Paper Group NANR 197
WordNet Gloss Translation for Under-resourced Languages using Multilingual Neural Machine Translation. Would MT kill creativity in literary retranslation?. Building a Speech Corpus based on Arabic Podcasts for Language and Dialect Identification. AspeRa: Aspect-Based Rating Prediction Based on User Reviews. Drive&Act: A Multi-Modal Dataset for Fine …
WordNet Gloss Translation for Under-resourced Languages using Multilingual Neural Machine Translation
| Title | WordNet Gloss Translation for Under-resourced Languages using Multilingual Neural Machine Translation |
| Authors | Bharathi Raja Chakravarthi, Mihael Arcan, John P. McCrae |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7101/ |
| https://www.aclweb.org/anthology/W19-7101 | |
| PWC | https://paperswithcode.com/paper/wordnet-gloss-translation-for-under-resourced |
| Repo | |
| Framework | |
Would MT kill creativity in literary retranslation?
| Title | Would MT kill creativity in literary retranslation? |
| Authors | Mehmet {\c{S}}ahin, Sabri G{"u}rses |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7304/ |
| https://www.aclweb.org/anthology/W19-7304 | |
| PWC | https://paperswithcode.com/paper/would-mt-kill-creativity-in-literary |
| Repo | |
| Framework | |
Building a Speech Corpus based on Arabic Podcasts for Language and Dialect Identification
| Title | Building a Speech Corpus based on Arabic Podcasts for Language and Dialect Identification |
| Authors | Khaled Lounnas, Mourad Abbas, Mohamed Lichouri |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-7408/ |
| https://www.aclweb.org/anthology/W19-7408 | |
| PWC | https://paperswithcode.com/paper/building-a-speech-corpus-based-on-arabic |
| Repo | |
| Framework | |
AspeRa: Aspect-Based Rating Prediction Based on User Reviews
| Title | AspeRa: Aspect-Based Rating Prediction Based on User Reviews |
| Authors | Elena Tutubalina, Valentin Malykh, Sergey Nikolenko, Anton Alekseev, Ilya Shenbin |
| Abstract | We propose a novel Aspect-based Rating Prediction model (AspeRa) that estimates user rating based on review texts for the items. It is based on aspect extraction with neural networks and combines the advantages of deep learning and topic modeling. It is mainly designed for recommendations, but an important secondary goal of AspeRa is to discover coherent aspects of reviews that can be used to explain predictions or for user profiling. We conduct a comprehensive empirical study of AspeRa, showing that it outperforms state-of-the-art models in terms of recommendation quality and produces interpretable aspects. This paper is an abridged version of our work (Nikolenko et al., 2019) |
| Tasks | Aspect Extraction |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3605/ |
| https://www.aclweb.org/anthology/W19-3605 | |
| PWC | https://paperswithcode.com/paper/aspera-aspect-based-rating-prediction-based |
| Repo | |
| Framework | |
Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles
| Title | Drive&Act: A Multi-Modal Dataset for Fine-Grained Driver Behavior Recognition in Autonomous Vehicles |
| Authors | Manuel Martin, Alina Roitberg, Monica Haurilet, Matthias Horne, Simon Reiss, Michael Voit, Rainer Stiefelhagen |
| Abstract | We introduce the novel domain-specific Drive&Act benchmark for fine-grained categorization of driver behavior. Our dataset features twelve hours and over 9.6 million frames of people engaged in distractive activities during both, manual and automated driving. We capture color, infrared, depth and 3D body pose information from six views and densely label the videos with a hierarchical annotation scheme, resulting in 83 categories. The key challenges of our dataset are: (1) recognition of fine-grained behavior inside the vehicle cabin; (2) multi-modal activity recognition, focusing on diverse data streams; and (3) a cross view recognition benchmark, where a model handles data from an unfamiliar domain, as sensor type and placement in the cabin can change between vehicles. Finally, we provide challenging benchmarks by adopting prominent methods for video- and body pose-based action recognition. |
| Tasks | Activity Recognition, Autonomous Vehicles |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Martin_DriveAct_A_Multi-Modal_Dataset_for_Fine-Grained_Driver_Behavior_Recognition_in_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Martin_DriveAct_A_Multi-Modal_Dataset_for_Fine-Grained_Driver_Behavior_Recognition_in_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/driveact-a-multi-modal-dataset-for-fine |
| Repo | |
| Framework | |
Fermi at SemEval-2019 Task 8: An elementary but effective approach to Question Discernment in Community QA Forums
| Title | Fermi at SemEval-2019 Task 8: An elementary but effective approach to Question Discernment in Community QA Forums |
| Authors | Bakhtiyar Syed, Vijayasaradhi Indurthi, Manish Shrivastava, Manish Gupta, Vasudeva Varma |
