Paper Group NANR 241
An Analysis of Emotion Communication Channels in Fan-Fiction: Towards Emotional Storytelling. SemEval-2019 Task 3: EmoContext Contextual Emotion Detection in Text. Comparison of Machine Learning Approaches for Industry Classification Based on Textual Descriptions of Companies. What Part of the Neural Network Does This? Understanding LSTMs by Measur …
An Analysis of Emotion Communication Channels in Fan-Fiction: Towards Emotional Storytelling
| Title | An Analysis of Emotion Communication Channels in Fan-Fiction: Towards Emotional Storytelling |
| Authors | Evgeny Kim, Roman Klinger |
| Abstract | Centrality of emotion for the stories told by humans is underpinned by numerous studies in literature and psychology. The research in automatic storytelling has recently turned towards emotional storytelling, in which characters{'} emotions play an important role in the plot development (Theune et al., 2004; y Perez, 2007; Mendez et al., 2016). However, these studies mainly use emotion to generate propositional statements in the form {}A feels affection towards B{''} or {}A confronts B{''}. At the same time, emotional behavior does not boil down to such propositional descriptions, as humans display complex and highly variable patterns in communicating their emotions, both verbally and non-verbally. In this paper, we analyze how emotions are expressed non-verbally in a corpus of fan fiction short stories. Our analysis shows that stories written by humans convey character emotions along various non-verbal channels. We find that some non-verbal channels, such as facial expressions and voice characteristics of the characters, are more strongly associated with joy, while gestures and body postures are more likely to occur with trust. Based on our analysis, we argue that automatic storytelling systems should take variability of emotion into account when generating descriptions of characters{'} emotions. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3406/ |
| https://www.aclweb.org/anthology/W19-3406 | |
| PWC | https://paperswithcode.com/paper/an-analysis-of-emotion-communication-channels-1 |
| Repo | |
| Framework | |
SemEval-2019 Task 3: EmoContext Contextual Emotion Detection in Text
| Title | SemEval-2019 Task 3: EmoContext Contextual Emotion Detection in Text |
| Authors | Ankush Chatterjee, Kedhar Nath Narahari, Meghana Joshi, Puneet Agrawal |
| Abstract | In this paper, we present the SemEval-2019 Task 3 - EmoContext: Contextual Emotion Detection in Text. Lack of facial expressions and voice modulations make detecting emotions in text a challenging problem. For instance, as humans, on reading {``}Why don{'}t you ever text me!{''} we can either interpret it as a sad or angry emotion and the same ambiguity exists for machines. However, the context of dialogue can prove helpful in detection of the emotion. In this task, given a textual dialogue i.e. an utterance along with two previous turns of context, the goal was to infer the underlying emotion of the utterance by choosing from four emotion classes - Happy, Sad, Angry and Others. To facilitate the participation in this task, textual dialogues from user interaction with a conversational agent were taken and annotated for emotion classes after several data processing steps. A training data set of 30160 dialogues, and two evaluation data sets, Test1 and Test2, containing 2755 and 5509 dialogues respectively were released to the participants. A total of 311 teams made submissions to this task. The final leader-board was evaluated on Test2 data set, and the highest ranked submission achieved 79.59 micro-averaged F1 score. Our analysis of systems submitted to the task indicate that Bi-directional LSTM was the most common choice of neural architecture used, and most of the systems had the best performance for the Sad emotion class, and the worst for the Happy emotion class. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2005/ |
| https://www.aclweb.org/anthology/S19-2005 | |
| PWC | https://paperswithcode.com/paper/semeval-2019-task-3-emocontext-contextual |
| Repo | |
| Framework | |
Comparison of Machine Learning Approaches for Industry Classification Based on Textual Descriptions of Companies
| Title | Comparison of Machine Learning Approaches for Industry Classification Based on Textual Descriptions of Companies |
| Authors | Andrey Tagarev, Nikola Tulechki, Svetla Boytcheva |
| Abstract | This paper addresses the task of categorizing companies within industry classification schemes. The datasets consists of encyclopedic articles about companies and their economic activities. The target classification schema is build by mapping linked open data in a semi-supervised manner. Target classes are build bottom-up from DBpedia. We apply several state of the art text classification techniques, based both on deep-learning and classical vector-space models. |
| Tasks | Text Classification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1134/ |
| https://www.aclweb.org/anthology/R19-1134 | |
| PWC | https://paperswithcode.com/paper/comparison-of-machine-learning-approaches-for |
| Repo | |
| Framework | |
What Part of the Neural Network Does This? Understanding LSTMs by Measuring and Dissecting Neurons
