October 15, 2019

2028 words 10 mins read

Paper Group NANR 241

Paper Group NANR 241

Multi-object Tracking with Neural Gating Using Bilinear LSTM. Learning Scalar Adjective Intensity from Paraphrases. UWB at SemEval-2018 Task 10: Capturing Discriminative Attributes from Word Distributions. SemEval-2018 Task 9: Hypernym Discovery. TRAVERSAL at PARSEME Shared Task 2018: Identification of Verbal Multiword Expressions Using a Discrimin …

Multi-object Tracking with Neural Gating Using Bilinear LSTM

Title Multi-object Tracking with Neural Gating Using Bilinear LSTM
Authors Chanho Kim, Fuxin Li, James M. Rehg
Abstract In recent deep online and near-online multi-object tracking approaches, a difficulty has been to incorporate long-term appearance models to efficiently score object tracks under severe occlusion and multiple missing detections. In this paper, we propose a novel recurrent network model, the bilinear LSTM, in order to improve long-term appearance models via a recurrent network. Based on intuitions drawn from recursive least squares, bilinear LSTM stores building blocks of a linear predictor in its memory, which is then coupled with the input in a multiplicative manner, instead of the additive coupling in conventional LSTM approaches. Such coupling resembles an online learned classifier/regressor at each time step, which we have found to improve performances in using LSTM for appearance modeling. We also propose novel data augmentation approaches to efficiently train recurrent models that score object tracks on both appearance and motion. We train an LSTM that can score object tracks based on both appearance and motion and utilize it in a multiple hypothesis tracking framework. In experiments, we show that with our novel LSTM model, we achieved state-of-the-art performance on near-online multiple object tracking on the MOT 2016 and MOT 2017 benchmarks.
Tasks Data Augmentation, Multi-Object Tracking, Multiple Object Tracking, Object Tracking, Online Multi-Object Tracking
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Chanho_Kim_Multi-object_Tracking_with_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Chanho_Kim_Multi-object_Tracking_with_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/multi-object-tracking-with-neural-gating
Repo
Framework

Learning Scalar Adjective Intensity from Paraphrases

Title Learning Scalar Adjective Intensity from Paraphrases
Authors Anne Cocos, Skyler Wharton, Ellie Pavlick, Marianna Apidianaki, Chris Callison-Burch
Abstract Adjectives like {}warm{''}, {}hot{''}, and {}scalding{''} all describe temperature but differ in intensity. Understanding these differences between adjectives is a necessary part of reasoning about natural language. We propose a new paraphrase-based method to automatically learn the relative intensity relation that holds between a pair of scalar adjectives. Our approach analyzes over 36k adjectival pairs from the Paraphrase Database under the assumption that, for example, paraphrase pair {}really hot{''} {\textless}{–}{\textgreater} {}scalding{''} suggests that {}hot{''} {\textless} {}scalding{''}. We show that combining this paraphrase evidence with existing, complementary pattern- and lexicon-based approaches improves the quality of systems for automatically ordering sets of scalar adjectives and inferring the polarity of indirect answers to {}yes/no{''} questions.
Tasks Hypernym Discovery, Question Answering, Sentiment Analysis
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1202/
PDF https://www.aclweb.org/anthology/D18-1202
PWC https://paperswithcode.com/paper/learning-scalar-adjective-intensity-from
Repo
Framework

UWB at SemEval-2018 Task 10: Capturing Discriminative Attributes from Word Distributions

Title UWB at SemEval-2018 Task 10: Capturing Discriminative Attributes from Word Distributions
Authors Tom{'a}{\v{s}} Brychc{'\i}n, Tom{'a}{\v{s}} Hercig, Josef Steinberger, Michal Konkol
Abstract We present our UWB system for the task of capturing discriminative attributes at SemEval 2018. Given two words and an attribute, the system decides, whether this attribute is discriminative between the words or not. Assuming Distributional Hypothesis, i.e., a word meaning is related to the distribution across contexts, we introduce several approaches to compare word contextual information. We experiment with state-of-the-art semantic spaces and with simple co-occurrence statistics. We show the word distribution in the corpus has potential for detecting discriminative attributes. Our system achieves F1 score 72.1{%} and is ranked {#}4 among 26 submitted systems.
Tasks
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1153/
PDF https://www.aclweb.org/anthology/S18-1153
PWC https://paperswithcode.com/paper/uwb-at-semeval-2018-task-10-capturing
Repo
Framework