| Abstract | Online Community Question Answering Forums (cQA) have gained massive popularity within recent years. The rise in users for such forums have led to the increase in the need for automated evaluation for question comprehension and fact evaluation of the answers provided by various participants in the forum. Our team, \textbf{Fermi}, participated in sub-task A of Task 8 at SemEval 2019 - which tackles the first problem in the pipeline of factual evaluation in cQA forums, i.e., deciding whether a posed question asks for a factual information, an opinion/advice or is just socializing. This information is highly useful in segregating factual questions from non-factual ones which highly helps in organizing the questions into useful categories and trims down the problem space for the next task in the pipeline for fact evaluation among the available answers. Our system uses the embeddings obtained from Universal Sentence Encoder combined with XGBoost for the classification sub-task A. We also evaluate other combinations of embeddings and off-the-shelf machine learning algorithms to demonstrate the efficacy of the various representations and their combinations. Our results across the evaluation test set gave an accuracy of 84{%} and received the first position in the final standings judged by the organizers. |
| Tasks | Community Question Answering, Question Answering |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2203/ |
| https://www.aclweb.org/anthology/S19-2203 | |
| PWC | https://paperswithcode.com/paper/fermi-at-semeval-2019-task-8-an-elementary |
| Repo | |
| Framework | |
MVP Matching: A Maximum-Value Perfect Matching for Mining Hard Samples, With Application to Person Re-Identification
| Title | MVP Matching: A Maximum-Value Perfect Matching for Mining Hard Samples, With Application to Person Re-Identification |
| Authors | Han Sun, Zhiyuan Chen, Shiyang Yan, Lin Xu |
| Abstract | How to correctly stress hard samples in metric learning is critical for visual recognition tasks, especially in challenging person re-ID applications. Pedestrians across cameras with significant appearance variations are easily confused, which could bias the learned metric and slow down the convergence rate. In this paper, we propose a novel weighted complete bipartite graph based maximum-value perfect (MVP) matching for mining the hard samples from a batch of samples. It can emphasize the hard positive and negative sample pairs respectively, and thus relieve adverse optimization and sample imbalance problems. We then develop a new batch-wise MVP matching based loss objective and combine it in an end-to-end deep metric learning manner. It leads to significant improvements in both convergence rate and recognition performance. Extensive empirical results on five person re-ID benchmark datasets, i.e., Market-1501, CUHK03-Detected, CUHK03-Labeled, Duke-MTMC, and MSMT17, demonstrate the superiority of the proposed method. It can accelerate the convergence rate significantly while achieving state-of-the-art performance. The source code of our method is available at https://github.com/IAAI-CVResearchGroup/MVP-metric. |
| Tasks | Metric Learning, Person Re-Identification |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Sun_MVP_Matching_A_Maximum-Value_Perfect_Matching_for_Mining_Hard_Samples_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Sun_MVP_Matching_A_Maximum-Value_Perfect_Matching_for_Mining_Hard_Samples_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mvp-matching-a-maximum-value-perfect-matching |
| Repo | |
| Framework | |
Cross-Sentence Transformations in Text Simplification
| Title | Cross-Sentence Transformations in Text Simplification |
| Authors | Fern Alva-Manchego, o, Carolina Scarton, Lucia Specia |
| Abstract | Current approaches to Text Simplification focus on simplifying sentences individually. However, certain simplification transformations span beyond single sentences (e.g. joining and re- ordering sentences). In this paper, we motivate the need for modelling the simplification task at the document level, and assess the performance of sequence-to-sequence neural models in this setup. We analyse parallel original-simplified documents created by professional editors and show that there are frequent rewriting transformations that are not restricted to sentence boundaries. We also propose strategies to automatically evaluate the performance of a simplification model on these cross-sentence transformations. Our experiments show the inability of standard sequence-to-sequence neural models to learn these transformations, and suggest directions towards document-level simplification. |
| Tasks | Text Simplification |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3656/ |
| https://www.aclweb.org/anthology/W19-3656 | |
| PWC | https://paperswithcode.com/paper/cross-sentence-transformations-in-text |
| Repo | |
| Framework | |
DeepGeneMD: A Joint Deep Learning Model for Extracting Gene Mutation-Disease Knowledge from PubMed Literature
| Title | DeepGeneMD: A Joint Deep Learning Model for Extracting Gene Mutation-Disease Knowledge from PubMed Literature |
