Paper Group NANR 32
Dichromatic Model Based Temporal Color Constancy for AC Light Sources. Language Modeling with Shared Grammar. Better Generalization with On-the-fly Dataset Denoising. Entropy as a Proxy for Gap Complexity in Open Cloze Tests. The Second Multilingual Surface Realisation Shared Task (SR’19): Overview and Evaluation Results. KGPChamps at SemEval-2019 …
Dichromatic Model Based Temporal Color Constancy for AC Light Sources
Title | Dichromatic Model Based Temporal Color Constancy for AC Light Sources |
Authors | Jun-Sang Yoo, Jong-Ok Kim |
Abstract | Existing dichromatic color constancy approach commonly requires a number of spatial pixels which have high specularity. In this paper, we propose a novel approach to estimate the illuminant chromaticity of AC light source using high-speed camera. We found that the temporal observations of an image pixel at a fixed location distribute on an identical dichromatic plane. Instead of spatial pixels with high specularity, multiple temporal samples of a pixel are exploited to determine AC pixels for dichromatic plane estimation, whose pixel intensity is sinusoidally varying well. A dichromatic plane is calculated per each AC pixel, and illuminant chromaticity is determined by the intersection of dichromatic planes. From multiple dichromatic planes, an optimal illuminant is estimated with a novel MAP framework. It is shown that the proposed method outperforms both existing dichromatic based methods and temporal color constancy methods, irrespective of the amount of specularity. |
Tasks | Color Constancy |
Published | 2019-06-01 |
URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Yoo_Dichromatic_Model_Based_Temporal_Color_Constancy_for_AC_Light_Sources_CVPR_2019_paper.html |
http://openaccess.thecvf.com/content_CVPR_2019/papers/Yoo_Dichromatic_Model_Based_Temporal_Color_Constancy_for_AC_Light_Sources_CVPR_2019_paper.pdf | |
PWC | https://paperswithcode.com/paper/dichromatic-model-based-temporal-color |
Repo | |
Framework | |
Language Modeling with Shared Grammar
Title | Language Modeling with Shared Grammar |
Authors | Yuyu Zhang, Le Song |
Abstract | Sequential recurrent neural networks have achieved superior performance on language modeling, but overlook the structure information in natural language. Recent works on structure-aware models have shown promising results on language modeling. However, how to incorporate structure knowledge on corpus without syntactic annotations remains an open problem. In this work, we propose neural variational language model (NVLM), which enables the sharing of grammar knowledge among different corpora. Experimental results demonstrate the effectiveness of our framework on two popular benchmark datasets. With the help of shared grammar, our language model converges significantly faster to a lower perplexity on new training corpus. |
Tasks | Language Modelling |
Published | 2019-07-01 |
URL | https://www.aclweb.org/anthology/P19-1437/ |
https://www.aclweb.org/anthology/P19-1437 | |
PWC | https://paperswithcode.com/paper/language-modeling-with-shared-grammar |
Repo | |
Framework | |
Better Generalization with On-the-fly Dataset Denoising
Title | Better Generalization with On-the-fly Dataset Denoising |
Authors | Jiaming Song, Tengyu Ma, Michael Auli, Yann Dauphin |
Abstract | Memorization in over-parameterized neural networks can severely hurt generalization in the presence of mislabeled examples. However, mislabeled examples are to hard avoid in extremely large datasets. We address this problem using the implicit regularization effect of stochastic gradient descent with large learning rates, which we find to be able to separate clean and mislabeled examples with remarkable success using loss statistics. We leverage this to identify and on-the-fly discard mislabeled examples using a threshold on their losses. This leads to On-the-fly Data Denoising (ODD), a simple yet effective algorithm that is robust to mislabeled examples, while introducing almost zero computational overhead. Empirical results demonstrate the effectiveness of ODD on several datasets containing artificial and real-world mislabeled examples. |
Tasks | Denoising |
Published | 2019-05-01 |
URL | https://openreview.net/forum?id=HyGDdsCcFQ |
https://openreview.net/pdf?id=HyGDdsCcFQ | |
PWC | https://paperswithcode.com/paper/better-generalization-with-on-the-fly-dataset |
Repo | |
Framework | |
Entropy as a Proxy for Gap Complexity in Open Cloze Tests
Title | Entropy as a Proxy for Gap Complexity in Open Cloze Tests |
Authors | Mariano Felice, Paula Buttery |
