Paper Group NANR 110
Using contextual information for automatic triage of posts in a peer-support forum. Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained Classification. A Real-life, French-accented Corpus of Air Traffic Control Communications. Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled …
Using contextual information for automatic triage of posts in a peer-support forum
| Title | Using contextual information for automatic triage of posts in a peer-support forum |
| Authors | Edgar Altszyler, Ariel J. Berenstein, David Milne, Rafael A. Calvo, Fern, Diego ez Slezak |
| Abstract | Mental health forums are online spaces where people can share their experiences anonymously and get peer support. These forums, require the supervision of moderators to provide support in delicate cases, such as posts expressing suicide ideation. The large increase in the number of forum users makes the task of the moderators unmanageable without the help of automatic triage systems. In the present paper, we present a Machine Learning approach for the triage of posts. Most approaches in the literature focus on the content of the posts, but only a few authors take advantage of features extracted from the context in which they appear. Our approach consists of the development and implementation of a large variety of new features from both, the content and the context of posts, such as previous messages, interaction with other users and author{'}s history. Our method has competed in the CLPsych 2017 Shared Task, obtaining the first place for several of the subtasks. Moreover, we also found that models that take advantage of post context improve significantly its performance in the detection of flagged posts (posts that require moderators attention), as well as those that focus on post content outperforms in the detection of most urgent events. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0606/ |
| https://www.aclweb.org/anthology/W18-0606 | |
| PWC | https://paperswithcode.com/paper/using-contextual-information-for-automatic |
| Repo | |
| Framework | |
Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained Classification
| Title | Webly Supervised Learning Meets Zero-Shot Learning: A Hybrid Approach for Fine-Grained Classification |
| Authors | Li Niu, Ashok Veeraraghavan, Ashutosh Sabharwal |
| Abstract | Fine-grained image classification, which targets at distinguishing subtle distinctions among various subordinate categories, remains a very difficult task due to the high annotation cost of enormous fine-grained categories. To cope with the scarcity of well-labeled training images, existing works mainly follow two research directions: 1) utilize freely available web images without human annotation; 2) only annotate some fine-grained categories and transfer the knowledge to other fine-grained categories, which falls into the scope of zero-shot learning (ZSL). However, the above two directions have their own drawbacks. For the first direction, the labels of web images are very noisy and the data distribution between web images and test images are considerably different. For the second direction, the performance gap between ZSL and traditional supervised learning is still very large. The drawbacks of the above two directions motivate us to design a new framework which can jointly leverage both web data and auxiliary labeled categories to predict the test categories that are not associated with any well-labeled training images. Comprehensive experiments on three benchmark datasets demonstrate the effectiveness of our proposed framework. |
| Tasks | Fine-Grained Image Classification, Image Classification, Zero-Shot Learning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Niu_Webly_Supervised_Learning_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Niu_Webly_Supervised_Learning_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/webly-supervised-learning-meets-zero-shot |
| Repo | |
| Framework | |
A Real-life, French-accented Corpus of Air Traffic Control Communications
| Title | A Real-life, French-accented Corpus of Air Traffic Control Communications |
| Authors | Estelle Delpech, Marion Laignelet, Christophe Pimm, C{'e}line Raynal, Michal Trzos, Alex Arnold, re, Dominique Pronto |
| Abstract | |
| Tasks | Speech Recognition |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1453/ |
| https://www.aclweb.org/anthology/L18-1453 | |
| PWC | https://paperswithcode.com/paper/a-real-life-french-accented-corpus-of-air |
| Repo | |
| Framework | |
Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled Diversity
| Title | Minimax Curriculum Learning: Machine Teaching with Desirable Difficulties and Scheduled Diversity |
| Authors | Tianyi Zhou, Jeff Bilmes |