| Title | What Part of the Neural Network Does This? Understanding LSTMs by Measuring and Dissecting Neurons |
| Authors | Ji Xin, Jimmy Lin, Yaoliang Yu |
| Abstract | Memory neurons of long short-term memory (LSTM) networks encode and process information in powerful yet mysterious ways. While there has been work to analyze their behavior in carrying low-level information such as linguistic properties, how they directly contribute to label prediction remains unclear. We find inspiration from biologists and study the affinity between individual neurons and labels, propose a novel metric to quantify the sensitivity of neurons to each label, and conduct experiments to show the validity of our proposed metric. We discover that some neurons are trained to specialize on a subset of labels, and while dropping an arbitrary neuron has little effect on the overall accuracy of the model, dropping label-specialized neurons predictably and significantly degrades prediction accuracy on the associated label. We further examine the consistency of neuron-label affinity across different models. These observations provide insight into the inner mechanisms of LSTMs. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1591/ |
| https://www.aclweb.org/anthology/D19-1591 | |
| PWC | https://paperswithcode.com/paper/what-part-of-the-neural-network-does-this |
| Repo | |
| Framework | |
Generating Quantified Referring Expressions with Perceptual Cost Pruning
| Title | Generating Quantified Referring Expressions with Perceptual Cost Pruning |
| Authors | Gordon Briggs, Hillary Harner |
| Abstract | We model the production of quantified referring expressions (QREs) that identify collections of visual items. To address this task, we propose a method of perceptual cost pruning, which consists of two steps: (1) determine what subset of quantity information can be perceived given a time limit t, and (2) apply a preference order based REG algorithm (e.g., the Incremental Algorithm) to this reduced set of information. We demonstrate that this method successfully improves the human-likeness of the IA in the QRE generation task and successfully models human-generated language in most cases. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8602/ |
| https://www.aclweb.org/anthology/W19-8602 | |
| PWC | https://paperswithcode.com/paper/generating-quantified-referring-expressions |
| Repo | |
| Framework | |
Few-Shot Image Recognition With Knowledge Transfer
| Title | Few-Shot Image Recognition With Knowledge Transfer |
| Authors | Zhimao Peng, Zechao Li, Junge Zhang, Yan Li, Guo-Jun Qi, Jinhui Tang |
| Abstract | Human can well recognize images of novel categories just after browsing few examples of these categories. One possible reason is that they have some external discriminative visual information about these categories from their prior knowledge. Inspired from this, we propose a novel Knowledge Transfer Network architecture (KTN) for few-shot image recognition. The proposed KTN model jointly incorporates visual feature learning, knowledge inferring and classifier learning into one unified framework for their optimal compatibility. First, the visual classifiers for novel categories are learned based on the convolutional neural network with the cosine similarity optimization. To fully explore the prior knowledge, a semantic-visual mapping network is then developed to conduct knowledge inference, which enables to infer the classifiers for novel categories from base categories. Finally, we design an adaptive fusion scheme to infer the desired classifiers by effectively integrating the above knowledge and visual information. Extensive experiments are conducted on two widely-used Mini-ImageNet and ImageNet Few-Shot benchmarks to evaluate the effectiveness of the proposed method. The results compared with the state-of-the-art approaches show the encouraging performance of the proposed method, especially on 1-shot and 2-shot tasks. |
| Tasks | Transfer Learning |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Peng_Few-Shot_Image_Recognition_With_Knowledge_Transfer_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Peng_Few-Shot_Image_Recognition_With_Knowledge_Transfer_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/few-shot-image-recognition-with-knowledge |
| Repo | |
| Framework | |
Text Genre and Training Data Size in Human-like Parsing
| Title | Text Genre and Training Data Size in Human-like Parsing |
| Authors | John Hale, Adhiguna Kuncoro, Keith Hall, Chris Dyer, Jonathan Brennan |
| Abstract | Domain-specific training typically makes NLP systems work better. We show that this extends to cognitive modeling as well by relating the states of a neural phrase-structure parser to electrophysiological measures from human participants. These measures were recorded as participants listened to a spoken recitation of the same literary text that was supplied as input to the neural parser. Given more training data, the system derives a better cognitive model {—} but only when the training examples come from the same textual genre. This finding is consistent with the idea that humans adapt syntactic expectations to particular genres during language comprehension (Kaan and Chun, 2018; Branigan and Pickering, 2017). |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1594/ |