SemEval-2018 Task 9: Hypernym Discovery

Title SemEval-2018 Task 9: Hypernym Discovery
Authors Jose Camacho-Collados, Claudio Delli Bovi, Luis Espinosa-Anke, Sergio Oramas, Tommaso Pasini, Enrico Santus, Vered Shwartz, Roberto Navigli, Horacio Saggion
Abstract This paper describes the SemEval 2018 Shared Task on Hypernym Discovery. We put forward this task as a complementary benchmark for modeling hypernymy, a problem which has traditionally been cast as a binary classification task, taking a pair of candidate words as input. Instead, our reformulated task is defined as follows: given an input term, retrieve (or discover) its suitable hypernyms from a target corpus. We proposed five different subtasks covering three languages (English, Spanish, and Italian), and two specific domains of knowledge in English (Medical and Music). Participants were allowed to compete in any or all of the subtasks. Overall, a total of 11 teams participated, with a total of 39 different systems submitted through all subtasks. Data, results and further information about the task can be found at \url{https://competitions.codalab.org/competitions/17119}.
Tasks Hypernym Discovery, Natural Language Inference, Question Answering
Published 2018-06-01
URL https://www.aclweb.org/anthology/S18-1115/
PDF https://www.aclweb.org/anthology/S18-1115
PWC https://paperswithcode.com/paper/semeval-2018-task-9-hypernym-discovery
Repo
Framework

TRAVERSAL at PARSEME Shared Task 2018: Identification of Verbal Multiword Expressions Using a Discriminative Tree-Structured Model

Title TRAVERSAL at PARSEME Shared Task 2018: Identification of Verbal Multiword Expressions Using a Discriminative Tree-Structured Model
Authors Jakub Waszczuk
Abstract This paper describes a system submitted to the closed track of the PARSEME shared task (edition 1.1) on automatic identification of verbal multiword expressions (VMWEs). The system represents VMWE identification as a labeling task where one of two labels (MWE or not-MWE) must be predicted for each node in the dependency tree based on local context, including adjacent nodes and their labels. The system relies on multiclass logistic regression to determine the globally optimal labeling of a tree. The system ranked 1st in the general cross-lingual ranking of the closed track systems, according to both official evaluation measures: MWE-based F1 and token-based F1.
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4931/
PDF https://www.aclweb.org/anthology/W18-4931
PWC https://paperswithcode.com/paper/traversal-at-parseme-shared-task-2018
Repo
Framework

Systematic Error Analysis of the Stanford Question Answering Dataset

Title Systematic Error Analysis of the Stanford Question Answering Dataset
Authors Marc-Antoine Rondeau, T. J. Hazen
Abstract We analyzed the outputs of multiple question answering (QA) models applied to the Stanford Question Answering Dataset (SQuAD) to identify the core challenges for QA systems on this data set. Through an iterative process, challenging aspects were hypothesized through qualitative analysis of the common error cases. A classifier was then constructed to predict whether SQuAD test examples were likely to be difficult for systems to answer based on features associated with the hypothesized aspects. The classifier{'}s performance was used to accept or reject each aspect as an indicator of difficulty. With this approach, we ensured that our hypotheses were systematically tested and not simply accepted based on our pre-existing biases. Our explanations are not accepted based on human evaluation of individual examples. This process also enabled us to identify the primary QA strategy learned by the models, i.e., systems determined the acceptable answer type for a question and then selected the acceptable answer span of that type containing the highest density of words present in the question within its local vicinity in the passage.
Tasks Common Sense Reasoning, Machine Reading Comprehension, Question Answering, Reading Comprehension
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2602/
PDF https://www.aclweb.org/anthology/W18-2602
PWC https://paperswithcode.com/paper/systematic-error-analysis-of-the-stanford
Repo
Framework

Investigating Effective Parameters for Fine-tuning of Word Embeddings Using Only a Small Corpus

Title Investigating Effective Parameters for Fine-tuning of Word Embeddings Using Only a Small Corpus
Authors Kanako Komiya, Hiroyuki Shinnou
Abstract Fine-tuning is a popular method to achieve better performance when only a small target corpus is available. However, it requires tuning of a number of metaparameters and thus it might carry risk of adverse effect when inappropriate metaparameters are used. Therefore, we investigate effective parameters for fine-tuning when only a small target corpus is available. In the current study, we target at improving Japanese word embeddings created from a huge corpus. First, we demonstrate that even the word embeddings created from the huge corpus are affected by domain shift. After that, we investigate effective parameters for fine-tuning of the word embeddings using a small target corpus. We used perplexity of a language model obtained from a Long Short-Term Memory network to assess the word embeddings input into the network. The experiments revealed that fine-tuning sometimes give adverse effect when only a small target corpus is used and batch size is the most important parameter for fine-tuning. In addition, we confirmed that effect of fine-tuning is higher when size of a target corpus was larger.
Tasks Language Modelling, Word Embeddings
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-3408/
PDF https://www.aclweb.org/anthology/W18-3408
PWC https://paperswithcode.com/paper/investigating-effective-parameters-for-fine
Repo
Framework

Linguistic Features of Helpfulness in Automated Support for Creative Writing

Title Linguistic Features of Helpfulness in Automated Support for Creative Writing
Authors Melissa Roemmele, Andrew Gordon
Abstract We examine an emerging NLP application that supports creative writing by automatically suggesting continuing sentences in a story. The application tracks users{'} modifications to generated sentences, which can be used to quantify their {``}helpfulness{''} in advancing the story. We explore the task of predicting helpfulness based on automatically detected linguistic features of the suggestions. We illustrate this analysis on a set of user interactions with the application using an initial selection of features relevant to story generation. |
Tasks Grammatical Error Correction, Text Generation
Published 2018-06-01
URL https://www.aclweb.org/anthology/W18-1502/
PDF https://www.aclweb.org/anthology/W18-1502
PWC https://paperswithcode.com/paper/linguistic-features-of-helpfulness-in
Repo
Framework

