Paper Group NANR 167
Pre-Training BERT on Domain Resources for Short Answer Grading. Gender Stereotypes Differ between Male and Female Writings. What does the Nom say? An algorithm for case disambiguation in Hungarian. Translating a Fragment of Natural Deduction System for Natural Language into Modern Type Theory. Attentional Neural Fields for Crowd Counting. Sentiment …
Pre-Training BERT on Domain Resources for Short Answer Grading
| Title | Pre-Training BERT on Domain Resources for Short Answer Grading |
| Authors | Chul Sung, Tejas Dhamecha, Swarnadeep Saha, Tengfei Ma, Vinay Reddy, Rishi Arora |
| Abstract | Pre-trained BERT contextualized representations have achieved state-of-the-art results on multiple downstream NLP tasks by fine-tuning with task-specific data. While there has been a lot of focus on task-specific fine-tuning, there has been limited work on improving the pre-trained representations. In this paper, we explore ways of improving the pre-trained contextual representations for the task of automatic short answer grading, a critical component of intelligent tutoring systems. We show that the pre-trained BERT model can be improved by augmenting data from the domain-specific resources like textbooks. We also present a new approach to use labeled short answering grading data for further enhancement of the language model. Empirical evaluation on multi-domain datasets shows that task-specific fine-tuning on the enhanced pre-trained language model achieves superior performance for short answer grading. |
| Tasks | Language Modelling |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1628/ |
| https://www.aclweb.org/anthology/D19-1628 | |
| PWC | https://paperswithcode.com/paper/pre-training-bert-on-domain-resources-for |
| Repo | |
| Framework | |
Gender Stereotypes Differ between Male and Female Writings
| Title | Gender Stereotypes Differ between Male and Female Writings |
| Authors | Yusu Qian |
| Abstract | Written language often contains gender stereotypes, typically conveyed unintentionally by the author. To study the difference in how female and male authors portray people of different genders, we quantitatively evaluate and analyze the gender stereotypes in their writings on two different datasets and from multiple aspects. We show that writings by females on average have lower gender stereotype scores. We plan to study and interpret the distributions of gender stereotype scores of individual words, and how they differ between male and female writings. We also plan on using more datasets over the past century to study how the stereotypes in female and male writings evolved over time. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2007/ |
| https://www.aclweb.org/anthology/P19-2007 | |
| PWC | https://paperswithcode.com/paper/gender-stereotypes-differ-between-male-and |
| Repo | |
| Framework | |
What does the Nom say? An algorithm for case disambiguation in Hungarian
| Title | What does the Nom say? An algorithm for case disambiguation in Hungarian |
| Authors | No{'e}mi Ligeti-Nagy, Andrea D{"o}m{"o}t{"o}r, No{'e}mi Vad{'a}sz |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0303/ |
| https://www.aclweb.org/anthology/W19-0303 | |
| PWC | https://paperswithcode.com/paper/what-does-the-nom-say-an-algorithm-for-case |
| Repo | |
| Framework | |
Translating a Fragment of Natural Deduction System for Natural Language into Modern Type Theory
| Title | Translating a Fragment of Natural Deduction System for Natural Language into Modern Type Theory |
| Authors | Ivo Pezlar |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1002/ |
| https://www.aclweb.org/anthology/W19-1002 | |
| PWC | https://paperswithcode.com/paper/translating-a-fragment-of-natural-deduction |
| Repo | |
| Framework | |
Attentional Neural Fields for Crowd Counting
| Title | Attentional Neural Fields for Crowd Counting |
| Authors | Anran Zhang, Lei Yue, Jiayi Shen, Fan Zhu, Xiantong Zhen, Xianbin Cao, Ling Shao |
| Abstract | Crowd counting has recently generated huge popularity in computer vision, and is extremely challenging due to the huge scale variations of objects. In this paper, we propose the Attentional Neural Field (ANF) for crowd counting via density estimation. Within the encoder-decoder network, we introduce conditional random fields (CRFs) to aggregate multi-scale features, which can build more informative representations. To better model pair-wise potentials in CRFs, we incorperate non-local attention mechanism implemented as inter- and intra-layer attentions to expand the receptive field to the entire image respectively within the same layer and across different layers, which captures long-range dependencies to conquer huge scale variations. The CRFs coupled with the attention mechanism are seamlessly integrated into the encoder-decoder network, establishing an ANF that can be optimized end-to-end by back propagation. We conduct extensive experiments on four public datasets, including ShanghaiTech, WorldEXPO 10, UCF-CC-50 and UCF-QNRF. The results show that our ANF achieves high counting performance, surpassing most previous methods. |