| https://www.aclweb.org/anthology/D19-1594 | |
| PWC | https://paperswithcode.com/paper/text-genre-and-training-data-size-in-human |
| Repo | |
| Framework | |
Reranking for Neural Semantic Parsing
| Title | Reranking for Neural Semantic Parsing |
| Authors | Pengcheng Yin, Graham Neubig |
| Abstract | Semantic parsing considers the task of transducing natural language (NL) utterances into machine executable meaning representations (MRs). While neural network-based semantic parsers have achieved impressive improvements over previous methods, results are still far from perfect, and cursory manual inspection can easily identify obvious problems such as lack of adequacy or coherence of the generated MRs. This paper presents a simple approach to quickly iterate and improve the performance of an existing neural semantic parser by reranking an n-best list of predicted MRs, using features that are designed to fix observed problems with baseline models. We implement our reranker in a competitive neural semantic parser and test on four semantic parsing (GEO, ATIS) and Python code generation (Django, CoNaLa) tasks, improving the strong baseline parser by up to 5.7{%} absolute in BLEU (CoNaLa) and 2.9{%} in accuracy (Django), outperforming the best published neural parser results on all four datasets. |
| Tasks | Code Generation, Semantic Parsing |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1447/ |
| https://www.aclweb.org/anthology/P19-1447 | |
| PWC | https://paperswithcode.com/paper/reranking-for-neural-semantic-parsing |
| Repo | |
| Framework | |
A Deep Learning Approach to Language-independent Gender Prediction on Twitter
| Title | A Deep Learning Approach to Language-independent Gender Prediction on Twitter |
| Authors | Reyhaneh Hashempour |
| Abstract | This work presents a set of experiments conducted to predict the gender of Twitter users based on language-independent features extracted from the text of the users{'} tweets. The experiments were performed on a version of TwiSty dataset including tweets written by the users of six different languages: Portuguese, French, Dutch, English, German, and Italian. Logistic regression (LR), and feed-forward neural networks (FFNN) with back-propagation were used to build models in two different settings: Inter-Lingual (IL) and Cross-Lingual (CL). In the IL setting, the training and testing were performed on the same language whereas in the CL, Italian and German datasets were set aside and only used as test sets and the rest were combined to compose training and development sets. In the IL, the highest accuracy score belongs to LR whereas, in the CL, FFNN with three hidden layers yields the highest score. The results show that neural network based models underperform traditional models when the size of the training set is small; however, they beat traditional models by a non-trivial margin, when they are fed with large enough data. Finally, the feature analysis confirms that men and women have different writing styles independent of their language. |
| Tasks | Gender Prediction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3630/ |
| https://www.aclweb.org/anthology/W19-3630 | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-approach-to-language |
| Repo | |
| Framework | |
Outlier Detection from Image Data
| Title | Outlier Detection from Image Data |
| Authors | Lei Cao, Yizhou Yan, Samuel Madden, Elke Rundensteiner |
| Abstract | Modern applications from Autonomous Vehicles to Video Surveillance generate massive amounts of image data. In this work we propose a novel image outlier detection approach (IOD for short) that leverages the cutting-edge image classifier to discover outliers without using any labeled outlier. We observe that although intuitively the confidence that a convolutional neural network (CNN) has that an image belongs to a particular class could serve as outlierness measure to each image, directly applying this confidence to detect outlier does not work well. This is because CNN often has high confidence on an outlier image that does not belong to any target class due to its generalization ability that ensures the high accuracy in classification. To solve this issue, we propose a Deep Neural Forest-based approach that harmonizes the contradictory requirements of accurately classifying images and correctly detecting the outlier images. Our experiments using several benchmark image datasets including MNIST, CIFAR-10, CIFAR-100, and SVHN demonstrate the effectiveness of our IOD approach for outlier detection, capturing more than 90% of outliers generated by injecting one image dataset into another, while still preserving the classification accuracy of the multi-class classification problem. |
| Tasks | Autonomous Vehicles, Outlier Detection |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HygTE309t7 |
| https://openreview.net/pdf?id=HygTE309t7 | |
| PWC | https://paperswithcode.com/paper/outlier-detection-from-image-data |
| Repo | |
| Framework | |
A Surprisingly Robust Trick for the Winograd Schema Challenge
| Title | A Surprisingly Robust Trick for the Winograd Schema Challenge |
| Authors | Vid Kocijan, Ana-Maria Cretu, Oana-Maria Camburu, Yordan Yordanov, Thomas Lukasiewicz |