| Authors | Feifan Liu, Xiaoyu Zheng, Bo Wang, Catarina Kiefe |
| Abstract | Understanding the pathogenesis of genetic diseases through different gene activities and their relations to relevant diseases is important for new drug discovery and drug repositioning. In this paper, we present a joint deep learning model in a multi-task learning paradigm for gene mutation-disease knowledge extraction, DeepGeneMD, which adapts the state-of-the-art hierarchical multi-task learning framework for joint inference on named entity recognition (NER) and relation extraction (RE) in the context of the AGAC (Active Gene Annotation Corpus) track at 2019 BioNLP Open Shared Tasks (BioNLP-OST). It simultaneously extracts gene mutation related activities, diseases, and their relations from the published scientific literature. In DeepGeneMD, we explore the task decomposition to create auxiliary subtasks so that more interactions between different learning subtasks can be leveraged in model training. Our model achieves the average F1 score of 0.45 on recognizing gene activities and disease entities, ranking 2nd in the AGAC NER task; and the average F1 score of 0.35 on extracting relations, ranking 1st in the AGAC RE task. |
| Tasks | Drug Discovery, Multi-Task Learning, Named Entity Recognition, Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5712/ |
| https://www.aclweb.org/anthology/D19-5712 | |
| PWC | https://paperswithcode.com/paper/deepgenemd-a-joint-deep-learning-model-for |
| Repo | |
| Framework | |
Not All Reviews Are Equal: Towards Addressing Reviewer Biases for Opinion Summarization
| Title | Not All Reviews Are Equal: Towards Addressing Reviewer Biases for Opinion Summarization |
| Authors | Wenyi Tay |
| Abstract | Consumers read online reviews for insights which help them to make decisions. Given the large volumes of reviews, succinct review summaries are important for many applications. Existing research has focused on mining for opinions from only review texts and largely ignores the reviewers. However, reviewers have biases and may write lenient or harsh reviews; they may also have preferences towards some topics over others. Therefore, not all reviews are equal. Ignoring the biases in reviews can generate misleading summaries. We aim for summarization of reviews to include balanced opinions from reviewers of different biases and preferences. We propose to model reviewer biases from their review texts and rating distributions, and learn a bias-aware opinion representation. We further devise an approach for balanced opinion summarization of reviews using our bias-aware opinion representation. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2005/ |
| https://www.aclweb.org/anthology/P19-2005 | |
| PWC | https://paperswithcode.com/paper/not-all-reviews-are-equal-towards-addressing |
| Repo | |
| Framework | |
On a Chatbot Conducting Dialogue-in-Dialogue
| Title | On a Chatbot Conducting Dialogue-in-Dialogue |
| Authors | Boris Galitsky, Dmitry Ilvovsky, Elizaveta Goncharova |
| Abstract | We demo a chatbot that delivers content in the form of virtual dialogues automatically produced from plain texts extracted and selected from documents. This virtual dialogue content is provided in the form of answers derived from the found and selected documents split into fragments, and questions are automatically generated for these answers. |
| Tasks | Chatbot |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5916/ |
| https://www.aclweb.org/anthology/W19-5916 | |
| PWC | https://paperswithcode.com/paper/on-a-chatbot-conducting-dialogue-in-dialogue |
| Repo | |
| Framework | |
Transformer based Grapheme-to-Phoneme Conversion
| Title | Transformer based Grapheme-to-Phoneme Conversion |
| Authors | Sevinj Yolchuyeva, Géza Németh, Bálint Gyires-Tóth |
| Abstract | Attention mechanism is one of the most successful techniques in deep learning based Natural Language Processing (NLP). The transformer network architecture is completely based on attention mechanisms, and it outperforms sequence-to-sequence models in neural machine translation without recurrent and convolutional layers. Grapheme-to-phoneme (G2P) conversion is a task of converting letters (grapheme sequence) to their pronunciations (phoneme sequence). It plays a significant role in text-to-speech (TTS) and automatic speech recognition (ASR) systems. In this paper, we investigate the application of transformer architecture to G2P conversion and compare its performance with recurrent and convolutional neural network based approaches. Phoneme and word error rates are evaluated on the CMUDict dataset for US English and the NetTalk dataset. The results show that transformer based G2P outperforms the convolutional-based approach in terms of word error rate and our results significantly exceeded previous recurrent approaches (without attention) regarding word and phoneme error rates on both datasets. Furthermore, the size of the proposed model is much smaller than the size of the previous approaches. |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2019-09-15 |
