Paper Group NANR 136
Dynamic Neural Program Embeddings for Program Repair. Cross-cultural differences in language markers of depression online. YNU_AI1799 at SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge of Different model ensemble. Supervised Treebank Conversion: Data and Approaches. Regularized Training Objective for Continued Training for …
Dynamic Neural Program Embeddings for Program Repair
| Title | Dynamic Neural Program Embeddings for Program Repair |
| Authors | Ke Wang, Rishabh Singh, Zhendong Su |
| Abstract | Neural program embeddings have shown much promise recently for a variety of program analysis tasks, including program synthesis, program repair, code completion, and fault localization. However, most existing program embeddings are based on syntactic features of programs, such as token sequences or abstract syntax trees. Unlike images and text, a program has well-defined semantics that can be difficult to capture by only considering its syntax (i.e. syntactically similar programs can exhibit vastly different run-time behavior), which makes syntax-based program embeddings fundamentally limited. We propose a novel semantic program embedding that is learned from program execution traces. Our key insight is that program states expressed as sequential tuples of live variable values not only capture program semantics more precisely, but also offer a more natural fit for Recurrent Neural Networks to model. We evaluate different syntactic and semantic program embeddings on the task of classifying the types of errors that students make in their submissions to an introductory programming class and on the CodeHunt education platform. Our evaluation results show that the semantic program embeddings significantly outperform the syntactic program embeddings based on token sequences and abstract syntax trees. In addition, we augment a search-based program repair system with predictions made from our semantic embedding and demonstrate significantly improved search efficiency. |
| Tasks | Program Synthesis |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BJuWrGW0Z |
| https://openreview.net/pdf?id=BJuWrGW0Z | |
| PWC | https://paperswithcode.com/paper/dynamic-neural-program-embeddings-for-program |
| Repo | |
| Framework | |
Cross-cultural differences in language markers of depression online
| Title | Cross-cultural differences in language markers of depression online |
| Authors | Kate Loveys, Jonathan Torrez, Alex Fine, Glen Moriarty, Glen Coppersmith |
| Abstract | Depression is a global mental health condition that affects all cultures. Despite this, the way depression is expressed varies by culture. Uptake of machine learning technology for diagnosing mental health conditions means that increasingly more depression classifiers are created from online language data. Yet, culture is rarely considered as a factor affecting online language in this literature. This study explores cultural differences in online language data of users with depression. Written language data from 1,593 users with self-reported depression from the online peer support community 7 Cups of Tea was analyzed using the Linguistic Inquiry and Word Count (LIWC), topic modeling, data visualization, and other techniques. We compared the language of users identifying as White, Black or African American, Hispanic or Latino, and Asian or Pacific Islander. Exploratory analyses revealed cross-cultural differences in depression expression in online language data, particularly in relation to emotion expression, cognition, and functioning. The results have important implications for avoiding depression misclassification from machine-driven assessments when used in a clinical setting, and for avoiding inadvertent cultural biases in this line of research more broadly. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0608/ |
| https://www.aclweb.org/anthology/W18-0608 | |
| PWC | https://paperswithcode.com/paper/cross-cultural-differences-in-language |
| Repo | |
| Framework | |
YNU_AI1799 at SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge of Different model ensemble
| Title | YNU_AI1799 at SemEval-2018 Task 11: Machine Comprehension using Commonsense Knowledge of Different model ensemble |
| Authors | Qingxun Liu, Hongdou Yao, Xaobing Zhou, Ge Xie |
| Abstract | In this paper, we describe a machine reading comprehension system that participated in SemEval-2018 Task 11: Machine Comprehension using commonsense knowledge. In this work, we train a series of neural network models such as multi-LSTM, BiLSTM, multi- BiLSTM-CNN and attention-based BiLSTM, etc. On top of some sub models, there are two kinds of word embedding: (a) general word embedding generated from unsupervised neural language model; and (b) position embedding generated from general word embedding. Finally, we make a hard vote on the predictions of these models and achieve relatively good result. The proposed approach achieves 8th place in Task 11 with the accuracy of 0.7213. |
| Tasks | Language Modelling, Machine Reading Comprehension, Reading Comprehension, Text Classification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1173/ |
| https://www.aclweb.org/anthology/S18-1173 | |
| PWC | https://paperswithcode.com/paper/ynu_ai1799-at-semeval-2018-task-11-machine |
| Repo | |
| Framework | |
Supervised Treebank Conversion: Data and Approaches
| Title | Supervised Treebank Conversion: Data and Approaches |