Abstract | This paper presents a pilot study of entropy as a measure of gap complexity in open cloze tests aimed at learners of English. Entropy is used to quantify the information content in each gap, which can be used to estimate complexity. Our study shows that average gap entropy correlates positively with proficiency levels while individual gap entropy can capture contextual complexity. To the best of our knowledge, this is the first unsupervised information-theoretical approach to evaluating the quality of cloze tests. |
Tasks | |
Published | 2019-09-01 |
URL | https://www.aclweb.org/anthology/R19-1037/ |
https://www.aclweb.org/anthology/R19-1037 | |
PWC | https://paperswithcode.com/paper/entropy-as-a-proxy-for-gap-complexity-in-open |
Repo | |
Framework | |
The Second Multilingual Surface Realisation Shared Task (SR’19): Overview and Evaluation Results
Title | The Second Multilingual Surface Realisation Shared Task (SR’19): Overview and Evaluation Results |
Authors | Simon Mille, Anja Belz, Bernd Bohnet, Yvette Graham, Leo Wanner |
Abstract | We report results from the SR{'}19 Shared Task, the second edition of a multilingual surface realisation task organised as part of the EMNLP{'}19 Workshop on Multilingual Surface Realisation. As in SR{'}18, the shared task comprised two tracks with different levels of complexity: (a) a shallow track where the inputs were full UD structures with word order information removed and tokens lemmatised; and (b) a deep track where additionally, functional words and morphological information were removed. The shallow track was offered in eleven, and the deep track in three languages. Systems were evaluated (a) automatically, using a range of intrinsic metrics, and (b) by human judges in terms of readability and meaning similarity. This report presents the evaluation results, along with descriptions of the SR{'}19 tracks, data and evaluation methods. For full descriptions of the participating systems, please see the separate system reports elsewhere in this volume. |
Tasks | |
Published | 2019-11-01 |
URL | https://www.aclweb.org/anthology/D19-6301/ |
https://www.aclweb.org/anthology/D19-6301 | |
PWC | https://paperswithcode.com/paper/the-second-multilingual-surface-realisation |
Repo | |
Framework | |
KGPChamps at SemEval-2019 Task 3: A deep learning approach to detect emotions in the dialog utterances.
Title | KGPChamps at SemEval-2019 Task 3: A deep learning approach to detect emotions in the dialog utterances. |
Authors | Jasabanta Patro, Nitin Choudhary, Kalpit Chittora, Animesh Mukherjee |
Abstract | This paper describes our approach to solve \textit{Semeval task 3: EmoContext}; where, given a textual dialogue i.e. a user utterance along with two turns of context, we have to classify the emotion associated with the utterance as one of the following emotion classes: \textit{Happy, Sad, Angry} or \textit{Others}. To solve this problem, we experiment with different deep learning models ranging from simple bidirectional LSTM (Long and short term memory) model to comparatively complex attention model. We also experiment with word embedding conceptnet along with word embedding generated from bi-directional LSTM taking input characters. We fine-tune different parameters and hyper-parameters associated with each of our models and report the value of evaluating measure i.e. micro precision along with class wise precision, recall and F1-score of each system. We report the bidirectional LSTM model, along with the input word embedding as the concatenation of word embedding generated from bidirectional LSTM for word characters and conceptnet embedding, as the best performing model with a highest micro-F1 score of 0.7261. We also report class wise precision, recall, and f1-score of best performing model along with other models that we have experimented with. |
Tasks | |
Published | 2019-06-01 |
URL | https://www.aclweb.org/anthology/S19-2040/ |
https://www.aclweb.org/anthology/S19-2040 | |
PWC | https://paperswithcode.com/paper/kgpchamps-at-semeval-2019-task-3-a-deep |
Repo | |
Framework | |
Two-Timescale Networks for Nonlinear Value Function Approximation
Title | Two-Timescale Networks for Nonlinear Value Function Approximation |
Authors | Wesley Chung, Somjit Nath, Ajin Joseph, Martha White |
