Evaluation of Automatic Formant Trackers
Authors Florian Schiel, Thomas Zitzelsberger
Abstract
Tasks Speaker Identification, Speaker Recognition
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1449/
PDF https://www.aclweb.org/anthology/L18-1449
PWC https://paperswithcode.com/paper/evaluation-of-automatic-formant-trackers
Repo
Framework

RtGender: A Corpus for Studying Differential Responses to Gender

Title RtGender: A Corpus for Studying Differential Responses to Gender
Authors Rob Voigt, David Jurgens, Vinodkumar Prabhakaran, Dan Jurafsky, Yulia Tsvetkov
Abstract
Tasks Text Generation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1445/
PDF https://www.aclweb.org/anthology/L18-1445
PWC https://paperswithcode.com/paper/rtgender-a-corpus-for-studying-differential
Repo
Framework

Neural Task Graph Execution

Title Neural Task Graph Execution
Authors Sungryull Sohn, Junhyuk Oh, Honglak Lee
Abstract In order to develop a scalable multi-task reinforcement learning (RL) agent that is able to execute many complex tasks, this paper introduces a new RL problem where the agent is required to execute a given task graph which describes a set of subtasks and dependencies among them. Unlike existing approaches which explicitly describe what the agent should do, our problem only describes properties of subtasks and relationships between them, which requires the agent to perform a complex reasoning to find the optimal subtask to execute. To solve this problem, we propose a neural task graph solver (NTS) which encodes the task graph using a recursive neural network. To overcome the difficulty of training, we propose a novel non-parametric gradient-based policy that performs back-propagation over a differentiable form of the task graph to compute the influence of each subtask on the other subtasks. Our NTS is pre-trained to approximate the proposed gradient-based policy and fine-tuned through actor-critic method. The experimental results on a 2D visual domain show that our method to pre-train from the gradient-based policy significantly improves the performance of NTS. We also demonstrate that our agent can perform a complex reasoning to find the optimal way of executing the task graph and generalize well to unseen task graphs. In addition, we compare our agent with a Monte-Carlo Tree Search (MCTS) method showing that our method is much more efficient than MCTS, and the performance of our agent can be further improved by combining with MCTS. The demo video is available at https://youtu.be/e_ZXVS5VutM.
Tasks
Published 2018-01-01
URL https://openreview.net/forum?id=B1NOXfWR-
PDF https://openreview.net/pdf?id=B1NOXfWR-
PWC https://paperswithcode.com/paper/neural-task-graph-execution
Repo
Framework

Learner Corpus Anonymization in the Age of GDPR: Insights from the Creation of a Learner Corpus of Swedish

Title Learner Corpus Anonymization in the Age of GDPR: Insights from the Creation of a Learner Corpus of Swedish
Authors Be{'a}ta Megyesi, Lena Granstedt, Sofia Johansson, Julia Prentice, Dan Ros{'e}n, Carl-Johan Schenstr{"o}m, Gunl{"o}g Sundberg, Mats Wir{'e}n, Elena Volodina
Abstract
Tasks Language Acquisition
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-7106/
PDF https://www.aclweb.org/anthology/W18-7106
PWC https://paperswithcode.com/paper/learner-corpus-anonymization-in-the-age-of
Repo
Framework

The Niki and Julie Corpus: Collaborative Multimodal Dialogues between Humans, Robots, and Virtual Agents

Title The Niki and Julie Corpus: Collaborative Multimodal Dialogues between Humans, Robots, and Virtual Agents
Authors Ron Artstein, Jill Boberg, Alesia Gainer, Jonathan Gratch, Emmanuel Johnson, Anton Leuski, Gale Lucas, David Traum
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1463/
PDF https://www.aclweb.org/anthology/L18-1463
PWC https://paperswithcode.com/paper/the-niki-and-julie-corpus-collaborative
Repo
Framework
comments powered by Disqus