| Authors | Xinzhou Jiang, Zhenghua Li, Bo Zhang, Min Zhang, Sheng Li, Luo Si |
| Abstract | Treebank conversion is a straightforward and effective way to exploit various heterogeneous treebanks for boosting parsing performance. However, previous work mainly focuses on unsupervised treebank conversion and has made little progress due to the lack of manually labeled data where each sentence has two syntactic trees complying with two different guidelines at the same time, referred as bi-tree aligned data. In this work, we for the first time propose the task of supervised treebank conversion. First, we manually construct a bi-tree aligned dataset containing over ten thousand sentences. Then, we propose two simple yet effective conversion approaches (pattern embedding and treeLSTM) based on the state-of-the-art deep biaffine parser. Experimental results show that 1) the two conversion approaches achieve comparable conversion accuracy, and 2) treebank conversion is superior to the widely used multi-task learning framework in multi-treebank exploitation and leads to significantly higher parsing accuracy. |
| Tasks | Dependency Parsing, Multi-Task Learning |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1252/ |
| https://www.aclweb.org/anthology/P18-1252 | |
| PWC | https://paperswithcode.com/paper/supervised-treebank-conversion-data-and |
| Repo | |
| Framework | |
Regularized Training Objective for Continued Training for Domain Adaptation in Neural Machine Translation
| Title | Regularized Training Objective for Continued Training for Domain Adaptation in Neural Machine Translation |
| Authors | Huda Khayrallah, Brian Thompson, Kevin Duh, Philipp Koehn |
| Abstract | Supervised domain adaptation{—}where a large generic corpus and a smaller in-domain corpus are both available for training{—}is a challenge for neural machine translation (NMT). Standard practice is to train a generic model and use it to initialize a second model, then continue training the second model on in-domain data to produce an in-domain model. We add an auxiliary term to the training objective during continued training that minimizes the cross entropy between the in-domain model{'}s output word distribution and that of the out-of-domain model to prevent the model{'}s output from differing too much from the original out-of-domain model. We perform experiments on EMEA (descriptions of medicines) and TED (rehearsed presentations), initialized from a general domain (WMT) model. Our method shows improvements over standard continued training by up to 1.5 BLEU. |
| Tasks | Domain Adaptation, Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2705/ |
| https://www.aclweb.org/anthology/W18-2705 | |
| PWC | https://paperswithcode.com/paper/regularized-training-objective-for-continued |
| Repo | |
| Framework | |
Enhancing the Transferability of Adversarial Examples with Noise Reduced Gradient
| Title | Enhancing the Transferability of Adversarial Examples with Noise Reduced Gradient |
| Authors | Lei Wu, Zhanxing Zhu, Cheng Tai, Weinan E |
| Abstract | Deep neural networks provide state-of-the-art performance for many applications of interest. Unfortunately they are known to be vulnerable to adversarial examples, formed by applying small but malicious perturbations to the original inputs. Moreover, the perturbations can transfer across models: adversarial examples generated for a specific model will often mislead other unseen models. Consequently the adversary can leverage it to attack against the deployed black-box systems. In this work, we demonstrate that the adversarial perturbation can be decomposed into two components: model-specific and data-dependent one, and it is the latter that mainly contributes to the transferability. Motivated by this understanding, we propose to craft adversarial examples by utilizing the noise reduced gradient (NRG) which approximates the data-dependent component. Experiments on various classification models trained on ImageNet demonstrates that the new approach enhances the transferability dramatically. We also find that low-capacity models have more powerful attack capability than high-capacity counterparts, under the condition that they have comparable test performance. These insights give rise to a principled manner to construct adversarial examples with high success rates and could potentially provide us guidance for designing effective defense approaches against black-box attacks. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=ryvxcPeAb |
| https://openreview.net/pdf?id=ryvxcPeAb | |
| PWC | https://paperswithcode.com/paper/enhancing-the-transferability-of-adversarial |
| Repo | |
| Framework | |
Toward Automatically Measuring Learner Ability from Human-Machine Dialog Interactions using Novel Psychometric Models
| Title | Toward Automatically Measuring Learner Ability from Human-Machine Dialog Interactions using Novel Psychometric Models |
| Authors | Vikram Ramanarayanan, Michelle LaMar |
| Abstract | While dialog systems have been widely deployed for computer-assisted language learning (CALL) and formative assessment systems in recent years, relatively limited work has been done with respect to the psychometrics and validity of these technologies in evaluating and providing feedback regarding student learning and conversational ability. This paper formulates a Markov decision process based measurement model, and applies it to text chat data collected from crowdsourced native and non-native English language speakers interacting with an automated dialog agent. We investigate how well the model measures speaker conversational ability, and find that it effectively captures the differences in how native and non-native speakers of English accomplish the dialog task. Such models could have important implications for CALL systems of the future that effectively combine dialog management with measurement of learner conversational ability in real-time. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0512/ |