Abstract | A key component for many reinforcement learning agents is to learn a value function, either for policy evaluation or control. Many of the algorithms for learning values, however, are designed for linear function approximation—with a fixed basis or fixed representation. Though there have been a few sound extensions to nonlinear function approximation, such as nonlinear gradient temporal difference learning, these methods have largely not been adopted, eschewed in favour of simpler but not sound methods like temporal difference learning and Q-learning. In this work, we provide a two-timescale network (TTN) architecture that enables linear methods to be used to learn values, with a nonlinear representation learned at a slower timescale. The approach facilitates the use of algorithms developed for the linear setting, such as data-efficient least-squares methods, eligibility traces and the myriad of recently developed linear policy evaluation algorithms, to provide nonlinear value estimates. We prove convergence for TTNs, with particular care given to ensure convergence of the fast linear component under potentially dependent features provided by the learned representation. We empirically demonstrate the benefits of TTNs, compared to other nonlinear value function approximation algorithms, both for policy evaluation and control. |
Tasks | Q-Learning |
Published | 2019-05-01 |
URL | https://openreview.net/forum?id=rJleN20qK7 |
https://openreview.net/pdf?id=rJleN20qK7 | |
PWC | https://paperswithcode.com/paper/two-timescale-networks-for-nonlinear-value |
Repo | |
Framework | |
Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally
Title | Facial Emotion Distribution Learning by Exploiting Low-Rank Label Correlations Locally |
Authors | Xiuyi Jia, Xiang Zheng, Weiwei Li, Changqing Zhang, Zechao Li |
Abstract | Emotion recognition from facial expressions is an interesting and challenging problem and has attracted much attention in recent years. Substantial previous research has only been able to address the ambiguity of “what describes the expression”, which assumes that each facial expression is associated with one or more predefined affective labels while ignoring the fact that multiple emotions always have different intensities in a single picture. Therefore, to depict facial expressions more accurately, this paper adopts a label distribution learning approach for emotion recognition that can address the ambiguity of “how to describe the expression” and proposes an emotion distribution learning method that exploits label correlations locally. Moreover, a local low-rank structure is employed to capture the local label correlations implicitly. Experiments on benchmark facial expression datasets demonstrate that our method can better address the emotion distribution recognition problem than state-of-the-art methods. |
Tasks | Emotion Recognition |
Published | 2019-06-01 |
URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Jia_Facial_Emotion_Distribution_Learning_by_Exploiting_Low-Rank_Label_Correlations_Locally_CVPR_2019_paper.html |
http://openaccess.thecvf.com/content_CVPR_2019/papers/Jia_Facial_Emotion_Distribution_Learning_by_Exploiting_Low-Rank_Label_Correlations_Locally_CVPR_2019_paper.pdf | |
PWC | https://paperswithcode.com/paper/facial-emotion-distribution-learning-by |
Repo | |
Framework | |
SAO WMT19 Test Suite: Machine Translation of Audit Reports
Title | SAO WMT19 Test Suite: Machine Translation of Audit Reports |
Authors | Tereza Vojt{\v{e}}chov{'a}, Michal Nov{'a}k, Milo{\v{s}} Klou{\v{c}}ek, Ond{\v{r}}ej Bojar |
Abstract | This paper describes a machine translation test set of documents from the auditing domain and its use as one of the {``}test suites{''} in the WMT19 News Translation Task for translation directions involving Czech, English and German. Our evaluation suggests that current MT systems optimized for the general news domain can perform quite well even in the particular domain of audit reports. The detailed manual evaluation however indicates that deep factual knowledge of the domain is necessary. For the naked eye of a non-expert, translations by many systems seem almost perfect and automatic MT evaluation with one reference is practically useless for considering these details. Furthermore, we show on a sample document from the domain of agreements that even the best systems completely fail in preserving the semantics of the agreement, namely the identity of the parties. | |
Tasks | Machine Translation |
Published | 2019-08-01 |
URL | https://www.aclweb.org/anthology/W19-5355/ |
https://www.aclweb.org/anthology/W19-5355 | |
PWC | https://paperswithcode.com/paper/sao-wmt19-test-suite-machine-translation-of |
Repo | |
Framework | |
Identifying Linguistic Areas for Geolocation
Title | Identifying Linguistic Areas for Geolocation |
Authors | Tommaso Fornaciari, Dirk Hovy |