| Abstract | We introduce and study minimax curriculum learning (MCL), a new method for adaptively selecting a sequence of training subsets for a succession of stages in machine learning. The subsets are encouraged to be small and diverse early on, and then larger, harder, and allowably more homogeneous in later stages. At each stage, model weights and training sets are chosen by solving a joint continuous-discrete minimax optimization, whose objective is composed of a continuous loss (reflecting training set hardness) and a discrete submodular promoter of diversity for the chosen subset. MCL repeatedly solves a sequence of such optimizations with a schedule of increasing training set size and decreasing pressure on diversity encouragement. We reduce MCL to the minimization of a surrogate function handled by submodular maximization and continuous gradient methods. We show that MCL achieves better performance and, with a clustering trick, uses fewer labeled samples for both shallow and deep models while achieving the same performance. Our method involves repeatedly solving constrained submodular maximization of an only slowly varying function on the same ground set. Therefore, we develop a heuristic method that utilizes the previous submodular maximization solution as a warm start for the current submodular maximization process to reduce computation while still yielding a guarantee. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=BywyFQlAW |
| https://openreview.net/pdf?id=BywyFQlAW | |
| PWC | https://paperswithcode.com/paper/minimax-curriculum-learning-machine-teaching |
| Repo | |
| Framework | |
Deep Learning for Depression Detection of Twitter Users
| Title | Deep Learning for Depression Detection of Twitter Users |
| Authors | Ahmed Husseini Orabi, Prasadith Buddhitha, Mahmoud Husseini Orabi, Diana Inkpen |
| Abstract | Mental illness detection in social media can be considered a complex task, mainly due to the complicated nature of mental disorders. In recent years, this research area has started to evolve with the continuous increase in popularity of social media platforms that became an integral part of people{'}s life. This close relationship between social media platforms and their users has made these platforms to reflect the users{'} personal life with different limitations. In such an environment, researchers are presented with a wealth of information regarding one{'}s life. In addition to the level of complexity in identifying mental illnesses through social media platforms, adopting supervised machine learning approaches such as deep neural networks have not been widely accepted due to the difficulties in obtaining sufficient amounts of annotated training data. Due to these reasons, we try to identify the most effective deep neural network architecture among a few of selected architectures that were successfully used in natural language processing tasks. The chosen architectures are used to detect users with signs of mental illnesses (depression in our case) given limited unstructured text data extracted from the Twitter social media platform. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0609/ |
| https://www.aclweb.org/anthology/W18-0609 | |
| PWC | https://paperswithcode.com/paper/deep-learning-for-depression-detection-of |
| Repo | |
| Framework | |
Adopting the Word-Pair-Dependency-Triplets with Individual Comparison for Natural Language Inference
| Title | Adopting the Word-Pair-Dependency-Triplets with Individual Comparison for Natural Language Inference |
| Authors | Qianlong Du, Chengqing Zong, Keh-Yih Su |
| Abstract | This paper proposes to perform natural language inference with Word-Pair-Dependency-Triplets. Most previous DNN-based approaches either ignore syntactic dependency among words, or directly use tree-LSTM to generate sentence representation with irrelevant information. To overcome the problems mentioned above, we adopt Word-Pair-Dependency-Triplets to improve alignment and inference judgment. To be specific, instead of comparing each triplet from one passage with the merged information of another passage, we first propose to perform comparison directly between the triplets of the given passage-pair to make the judgement more interpretable. Experimental results show that the performance of our approach is better than most of the approaches that use tree structures, and is comparable to other state-of-the-art approaches. |
| Tasks | Decision Making, Machine Translation, Natural Language Inference, Question Answering, Text Summarization |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1035/ |
| https://www.aclweb.org/anthology/C18-1035 | |
| PWC | https://paperswithcode.com/paper/adopting-the-word-pair-dependency-triplets |
| Repo | |
| Framework | |
Transliteration Better than Translation? Answering Code-mixed Questions over a Knowledge Base
| Title | Transliteration Better than Translation? Answering Code-mixed Questions over a Knowledge Base |
| Authors | Vishal Gupta, Manoj Chinnakotla, Manish Shrivastava |