| https://www.aclweb.org/anthology/W18-0512 | |
| PWC | https://paperswithcode.com/paper/toward-automatically-measuring-learner |
| Repo | |
| Framework | |
Neighbor-encoder
| Title | Neighbor-encoder |
| Authors | Chin-Chia Michael Yeh, Yan Zhu, Evangelos E. Papalexakis, Abdullah Mueen, Eamonn Keogh |
| Abstract | We propose a novel unsupervised representation learning framework called neighbor-encoder in which domain knowledge can be trivially incorporated into the learning process without modifying the general encoder-decoder architecture. In contrast to autoencoder, which reconstructs the input data, neighbor-encoder reconstructs the input data’s neighbors. The proposed neighbor-encoder can be considered as a generalization of autoencoder as the input data can be treated as the nearest neighbor of itself with zero distance. By reformulating the representation learning problem as a neighbor reconstruction problem, domain knowledge can be easily incorporated with appropriate definition of similarity or distance between objects. As such, any existing similarity search algorithms can be easily integrated into our framework. Applications of other algorithms (e.g., association rule mining) in our framework is also possible since the concept of ``neighbor” is an abstraction which can be appropriately defined differently in different contexts. We have demonstrated the effectiveness of our framework in various domains, including images, time series, music, etc., with various neighbor definitions. Experimental results show that neighbor-encoder outperforms autoencoder in most scenarios we considered. | |
| Tasks | Representation Learning, Time Series, Unsupervised Representation Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=r1vccClCb |
| https://openreview.net/pdf?id=r1vccClCb | |
| PWC | https://paperswithcode.com/paper/neighbor-encoder |
| Repo | |
| Framework | |
Findings of the WMT 2018 Biomedical Translation Shared Task: Evaluation on Medline test sets
| Title | Findings of the WMT 2018 Biomedical Translation Shared Task: Evaluation on Medline test sets |
| Authors | Mariana Neves, Antonio Jimeno Yepes, Aur{'e}lie N{'e}v{'e}ol, Cristian Grozea, Amy Siu, Madeleine Kittner, Karin Verspoor |
| Abstract | Machine translation enables the automatic translation of textual documents between languages and can facilitate access to information only available in a given language for non-speakers of this language, e.g. research results presented in scientific publications. In this paper, we provide an overview of the Biomedical Translation shared task in the Workshop on Machine Translation (WMT) 2018, which specifically examined the performance of machine translation systems for biomedical texts. This year, we provided test sets of scientific publications from two sources (EDP and Medline) and for six language pairs (English with each of Chinese, French, German, Portuguese, Romanian and Spanish). We describe the development of the various test sets, the submissions that we received and the evaluations that we carried out. We obtained a total of 39 runs from six teams and some of this year{'}s BLEU scores were somewhat higher that last year{'}s, especially for teams that made use of biomedical resources or state-of-the-art MT algorithms (e.g. Transformer). Finally, our manual evaluation scored automatic translations higher than the reference translations for German and Spanish. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6403/ |
| https://www.aclweb.org/anthology/W18-6403 | |
| PWC | https://paperswithcode.com/paper/findings-of-the-wmt-2018-biomedical |
| Repo | |
| Framework | |
Scalable Robust Matrix Factorization with Nonconvex Loss
| Title | Scalable Robust Matrix Factorization with Nonconvex Loss |
| Authors | Quanming Yao, James Kwok |
| Abstract | Robust matrix factorization (RMF), which uses the $\ell_1$-loss, often outperforms standard matrix factorization using the $\ell_2$-loss, particularly when outliers are present. The state-of-the-art RMF solver is the RMF-MM algorithm, which, however, cannot utilize data sparsity. Moreover, sometimes even the (convex) $\ell_1$-loss is not robust enough. In this paper, we propose the use of nonconvex loss to enhance robustness. To address the resultant difficult optimization problem, we use majorization-minimization (MM) optimization and propose a new MM surrogate. To improve scalability, we exploit data sparsity and optimize the surrogate via its dual with the accelerated proximal gradient algorithm. The resultant algorithm has low time and space complexities and is guaranteed to converge to a critical point. Extensive experiments demonstrate its superiority over the state-of-the-art in terms of both accuracy and scalability. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7753-scalable-robust-matrix-factorization-with-nonconvex-loss |
| http://papers.nips.cc/paper/7753-scalable-robust-matrix-factorization-with-nonconvex-loss.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-robust-matrix-factorization-with |