Abstract | Geolocating social media posts relies on the assumption that language carries sufficient geographic information. However, locations are usually given as continuous latitude/longitude tuples, so we first need to define discrete geographic regions that can serve as labels. Most studies use some form of clustering to discretize the continuous coordinates (Han et al., 2016). However, the resulting regions do not always correspond to existing linguistic areas. Consequently, accuracy at 100 miles tends to be good, but degrades for finer-grained distinctions, when different linguistic regions get lumped together. We describe a new algorithm, Point-to-City (P2C), an iterative k-d tree-based method for clustering geographic coordinates and associating them with towns. We create three sets of labels at different levels of granularity, and compare performance of a state-of-the-art geolocation model trained and tested with P2C labels to one with regular k-d tree labels. Even though P2C results in substantially more labels than the baseline, model accuracy increases significantly over using traditional labels at the fine-grained level, while staying comparable at 100 miles. The results suggest that identifying meaningful linguistic areas is crucial for improving geolocation at a fine-grained level. |
Tasks | |
Published | 2019-11-01 |
URL | https://www.aclweb.org/anthology/D19-5530/ |
https://www.aclweb.org/anthology/D19-5530 | |
PWC | https://paperswithcode.com/paper/identifying-linguistic-areas-for-geolocation |
Repo | |
Framework | |
AttentiveChecker: A Bi-Directional Attention Flow Mechanism for Fact Verification
Title | AttentiveChecker: A Bi-Directional Attention Flow Mechanism for Fact Verification |
Authors | Santosh Tokala, Vishal G, Avirup Saha, Niloy Ganguly |
Abstract | The recently released FEVER dataset provided benchmark results on a fact-checking task in which given a factual claim, the system must extract textual evidence (sets of sentences from Wikipedia pages) that support or refute the claim. In this paper, we present a completely task-agnostic pipelined system, AttentiveChecker, consisting of three homogeneous Bi-Directional Attention Flow (BIDAF) networks, which are multi-layer hierarchical networks that represent the context at different levels of granularity. We are the first to apply to this task a bi-directional attention flow mechanism to obtain a query-aware context representation without early summarization. AttentiveChecker can be used to perform document retrieval, sentence selection, and claim verification. Experiments on the FEVER dataset indicate that AttentiveChecker is able to achieve the state-of-the-art results on the FEVER test set. |
Tasks | |
Published | 2019-06-01 |
URL | https://www.aclweb.org/anthology/N19-1230/ |
https://www.aclweb.org/anthology/N19-1230 | |
PWC | https://paperswithcode.com/paper/attentivechecker-a-bi-directional-attention |
Repo | |
Framework | |
Towards Adaptive Text Summarization: How Does Compression Rate Affect Summary Readability of L2 Texts?
Title | Towards Adaptive Text Summarization: How Does Compression Rate Affect Summary Readability of L2 Texts? |
Authors | Tatiana Vodolazova, Elena Lloret |
Abstract | This paper addresses the problem of readability of automatically generated summaries in the context of second language learning. For this we experimented with a new corpus of level-annotated simplified English texts. The texts were summarized using a total of 7 extractive and abstractive summarization systems with compression rates of 20{%}, 40{%}, 60{%} and 80{%}. We analyzed the generated summaries in terms of lexical, syntactic and length-based features of readability, and concluded that summary complexity depends on the compression rate, summarization technique and the nature of the summarized corpus. Our experiments demonstrate the importance of choosing appropriate summarization techniques that align with user{'}s needs and language proficiency. |
Tasks | Abstractive Text Summarization, Text Summarization |
Published | 2019-09-01 |
URL | https://www.aclweb.org/anthology/R19-1145/ |
https://www.aclweb.org/anthology/R19-1145 | |
PWC | https://paperswithcode.com/paper/towards-adaptive-text-summarization-how-does |
Repo | |
Framework | |
SolomonLab at SemEval-2019 Task 8: Question Factuality and Answer Veracity Prediction in Community Forums
Title | SolomonLab at SemEval-2019 Task 8: Question Factuality and Answer Veracity Prediction in Community Forums |
Authors | Ankita Gupta, Sudeep Kumar Sahoo, Divya Prakash, Rohit R.R, Vertika Srivastava, Yeon Hyang Kim |