| Tasks | Crowd Counting, Density Estimation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhang_Attentional_Neural_Fields_for_Crowd_Counting_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Attentional_Neural_Fields_for_Crowd_Counting_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/attentional-neural-fields-for-crowd-counting |
| Repo | |
| Framework | |
Sentiment Analysis on Naija-Tweets
| Title | Sentiment Analysis on Naija-Tweets |
| Authors | Taiwo Kolajo, Olaw Daramola, e, Ayodele Adebiyi |
| Abstract | Examining sentiments in social media poses a challenge to natural language processing because of the intricacy and variability in the dialect articulation, noisy terms in form of slang, abbreviation, acronym, emoticon, and spelling error coupled with the availability of real-time content. Moreover, most of the knowledge-based approaches for resolving slang, abbreviation, and acronym do not consider the issue of ambiguity that evolves in the usage of these noisy terms. This research work proposes an improved framework for social media feed pre-processing that leverages on the combination of integrated local knowledge bases and adapted Lesk algorithm to facilitate pre-processing of social media feeds. The results from the experimental evaluation revealed an improvement over existing methods when applied to supervised learning algorithms in the task of extracting sentiments from Nigeria-origin tweets with an accuracy of 99.17{%}. |
| Tasks | Sentiment Analysis |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2047/ |
| https://www.aclweb.org/anthology/P19-2047 | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-on-naija-tweets |
| Repo | |
| Framework | |
Neural Text Normalization with Subword Units
| Title | Neural Text Normalization with Subword Units |
| Authors | Courtney Mansfield, Ming Sun, Yuzong Liu, G, Ankur he, Bj{"o}rn Hoffmeister |
| Abstract | Text normalization (TN) is an important step in conversational systems. It converts written text to its spoken form to facilitate speech recognition, natural language understanding and text-to-speech synthesis. Finite state transducers (FSTs) are commonly used to build grammars that handle text normalization. However, translating linguistic knowledge into grammars requires extensive effort. In this paper, we frame TN as a machine translation task and tackle it with sequence-to-sequence (seq2seq) models. Previous research focuses on normalizing a word (or phrase) with the help of limited word-level context, while our approach directly normalizes full sentences. We find subword models with additional linguistic features yield the best performance (with a word error rate of 0.17{%}). |
| Tasks | Machine Translation, Speech Recognition, Speech Synthesis, Text-To-Speech Synthesis |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2024/ |
| https://www.aclweb.org/anthology/N19-2024 | |
| PWC | https://paperswithcode.com/paper/neural-text-normalization-with-subword-units |
| Repo | |
| Framework | |
Leveraging Pre-Trained Embeddings for Welsh Taggers
| Title | Leveraging Pre-Trained Embeddings for Welsh Taggers |
| Authors | Ignatius Ezeani, Scott Piao, Steven Neale, Paul Rayson, Dawn Knight |
| Abstract | While the application of word embedding models to downstream Natural Language Processing (NLP) tasks has been shown to be successful, the benefits for low-resource languages is somewhat limited due to lack of adequate data for training the models. However, NLP research efforts for low-resource languages have focused on constantly seeking ways to harness pre-trained models to improve the performance of NLP systems built to process these languages without the need to re-invent the wheel. One such language is Welsh and therefore, in this paper, we present the results of our experiments on learning a simple multi-task neural network model for part-of-speech and semantic tagging for Welsh using a pre-trained embedding model from FastText. Our model{'}s performance was compared with those of the existing rule-based stand-alone taggers for part-of-speech and semantic taggers. Despite its simplicity and capacity to perform both tasks simultaneously, our tagger compared very well with the existing taggers. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4332/ |