A Taxonomy for In-depth Evaluation of Normalization for User Generated Content

Title A Taxonomy for In-depth Evaluation of Normalization for User Generated Content
Authors Rob van der Goot, Rik van Noord, Gertjan van Noord
Abstract
Tasks Grammatical Error Correction, Lexical Normalization, Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1109/
PDF https://www.aclweb.org/anthology/L18-1109
PWC https://paperswithcode.com/paper/a-taxonomy-for-in-depth-evaluation-of
Repo
Framework

Correction of OCR Word Segmentation Errors in Articles from the ACL Collection through Neural Machine Translation Methods

Title Correction of OCR Word Segmentation Errors in Articles from the ACL Collection through Neural Machine Translation Methods
Authors Vivi Nastase, Julian Hitschler
Abstract
Tasks Grammatical Error Correction, Keyword Extraction, Machine Translation, Optical Character Recognition, Relation Extraction
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1113/
PDF https://www.aclweb.org/anthology/L18-1113
PWC https://paperswithcode.com/paper/correction-of-ocr-word-segmentation-errors-in
Repo
Framework

A Computational Exploration of Exaggeration

Title A Computational Exploration of Exaggeration
Authors Enrica Troiano, Carlo Strapparava, G{"o}zde {"O}zbal, Serra Sinem Tekiro{\u{g}}lu
Abstract Several NLP studies address the problem of figurative language, but among non-literal phenomena, they have neglected exaggeration. This paper presents a first computational approach to this figure of speech. We explore the possibility to automatically detect exaggerated sentences. First, we introduce HYPO, a corpus containing overstatements (or hyperboles) collected on the web and validated via crowdsourcing. Then, we evaluate a number of models trained on HYPO, and bring evidence that the task of hyperbole identification can be successfully performed based on a small set of semantic features.
Tasks
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1367/
PDF https://www.aclweb.org/anthology/D18-1367
PWC https://paperswithcode.com/paper/a-computational-exploration-of-exaggeration
Repo
Framework

FooTweets: A Bilingual Parallel Corpus of World Cup Tweets

Title FooTweets: A Bilingual Parallel Corpus of World Cup Tweets
Authors Henny Sluyter-G{"a}thje, Pintu Lohar, Haithem Afli, Andy Way
Abstract
Tasks Machine Translation, Sentiment Analysis
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1422/
PDF https://www.aclweb.org/anthology/L18-1422
PWC https://paperswithcode.com/paper/footweets-a-bilingual-parallel-corpus-of
Repo
Framework

Morphology Injection for English-Malayalam Statistical Machine Translation

Title Morphology Injection for English-Malayalam Statistical Machine Translation
Authors Sreelekha S, Pushpak Bhattacharyya
Abstract
Tasks Machine Translation
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1413/
PDF https://www.aclweb.org/anthology/L18-1413
PWC https://paperswithcode.com/paper/morphology-injection-for-english-malayalam
Repo
Framework

An Evaluation Framework for Multimodal Interaction

Title An Evaluation Framework for Multimodal Interaction
Authors Nikhil Krishnaswamy, James Pustejovsky
Abstract
Tasks Gesture Recognition, Motion Capture
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1335/
PDF https://www.aclweb.org/anthology/L18-1335
PWC https://paperswithcode.com/paper/an-evaluation-framework-for-multimodal
Repo
Framework

3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare

Title 3D-RCNN: Instance-Level 3D Object Reconstruction via Render-and-Compare
Authors Abhijit Kundu, Yin Li, James M. Rehg
Abstract We present a fast inverse-graphics framework for instance-level 3D scene understanding. We train a deep convolutional network that learns to map image regions to the full 3D shape and pose of all object instances in the image. Our method produces a compact 3D representation of the scene, which can be readily used for applications like autonomous driving. Many traditional 2D vision outputs, like instance segmentations and depth-maps, can be obtained by simply rendering our output 3D scene model. We exploit class-specific shape priors by learning a low dimensional shape-space from collections of CAD models. We present novel representations of shape and pose, that strive towards better 3D equivariance and generalization. In order to exploit rich supervisory signals in the form of 2D annotations like segmentation, we propose a differentiable Render-and-Compare loss that allows 3D shape and pose to be learned with 2D supervision. We evaluate our method on the challenging real-world datasets of Pascal3D+ and KITTI, where we achieve state-of-the-art results.
Tasks 3D Object Reconstruction, Autonomous Driving, Object Reconstruction, Scene Understanding
Published 2018-06-01
URL http://openaccess.thecvf.com/content_cvpr_2018/html/Kundu_3D-RCNN_Instance-Level_3D_CVPR_2018_paper.html
PDF http://openaccess.thecvf.com/content_cvpr_2018/papers/Kundu_3D-RCNN_Instance-Level_3D_CVPR_2018_paper.pdf
PWC https://paperswithcode.com/paper/3d-rcnn-instance-level-3d-object
Repo
Framework
comments powered by Disqus