| Abstract | The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning. In this paper, we show that the performance of three language models on WSC273 consistently and robustly improves when fine-tuned on a similar pronoun disambiguation problem dataset (denoted WSCR). We additionally generate a large unsupervised WSC-like dataset. By fine-tuning the BERT language model both on the introduced and on the WSCR dataset, we achieve overall accuracies of 72.5{%} and 74.7{%} on WSC273 and WNLI, improving the previous state-of-the-art solutions by 8.8{%} and 9.6{%}, respectively. Furthermore, our fine-tuned models are also consistently more accurate on the {``}complex{''} subsets of WSC273, introduced by Trichelair et al. (2018). | |
| Tasks | Language Modelling |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1478/ |
| https://www.aclweb.org/anthology/P19-1478 | |
| PWC | https://paperswithcode.com/paper/a-surprisingly-robust-trick-for-the-winograd |
| Repo | |
| Framework | |
Revisiting the Evaluation of Theory of Mind through Question Answering
| Title | Revisiting the Evaluation of Theory of Mind through Question Answering |
| Authors | Matthew Le, Y-Lan Boureau, Maximilian Nickel |
| Abstract | Theory of mind, i.e., the ability to reason about intents and beliefs of agents is an important task in artificial intelligence and central to resolving ambiguous references in natural language dialogue. In this work, we revisit the evaluation of theory of mind through question answering. We show that current evaluation methods are flawed and that existing benchmark tasks can be solved without theory of mind due to dataset biases. Based on prior work, we propose an improved evaluation protocol and dataset in which we explicitly control for data regularities via a careful examination of the answer space. We show that state-of-the-art methods which are successful on existing benchmarks fail to solve theory-of-mind tasks in our proposed approach. |
| Tasks | Question Answering |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1598/ |
| https://www.aclweb.org/anthology/D19-1598 | |
| PWC | https://paperswithcode.com/paper/revisiting-the-evaluation-of-theory-of-mind |
| Repo | |
| Framework | |
EPITA-ADAPT at SemEval-2019 Task 3: Detecting emotions in textual conversations using deep learning models combination
| Title | EPITA-ADAPT at SemEval-2019 Task 3: Detecting emotions in textual conversations using deep learning models combination |
| Authors | Abdessalam Bouchekif, Praveen Joshi, Latifa Bouchekif, Haithem Afli |
| Abstract | Messaging platforms like WhatsApp, Facebook Messenger and Twitter have gained recently much popularity owing to their ability in connecting users in real-time. The content of these textual messages can be a useful resource for text mining to discover and unhide various aspects, including emotions. In this paper we present our submission for SemEval 2019 task {`}EmoContext{'}. The task consists of classifying a given textual dialogue into one of four emotion classes: Angry, Happy, Sad and Others. Our proposed system is based on the combination of different deep neural networks techniques. In particular, we use Recurrent Neural Networks (LSTM, B-LSTM, GRU, B-GRU), Convolutional Neural Network (CNN) and Transfer Learning (TL) methodes. Our final system, achieves an F1 score of 74.51{%} on the subtask evaluation dataset. | |
| Tasks | Transfer Learning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2035/ |
| https://www.aclweb.org/anthology/S19-2035 | |
| PWC | https://paperswithcode.com/paper/epita-adapt-at-semeval-2019-task-3-detecting |
| Repo | |
| Framework | |
Proceedings of the Fourth Arabic Natural Language Processing Workshop
| Title | Proceedings of the Fourth Arabic Natural Language Processing Workshop |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4600/ |
| https://www.aclweb.org/anthology/W19-4600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-fourth-arabic-natural |
| Repo | |
| Framework | |
Second-Order Adversarial Attack and Certifiable Robustness
| Title | Second-Order Adversarial Attack and Certifiable Robustness |
| Authors | Bai Li, Changyou Chen, Wenlin Wang, Lawrence Carin |
| Abstract | Adversarial training has been recognized as a strong defense against adversarial attacks. In this paper, we propose a powerful second-order attack method that reduces the accuracy of the defense model by Madry et al. (2017). We demonstrate that adversarial training overfits to the choice of the norm in the sense that it is only robust to the attack used for adversarial training, thus suggesting it has not achieved universal robustness. The effectiveness of our attack method motivates an investigation of provable robustness of a defense model. To this end, we introduce a framework that allows one to obtain a certifiable lower bound on the prediction accuracy against adversarial examples. We conduct experiments to show the effectiveness of our attack method. At the same time, our defense model achieves significant improvements compared to previous works under our proposed attack. |
| Tasks | Adversarial Attack |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SyxaYsAqY7 |
| https://openreview.net/pdf?id=SyxaYsAqY7 | |
| PWC | https://paperswithcode.com/paper/second-order-adversarial-attack-and-1 |
| Repo | |
| Framework | |