| https://www.aclweb.org/anthology/W19-4332 | |
| PWC | https://paperswithcode.com/paper/leveraging-pre-trained-embeddings-for-welsh |
| Repo | |
| Framework | |
A topic-based sentence representation for extractive text summarization
| Title | A topic-based sentence representation for extractive text summarization |
| Authors | Nikolaos Gialitsis, Nikiforos Pittaras, Panagiotis Stamatopoulos |
| Abstract | In this study, we examine the effect of probabilistic topic model-based word representations, on sentence-based extractive summarization. We formulate the task of summary extraction as a binary classification problem, and we test a variety of machine learning algorithms, exploring a range of different settings. An wide experimental evaluation on the MultiLing 2015 MSS dataset illustrates that topic-based representations can prove beneficial to the extractive summarization process in terms of F1, ROUGE-L and ROUGE-W scores, compared to a TF-IDF baseline, with QDA-based analysis providing the best results. |
| Tasks | Text Summarization |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8905/ |
| https://www.aclweb.org/anthology/W19-8905 | |
| PWC | https://paperswithcode.com/paper/a-topic-based-sentence-representation-for |
| Repo | |
| Framework | |
Evaluation Methodology for Attacks Against Confidence Thresholding Models
| Title | Evaluation Methodology for Attacks Against Confidence Thresholding Models |
| Authors | Ian Goodfellow, Yao Qin, David Berthelot |
| Abstract | Current machine learning algorithms can be easily fooled by adversarial examples. One possible solution path is to make models that use confidence thresholding to avoid making mistakes. Such models refuse to make a prediction when they are not confident of their answer. We propose to evaluate such models in terms of tradeoff curves with the goal of high success rate on clean examples and low failure rate on adversarial examples. Existing untargeted attacks developed for models that do not use confidence thresholding tend to underestimate such models’ vulnerability. We propose the MaxConfidence family of attacks, which are optimal in a variety of theoretical settings, including one realistic setting: attacks against linear models. Experiments show the attack attains good results in practice. We show that simple defenses are able to perform well on MNIST but not on CIFAR, contributing further to previous calls that MNIST should be retired as a benchmarking dataset for adversarial robustness research. We release code for these evaluations as part of the cleverhans (Papernot et al 2018) library (ICLR reviewers should be careful not to look at who contributed these features to cleverhans to avoid de-anonymizing this submission). |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=H1g0piA9tQ |
| https://openreview.net/pdf?id=H1g0piA9tQ | |
| PWC | https://paperswithcode.com/paper/evaluation-methodology-for-attacks-against |
| Repo | |
| Framework | |
Audio Visual Scene-Aware Dialog
| Title | Audio Visual Scene-Aware Dialog |
| Authors | Huda Alamri, Vincent Cartillier, Abhishek Das, Jue Wang, Anoop Cherian, Irfan Essa, Dhruv Batra, Tim K. Marks, Chiori Hori, Peter Anderson, Stefan Lee, Devi Parikh |
| Abstract | We introduce the task of scene-aware dialog. Our goal is to generate a complete and natural response to a question about a scene, given video and audio of the scene and the history of previous turns in the dialog. To answer successfully, agents must ground concepts from the question in the video while leveraging contextual cues from the dialog history. To benchmark this task, we introduce the Audio Visual Scene-Aware Dialog (AVSD) Dataset. For each of more than 11,000 videos of human actions from the Charades dataset, our dataset contains a dialog about the video, plus a final summary of the video by one of the dialog participants. We train several baseline systems for this task and evaluate the performance of the trained models using both qualitative and quantitative metrics. Our results indicate that models must utilize all the available inputs (video, audio, question, and dialog history) to perform best on this dataset. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Alamri_Audio_Visual_Scene-Aware_Dialog_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Alamri_Audio_Visual_Scene-Aware_Dialog_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/audio-visual-scene-aware-dialog-1 |
| Repo | |
| Framework | |
What Should I Ask? Using Conversationally Informative Rewards for Goal-oriented Visual Dialog.