| Abstract | Humans can learn multiple languages. If they know a fact in one language, they can answer a question in another language they understand. They can also answer Code-mix (CM) questions: questions which contain both languages. This behavior is attributed to the unique learning ability of humans. Our task aims to study if machines can achieve this. We demonstrate how effectively a machine can answer CM questions. In this work, we adopt a two phase approach: candidate generation and candidate re-ranking to answer questions. We propose a Triplet-Siamese-Hybrid CNN (TSHCNN) to re-rank candidate answers. We show experiments on the SimpleQuestions dataset. Our network is trained only on English questions provided in this dataset and noisy Hindi translations of these questions and can answer English-Hindi CM questions effectively without the need of translation into English. Back-transliterated CM questions outperform their lexical and sentence level translated counterparts by 5{%} {&} 35{%} in accuracy respectively, highlighting the efficacy of our approach in a resource constrained setting. |
| Tasks | Information Retrieval, Language Identification, Machine Translation, Part-Of-Speech Tagging, Question Answering, Reading Comprehension, Speech Recognition, Transliteration |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3205/ |
| https://www.aclweb.org/anthology/W18-3205 | |
| PWC | https://paperswithcode.com/paper/transliteration-better-than-translation |
| Repo | |
| Framework | |
Phrase-Based & Neural Unsupervised Machine Translation
| Title | Phrase-Based & Neural Unsupervised Machine Translation |
| Authors | Guillaume Lample, Myle Ott, Alexis Conneau, Ludovic Denoyer, Marc{'}Aurelio Ranzato |
| Abstract | Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of language pairs. This work investigates how to learn to translate when having access to only large monolingual corpora in each language. We propose two model variants, a neural and a phrase-based model. Both versions leverage a careful initialization of the parameters, the denoising effect of language models and automatic generation of parallel data by iterative back-translation. These models are significantly better than methods from the literature, while being simpler and having fewer hyper-parameters. On the widely used WMT{'}14 English-French and WMT{'}16 German-English benchmarks, our models respectively obtain 28.1 and 25.2 BLEU points without using a single parallel sentence, outperforming the state of the art by more than 11 BLEU points. On low-resource languages like English-Urdu and English-Romanian, our methods achieve even better results than semi-supervised and supervised approaches leveraging the paucity of available bitexts. Our code for NMT and PBSMT is publicly available. |
| Tasks | Denoising, Machine Translation, Unsupervised Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1549/ |
| https://www.aclweb.org/anthology/D18-1549 | |
| PWC | https://paperswithcode.com/paper/phrase-based-neural-unsupervised-machine-1 |
| Repo | |
| Framework | |
Lessons Learned: On the Challenges of Migrating a Research Data Repository from a Research Institution to a University Library.
| Title | Lessons Learned: On the Challenges of Migrating a Research Data Repository from a Research Institution to a University Library. |
| Authors | Thorsten Trippel, Claus Zinn |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1023/ |
| https://www.aclweb.org/anthology/L18-1023 | |
| PWC | https://paperswithcode.com/paper/lessons-learned-on-the-challenges-of |
| Repo | |
| Framework | |
Adversarial Training for Multi-task and Multi-lingual Joint Modeling of Utterance Intent Classification
| Title | Adversarial Training for Multi-task and Multi-lingual Joint Modeling of Utterance Intent Classification |
| Authors | Ryo Masumura, Yusuke Shinohara, Ryuichiro Higashinaka, Yushi Aono |
| Abstract | This paper proposes an adversarial training method for the multi-task and multi-lingual joint modeling needed for utterance intent classification. In joint modeling, common knowledge can be efficiently utilized among multiple tasks or multiple languages. This is achieved by introducing both language-specific networks shared among different tasks and task-specific networks shared among different languages. However, the shared networks are often specialized in majority tasks or languages, so performance degradation must be expected for some minor data sets. In order to improve the invariance of shared networks, the proposed method introduces both language-specific task adversarial networks and task-specific language adversarial networks; both are leveraged for purging the task or language dependencies of the shared networks. The effectiveness of the adversarial training proposal is demonstrated using Japanese and English data sets for three different utterance intent classification tasks. |
| Tasks | Intent Classification, Spoken Dialogue Systems |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1064/ |
| https://www.aclweb.org/anthology/D18-1064 | |
| PWC | https://paperswithcode.com/paper/adversarial-training-for-multi-task-and-multi |
| Repo | |
| Framework | |
Predicting Psychological Health from Childhood Essays. The UGent-IDLab CLPsych 2018 Shared Task System.