| Repo | |
| Framework | |
Recognizing Humour using Word Associations and Humour Anchor Extraction
| Title | Recognizing Humour using Word Associations and Humour Anchor Extraction |
| Authors | Andrew Cattle, Xiaojuan Ma |
| Abstract | This paper attempts to marry the interpretability of statistical machine learning approaches with the more robust models of joke structure and joke semantics capable of being learned by neural models. Specifically, we explore the use of semantic relatedness features based on word associations, rather than the more common Word2Vec similarity, on a binary humour identification task and identify several factors that make word associations a better fit for humour. We also explore the effects of using joke structure, in the form of humour anchors (Yang et al., 2015), for improving the performance of semantic features and show that, while an intriguing idea, humour anchors contain several pitfalls that can hurt performance. |
| Tasks | Semantic Textual Similarity, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1157/ |
| https://www.aclweb.org/anthology/C18-1157 | |
| PWC | https://paperswithcode.com/paper/recognizing-humour-using-word-associations |
| Repo | |
| Framework | |
Thermometer Encoding: One Hot Way To Resist Adversarial Examples
| Title | Thermometer Encoding: One Hot Way To Resist Adversarial Examples |
| Authors | Jacob Buckman, Aurko Roy, Colin Raffel, Ian Goodfellow |
| Abstract | It is well known that it is possible to construct “adversarial examples” for neural networks: inputs which are misclassified by the network yet indistinguishable from true data. We propose a simple modification to standard neural network architectures, thermometer encoding, which significantly increases the robustness of the network to adversarial examples. We demonstrate this robustness with experiments on the MNIST, CIFAR-10, CIFAR-100, and SVHN datasets, and show that models with thermometer-encoded inputs consistently have higher accuracy on adversarial examples, without decreasing generalization. State-of-the-art accuracy under the strongest known white-box attack was increased from 93.20% to 94.30% on MNIST and 50.00% to 79.16% on CIFAR-10. We explore the properties of these networks, providing evidence that thermometer encodings help neural networks to find more-non-linear decision boundaries. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=S18Su--CW |
| https://openreview.net/pdf?id=S18Su--CW | |
| PWC | https://paperswithcode.com/paper/thermometer-encoding-one-hot-way-to-resist |
| Repo | |
| Framework | |
Exploiting Syntactic Structures for Humor Recognition
| Title | Exploiting Syntactic Structures for Humor Recognition |
| Authors | Lizhen Liu, Donghai Zhang, Wei Song |
| Abstract | Humor recognition is an interesting and challenging task in natural language processing. This paper proposes to exploit syntactic structure features to enhance humor recognition. Our method achieves significant improvements compared with humor theory driven baselines. We found that some syntactic structure features consistently correlate with humor, which indicate interesting linguistic phenomena. Both the experimental results and the analysis demonstrate that humor can be viewed as a kind of style and content independent syntactic structures can help identify humor and have good interpretability. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1159/ |
| https://www.aclweb.org/anthology/C18-1159 | |
| PWC | https://paperswithcode.com/paper/exploiting-syntactic-structures-for-humor |
| Repo | |
| Framework | |
World Knowledge for Abstract Meaning Representation Parsing
| Title | World Knowledge for Abstract Meaning Representation Parsing |
| Authors | Charles Welch, Jonathan K. Kummerfeld, Song Feng, Rada Mihalcea |
| Abstract | |
| Tasks | Amr Parsing, Named Entity Recognition, Semantic Parsing |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1492/ |
| https://www.aclweb.org/anthology/L18-1492 | |
| PWC | https://paperswithcode.com/paper/world-knowledge-for-abstract-meaning |
| Repo | |
| Framework | |
A Multi-Stage Memory Augmented Neural Network for Machine Reading Comprehension
| Title | A Multi-Stage Memory Augmented Neural Network for Machine Reading Comprehension |
| Authors | Seunghak Yu, Sathish Reddy Indurthi, Seohyun Back, Haejun Lee |
| Abstract | Reading Comprehension (RC) of text is one of the fundamental tasks in natural language processing. In recent years, several end-to-end neural network models have been proposed to solve RC tasks. However, most of these models suffer in reasoning over long documents. In this work, we propose a novel Memory Augmented Machine Comprehension Network (MAMCN) to address long-range dependencies present in machine reading comprehension. We perform extensive experiments to evaluate proposed method with the renowned benchmark datasets such as SQuAD, QUASAR-T, and TriviaQA. We achieve the state of the art performance on both the document-level (QUASAR-T, TriviaQA) and paragraph-level (SQuAD) datasets compared to all the previously published approaches. |
| Tasks | Machine Reading Comprehension, Question Answering, Reading Comprehension |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2603/ |
| https://www.aclweb.org/anthology/W18-2603 | |
| PWC | https://paperswithcode.com/paper/a-multi-stage-memory-augmented-neural-network |
| Repo | |
| Framework | |