| Title | What Should I Ask? Using Conversationally Informative Rewards for Goal-oriented Visual Dialog. |
| Authors | Pushkar Shukla, Carlos Elmadjian, Richika Sharan, Vivek Kulkarni, Matthew Turk, William Yang Wang |
| Abstract | The ability to engage in goal-oriented conversations has allowed humans to gain knowledge, reduce uncertainty, and perform tasks more efficiently. Artificial agents, however, are still far behind humans in having goal-driven conversations. In this work, we focus on the task of goal-oriented visual dialogue, aiming to automatically generate a series of questions about an image with a single objective. This task is challenging since these questions must not only be consistent with a strategy to achieve a goal, but also consider the contextual information in the image. We propose an end-to-end goal-oriented visual dialogue system, that combines reinforcement learning with regularized information gain. Unlike previous approaches that have been proposed for the task, our work is motivated by the Rational Speech Act framework, which models the process of human inquiry to reach a goal. We test the two versions of our model on the GuessWhat?! dataset, obtaining significant results that outperform the current state-of-the-art models in the task of generating questions to find an undisclosed object in an image. |
| Tasks | Visual Dialog |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1646/ |
| https://www.aclweb.org/anthology/P19-1646 | |
| PWC | https://paperswithcode.com/paper/what-should-i-ask-using-conversationally |
| Repo | |
| Framework | |
A Variational EM Framework With Adaptive Edge Selection for Blind Motion Deblurring
| Title | A Variational EM Framework With Adaptive Edge Selection for Blind Motion Deblurring |
| Authors | Liuge Yang, Hui Ji |
| Abstract | Blind motion deblurring is an important problem that receives enduring attention in last decade. Based on the observation that a good intermediate estimate of latent image for estimating motion-blur kernel is not necessarily the one closest to latent image, edge selection has proven itself a very powerful technique for achieving state-of-the-art performance in blind deblurring. This paper presented an interpretation of edge selection/reweighting in terms of variational Bayes inference, and therefore developed a novel variational expectation maximization (VEM) algorithm with built-in adaptive edge selection for blind deblurring. Together with a restart strategy for avoiding undesired local convergence, the proposed VEM method not only has a solid mathematical foundation but also noticeably outperformed the state-of-the-art methods on benchmark datasets. |
| Tasks | Deblurring |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Yang_A_Variational_EM_Framework_With_Adaptive_Edge_Selection_for_Blind_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Yang_A_Variational_EM_Framework_With_Adaptive_Edge_Selection_for_Blind_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-variational-em-framework-with-adaptive-edge |
| Repo | |
| Framework | |
MonoForest framework for tree ensemble analysis
| Title | MonoForest framework for tree ensemble analysis |
| Authors | Igor Kuralenok, Vasilii Ershov, Igor Labutin |
| Abstract | In this work, we introduce a new decision tree ensemble representation framework: instead of using a graph model we transform each tree into a well-known polynomial form. We apply the new representation to three tasks: theoretical analysis, model reduction, and interpretation. The polynomial form of a tree ensemble allows a straightforward interpretation of the original model. In our experiments, it shows comparable results with state-of-the-art interpretation techniques. Another application of the framework is the ensemble-wise pruning: we can drop monomials from the polynomial, based on train data statistics. This way we reduce the model size up to 3 times without loss of its quality. It is possible to show the equivalence of tree shape classes that share the same polynomial. This fact gives us the ability to train a model in one tree’s shape and exploit it in another, which is easier for computation or interpretation. We formulate a problem statement for optimal tree ensemble translation from one form to another and build a greedy solution to this problem. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9530-monoforest-framework-for-tree-ensemble-analysis |
| http://papers.nips.cc/paper/9530-monoforest-framework-for-tree-ensemble-analysis.pdf | |
| PWC | https://paperswithcode.com/paper/monoforest-framework-for-tree-ensemble |
| Repo | |
| Framework | |
Spectral Reconstruction From Dispersive Blur: A Novel Light Efficient Spectral Imager
| Title | Spectral Reconstruction From Dispersive Blur: A Novel Light Efficient Spectral Imager |
| Authors | Yuanyuan Zhao, Xuemei Hu, Hui Guo, Zhan Ma, Tao Yue, Xun Cao |
| Abstract | Developing high light efficiency imaging techniques to retrieve high dimensional optical signal is a long-term goal in computational photography. Multispectral imaging, which captures images of different wavelengths and boosting the abilities for revealing scene properties, has developed rapidly in the last few decades. From scanning method to snapshot imaging, the limit of light collection efficiency is kept being pushed which enables wider applications especially under the light-starved scenes. In this work, we propose a novel multispectral imaging technique, that could capture the multispectral images with a high light efficiency. Through investigating the dispersive blur caused by spectral dispersers and introducing the difference of blur (DoB) constraints, we propose a basic theory for capturing multispectral information from a single dispersive-blurred image and an additional spectrum of an arbitrary point in the scene. Based on the theory, we design a prototype system and develop an optimization algorithm to realize snapshot multispectral imaging. The effectiveness of the proposed method is verified on both the synthetic data and real captured images. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhao_Spectral_Reconstruction_From_Dispersive_Blur_A_Novel_Light_Efficient_Spectral_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhao_Spectral_Reconstruction_From_Dispersive_Blur_A_Novel_Light_Efficient_Spectral_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/spectral-reconstruction-from-dispersive-blur |
| Repo | |
| Framework | |
