Paper Group NANR 162
Session-level Language Modeling for Conversational Speech. Generation of a Spanish Artificial Collocation Error Corpus. Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications. Proceedings of the 2nd Workshop on Abusive Language Online (ALW2). Classification of Tweets about Reported Events using Neural …
Session-level Language Modeling for Conversational Speech
| Title | Session-level Language Modeling for Conversational Speech |
| Authors | Wayne Xiong, Lingfeng Wu, Jun Zhang, Andreas Stolcke |
| Abstract | We propose to generalize language models for conversational speech recognition to allow them to operate across utterance boundaries and speaker changes, thereby capturing conversation-level phenomena such as adjacency pairs, lexical entrainment, and topical coherence. The model consists of a long-short-term memory (LSTM) recurrent network that reads the entire word-level history of a conversation, as well as information about turn taking and speaker overlap, in order to predict each next word. The model is applied in a rescoring framework, where the word history prior to the current utterance is approximated with preliminary recognition results. In experiments in the conversational telephone speech domain (Switchboard) we find that such a model gives substantial perplexity reductions over a standard LSTM-LM with utterance scope, as well as improvements in word error rate. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1296/ |
| https://www.aclweb.org/anthology/D18-1296 | |
| PWC | https://paperswithcode.com/paper/session-level-language-modeling-for |
| Repo | |
| Framework | |
Generation of a Spanish Artificial Collocation Error Corpus
| Title | Generation of a Spanish Artificial Collocation Error Corpus |
| Authors | Sara Rodr{'\i}guez-Fern{'a}ndez, Roberto Carlini, Leo Wanner |
| Abstract | |
| Tasks | Grammatical Error Detection |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1400/ |
| https://www.aclweb.org/anthology/L18-1400 | |
| PWC | https://paperswithcode.com/paper/generation-of-a-spanish-artificial |
| Repo | |
| Framework | |
Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications
| Title | Proceedings of the Thirteenth Workshop on Innovative Use of NLP for Building Educational Applications |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0500/ |
| https://www.aclweb.org/anthology/W18-0500 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-thirteenth-workshop-on |
| Repo | |
| Framework | |
Proceedings of the 2nd Workshop on Abusive Language Online (ALW2)
| Title | Proceedings of the 2nd Workshop on Abusive Language Online (ALW2) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5100/ |
| https://www.aclweb.org/anthology/W18-5100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-workshop-on-abusive |
| Repo | |
| Framework | |
Classification of Tweets about Reported Events using Neural Networks
| Title | Classification of Tweets about Reported Events using Neural Networks |
| Authors | Kiminobu Makino, Yuka Takei, Taro Miyazaki, Jun Goto |
| Abstract | We developed a system that automatically extracts {}Event-describing Tweets{''} which include incidents or accidents information for creating news reports. Event-describing Tweets can be classified into {}Reported-event Tweets{''} and {``}New-information Tweets.{''} Reported-event Tweets cite news agencies or user generated content sites, and New-information Tweets are other Event-describing Tweets. A system is needed to classify them so that creators of factual TV programs can use them in their productions. Proposing this Tweet classification task is one of the contributions of this paper, because no prior papers have used the same task even though program creators and other events information collectors have to do it to extract required information from social networking sites. To classify Tweets in this task, this paper proposes a method to input and concatenate character and word sequences in Japanese Tweets by using convolutional neural networks. This proposed method is another contribution of this paper. For comparison, character or word input methods and other neural networks are also used. Results show that a system using the proposed method and architectures can classify Tweets with an F1 score of 88 {%}. | |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6121/ |
| https://www.aclweb.org/anthology/W18-6121 | |
| PWC | https://paperswithcode.com/paper/classification-of-tweets-about-reported |
| Repo | |
| Framework | |
Efficient nonmyopic batch active search
| Title | Efficient nonmyopic batch active search |
| Authors | Shali Jiang, Gustavo Malkomes, Matthew Abbott, Benjamin Moseley, Roman Garnett |