| URL | https://pdfs.semanticscholar.org/5bdd/df7eac1d872d2d720be0d28f22cf65c22d2b.pdf |
| https://pdfs.semanticscholar.org/5bdd/df7eac1d872d2d720be0d28f22cf65c22d2b.pdf | |
| PWC | https://paperswithcode.com/paper/transformer-based-grapheme-to-phoneme |
| Repo | |
| Framework | |
Meta-Learning to Guide Segmentation
| Title | Meta-Learning to Guide Segmentation |
| Authors | Kate Rakelly*, Evan Shelhamer*, Trevor Darrell, Alexei A. Efros, Sergey Levine |
| Abstract | There are myriad kinds of segmentation, and ultimately the `"right” segmentation of a given scene is in the eye of the annotator. Standard approaches require large amounts of labeled data to learn just one particular kind of segmentation. As a first step towards relieving this annotation burden, we propose the problem of guided segmentation: given varying amounts of pixel-wise labels, segment unannotated pixels by propagating supervision locally (within an image) and non-locally (across images). We propose guided networks, which extract a latent task representation—guidance—from variable amounts and classes (categories, instances, etc.) of pixel supervision and optimize our architecture end-to-end for fast, accurate, and data-efficient segmentation by meta-learning. To span the few-shot and many-shot learning regimes, we examine guidance from as little as one pixel per concept to as much as 1000+ images, and compare to full gradient optimization at both extremes. To explore generalization, we analyze guidance as a bridge between different levels of supervision to segment classes as the union of instances. Our segmentor concentrates different amounts of supervision of different types of classes into an efficient latent representation, non-locally propagates this supervision across images, and can be updated quickly and cumulatively when given more supervision. | |
| Tasks | Meta-Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJej6jR5Fm |
| https://openreview.net/pdf?id=HJej6jR5Fm | |
| PWC | https://paperswithcode.com/paper/meta-learning-to-guide-segmentation |
| Repo | |
| Framework | |
Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model
| Title | Multi-Modal Sarcasm Detection in Twitter with Hierarchical Fusion Model |
| Authors | Yitao Cai, Huiyu Cai, Xiaojun Wan |
| Abstract | Sarcasm is a subtle form of language in which people express the opposite of what is implied. Previous works of sarcasm detection focused on texts. However, more and more social media platforms like Twitter allow users to create multi-modal messages, including texts, images, and videos. It is insufficient to detect sarcasm from multi-model messages based only on texts. In this paper, we focus on multi-modal sarcasm detection for tweets consisting of texts and images in Twitter. We treat text features, image features and image attributes as three modalities and propose a multi-modal hierarchical fusion model to address this task. Our model first extracts image features and attribute features, and then leverages attribute features and bidirectional LSTM network to extract text features. Features of three modalities are then reconstructed and fused into one feature vector for prediction. We create a multi-modal sarcasm detection dataset based on Twitter. Evaluation results on the dataset demonstrate the efficacy of our proposed model and the usefulness of the three modalities. |
| Tasks | Sarcasm Detection |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1239/ |
| https://www.aclweb.org/anthology/P19-1239 | |
| PWC | https://paperswithcode.com/paper/multi-modal-sarcasm-detection-in-twitter-with |
| Repo | |
| Framework | |
Adversarial Attention Modeling for Multi-dimensional Emotion Regression
| Title | Adversarial Attention Modeling for Multi-dimensional Emotion Regression |
| Authors | Suyang Zhu, Shoushan Li, Guodong Zhou |
| Abstract | In this paper, we propose a neural network-based approach, namely Adversarial Attention Network, to the task of multi-dimensional emotion regression, which automatically rates multiple emotion dimension scores for an input text. Especially, to determine which words are valuable for a particular emotion dimension, an attention layer is trained to weight the words in an input sequence. Furthermore, adversarial training is employed between two attention layers to learn better word weights via a discriminator. In particular, a shared attention layer is incorporated to learn public word weights between two emotion dimensions. Empirical evaluation on the EMOBANK corpus shows that our approach achieves notable improvements in r-values on both EMOBANK Reader{'}s and Writer{'}s multi-dimensional emotion regression tasks in all domains over the state-of-the-art baselines. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1045/ |
| https://www.aclweb.org/anthology/P19-1045 | |
| PWC | https://paperswithcode.com/paper/adversarial-attention-modeling-for-multi |
| Repo | |
| Framework | |