Abstract | We describe our system for SemEval-2019, Task 8 on {``}Fact-Checking in Community Question Answering Forums (cQA){''}. cQA forums are very prevalent nowadays, as they provide an effective means for communities to share knowledge. Unfortunately, this shared information is not always factual and fact-verified. In this task, we aim to identify factual questions posted on cQA and verify the veracity of answers to these questions. Our approach relies on data augmentation and aggregates cues from several dimensions such as semantics, linguistics, syntax, writing style and evidence obtained from trusted external sources. In subtask A, our submission is ranked 3rd, with an accuracy of 83.14{%}. Our current best solution stands 1st on the leaderboard with 88{%} accuracy. In subtask B, our present solution is ranked 2nd, with 58.33{%} MAP score. | |
Tasks | Community Question Answering, Data Augmentation, Question Answering |
Published | 2019-06-01 |
URL | https://www.aclweb.org/anthology/S19-2204/ |
https://www.aclweb.org/anthology/S19-2204 | |
PWC | https://paperswithcode.com/paper/solomonlab-at-semeval-2019-task-8-question |
Repo | |
Framework | |
Detecting Political Bias in News Articles Using Headline Attention
Title | Detecting Political Bias in News Articles Using Headline Attention |
Authors | Rama Rohit Reddy Gangula, Suma Reddy Duggenpudi, Radhika Mamidi |
Abstract | Language is a powerful tool which can be used to state the facts as well as express our views and perceptions. Most of the times, we find a subtle bias towards or against someone or something. When it comes to politics, media houses and journalists are known to create bias by shrewd means such as misinterpreting reality and distorting viewpoints towards some parties. This misinterpretation on a large scale can lead to the production of biased news and conspiracy theories. Automating bias detection in newspaper articles could be a good challenge for research in NLP. We proposed a headline attention network for this bias detection. Our model has two distinctive characteristics: (i) it has a structure that mirrors a person{'}s way of reading a news article (ii) it has attention mechanism applied on the article based on its headline, enabling it to attend to more critical content to predict bias. As the required datasets were not available, we created a dataset comprising of 1329 news articles collected from various Telugu newspapers and marked them for bias towards a particular political party. The experiments conducted on it demonstrated that our model outperforms various baseline methods by a substantial margin. |
Tasks | |
Published | 2019-08-01 |
URL | https://www.aclweb.org/anthology/W19-4809/ |
https://www.aclweb.org/anthology/W19-4809 | |
PWC | https://paperswithcode.com/paper/detecting-political-bias-in-news-articles |
Repo | |
Framework | |
CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense
Title | CODAH: An Adversarially-Authored Question Answering Dataset for Common Sense |
Authors | Michael Chen, Mike D{'}Arcy, Alisa Liu, Fern, Jared ez, Doug Downey |
Abstract | Commonsense reasoning is a critical AI capability, but it is difficult to construct challenging datasets that test common sense. Recent neural question answering systems, based on large pre-trained models of language, have already achieved near-human-level performance on commonsense knowledge benchmarks. These systems do not possess human-level common sense, but are able to exploit limitations of the datasets to achieve human-level scores. We introduce the CODAH dataset, an adversarially-constructed evaluation dataset for testing common sense. CODAH forms a challenging extension to the recently-proposed SWAG dataset, which tests commonsense knowledge using sentence-completion questions that describe situations observed in video. To produce a more difficult dataset, we introduce a novel procedure for question acquisition in which workers author questions designed to target weaknesses of state-of-the-art neural question answering systems. Workers are rewarded for submissions that models fail to answer correctly both before and after fine-tuning (in cross-validation). We create 2.8k questions via this procedure and evaluate the performance of multiple state-of-the-art question answering systems on our dataset. We observe a significant gap between human performance, which is 95.3{%}, and the performance of the best baseline accuracy of 65.3{%} by the OpenAI GPT model. |
Tasks | Common Sense Reasoning, Question Answering |
Published | 2019-06-01 |
URL | https://www.aclweb.org/anthology/W19-2008/ |
https://www.aclweb.org/anthology/W19-2008 | |
PWC | https://paperswithcode.com/paper/codah-an-adversarially-authored-question |
Repo | |
Framework | |