| Title | Predicting Psychological Health from Childhood Essays. The UGent-IDLab CLPsych 2018 Shared Task System. |
| Authors | Klim Zaporojets, Lucas Sterckx, Johannes Deleu, Thomas Demeester, Chris Develder |
| Abstract | This paper describes the IDLab system submitted to Task A of the CLPsych 2018 shared task. The goal of this task is predicting psychological health of children based on language used in hand-written essays and socio-demographic control variables. Our entry uses word- and character-based features as well as lexicon-based features and features derived from the essays such as the quality of the language. We apply linear models, gradient boosting as well as neural-network based regressors (feed-forward, CNNs and RNNs) to predict scores. We then make ensembles of our best performing models using a weighted average. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0613/ |
| https://www.aclweb.org/anthology/W18-0613 | |
| PWC | https://paperswithcode.com/paper/predicting-psychological-health-from |
| Repo | |
| Framework | |
Compositional Learning for Human Object Interaction
| Title | Compositional Learning for Human Object Interaction |
| Authors | Keizo Kato, Yin Li, Abhinav Gupta |
| Abstract | The world of human-object interactions is rich. While generally we sit on chairs and sofas, if need be we can even sit on TVs or top of shelves. In recent years, there has been progress in modeling actions and human-object interactions. However, most of these approaches require lots of data. It is not clear if the learned representations of actions are generalizable to new categories. In this paper, we explore the problem of zero-shot learning of human-object interactions. Given limited verb-noun interactions in training data, we want to learn a model than can work even on unseen combinations. To deal with this problem, In this paper, we propose a novel method using external knowledge graph and graph convolutional networks which learns how to compose classifiers for verb-noun pairs. We also provide benchmarks on several dataset for zero-shot learning including both image and video. We hope our method, dataset and baselines will facilitate future research in this direction. |
| Tasks | Human-Object Interaction Detection, Zero-Shot Learning |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Keizo_Kato_Compositional_Learning_of_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Keizo_Kato_Compositional_Learning_of_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/compositional-learning-for-human-object |
| Repo | |
| Framework | |
Automated Acquisition of Patterns for Coding Political Event Data: Two Case Studies
| Title | Automated Acquisition of Patterns for Coding Political Event Data: Two Case Studies |
| Authors | Peter Makarov |
| Abstract | We present a simple approach to the generation and labeling of extraction patterns for coding political event data, an important task in computational social science. We use weak supervision to identify pattern candidates and learn distributed representations for them. Given seed extraction patterns from existing pattern dictionaries, we use label propagation to label pattern candidates. We present two case studies. i) We derive patterns of acceptable quality for a number of international relations {&} conflicts categories using pattern candidates of O{'}Connor et al (2013). ii) We derive patterns for coding protest events that outperform an established set of Tabari / Petrarch hand-crafted patterns. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4512/ |
| https://www.aclweb.org/anthology/W18-4512 | |
| PWC | https://paperswithcode.com/paper/automated-acquisition-of-patterns-for-coding |
| Repo | |
| Framework | |
Sentiment analysis under temporal shift
| Title | Sentiment analysis under temporal shift |
| Authors | Jan Lukes, Anders S{\o}gaard |
| Abstract | Sentiment analysis models often rely on training data that is several years old. In this paper, we show that lexical features change polarity over time, leading to degrading performance. This effect is particularly strong in sparse models relying only on highly predictive features. Using predictive feature selection, we are able to significantly improve the accuracy of such models over time. |
| Tasks | Feature Selection, Sentiment Analysis |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6210/ |
| https://www.aclweb.org/anthology/W18-6210 | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-under-temporal-shift |
| Repo | |
| Framework | |
Multi-source synthetic treebank creation for improved cross-lingual dependency parsing
| Title | Multi-source synthetic treebank creation for improved cross-lingual dependency parsing |
| Authors | Francis Tyers, Mariya Sheyanova, Aleks Martynova, ra, Pavel Stepachev, Konstantin Vinogorodskiy |
| Abstract | This paper describes a method of creating synthetic treebanks for cross-lingual dependency parsing using a combination of machine translation (including pivot translation), annotation projection and the spanning tree algorithm. Sentences are first automatically translated from a lesser-resourced language to a number of related highly-resourced languages, parsed and then the annotations are projected back to the lesser-resourced language, leading to multiple trees for each sentence from the lesser-resourced language. The final treebank is created by merging the possible trees into a graph and running the spanning tree algorithm to vote for the best tree for each sentence. We present experiments aimed at parsing Faroese using a combination of Danish, Swedish and Norwegian. In a similar experimental setup to the CoNLL 2018 shared task on dependency parsing we report state-of-the-art results on dependency parsing for Faroese using an off-the-shelf parser. |
| Tasks | Dependency Parsing, Machine Translation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6017/ |
| https://www.aclweb.org/anthology/W18-6017 | |
| PWC | https://paperswithcode.com/paper/multi-source-synthetic-treebank-creation-for |
| Repo | |
| Framework | |