| Abstract | Active search is a learning paradigm for actively identifying as many members of a given class as possible. A critical target scenario is high-throughput screening for scientific discovery, such as drug or materials discovery. In these settings, specialized instruments can often evaluate \emph{multiple} points simultaneously; however, all existing work on active search focuses on sequential acquisition. We bridge this gap, addressing batch active search from both the theoretical and practical perspective. We first derive the Bayesian optimal policy for this problem, then prove a lower bound on the performance gap between sequential and batch optimal policies: the ``cost of parallelization.’’ We also propose novel, efficient batch policies inspired by state-of-the-art sequential policies, and develop an aggressive pruning technique that can dramatically speed up computation. We conduct thorough experiments on data from three application domains: a citation network, material science, and drug discovery, testing all proposed policies (14 total) with a wide range of batch sizes. Our results demonstrate that the empirical performance gap matches our theoretical bound, that nonmyopic policies usually significantly outperform myopic alternatives, and that diversity is an important consideration for batch policy design. | |
| Tasks | Drug Discovery |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7387-efficient-nonmyopic-batch-active-search |
| http://papers.nips.cc/paper/7387-efficient-nonmyopic-batch-active-search.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-nonmyopic-batch-active-search |
| Repo | |
| Framework | |
Assisted Lexical Simplification for French Native Children with Reading Difficulties
| Title | Assisted Lexical Simplification for French Native Children with Reading Difficulties |
| Authors | Firas Hmida, Mokhtar B. Billami, Thomas Fran{\c{c}}ois, N{'u}ria Gala |
| Abstract | |
| Tasks | Lexical Simplification, Text Simplification |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-7004/ |
| https://www.aclweb.org/anthology/W18-7004 | |
| PWC | https://paperswithcode.com/paper/assisted-lexical-simplification-for-french |
| Repo | |
| Framework | |
Hierarchical Recurrent Attention Networks for Structured Online Maps
| Title | Hierarchical Recurrent Attention Networks for Structured Online Maps |
| Authors | Namdar Homayounfar, Wei-Chiu Ma, Shrinidhi Kowshika Lakshmikanth, Raquel Urtasun |
| Abstract | In this paper, we tackle the problem of online road network extraction from sparse 3D point clouds. Our method is inspired by how an annotator builds a lane graph, by first identifying how many lanes there are and then drawing each one in turn. We develop a hierarchical recurrent network that attends to initial regions of a lane boundary and traces them out completely by outputting a structured polyline. We also propose a novel differentiable loss function that measures the deviation of the edges of the ground truth polylines and their predictions. This is more suitable than distances on vertices, as there exists many ways to draw equivalent polylines. We demonstrate the effectiveness of our method on a 90 km stretch of highway, and show that we can recover the right topology 92% of the time. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Homayounfar_Hierarchical_Recurrent_Attention_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Homayounfar_Hierarchical_Recurrent_Attention_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-recurrent-attention-networks-for |
| Repo | |
| Framework | |
Merging Datasets for Aggressive Text Identification
| Title | Merging Datasets for Aggressive Text Identification |
| Authors | Paula Fortuna, Jos{'e} Ferreira, Luiz Pires, Guilherme Routar, S{'e}rgio Nunes |
| Abstract | This paper presents the approach of the team {``}groutar{''} to the shared task on Aggression Identification, considering the test sets in English, both from Facebook and general Social Media. This experiment aims to test the effect of merging new datasets in the performance of classification models. We followed a standard machine learning approach with training, validation, and testing phases, and considered features such as part-of-speech, frequencies of insults, punctuation, sentiment, and capitalization. In terms of algorithms, we experimented with Boosted Logistic Regression, Multi-Layer Perceptron, Parallel Random Forest and eXtreme Gradient Boosting. One question appearing was how to merge datasets using different classification systems (e.g. aggression vs. toxicity). Other issue concerns the possibility to generalize models and apply them to data from different social networks. Regarding these, we merged two datasets, and the results showed that training with similar data is an advantage in the classification of social networks data. However, adding data from different platforms, allowed slightly better results in both Facebook and Social Media, indicating that more generalized models can be an advantage. | |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4416/ |
| https://www.aclweb.org/anthology/W18-4416 | |
| PWC | https://paperswithcode.com/paper/merging-datasets-for-aggressive-text |
| Repo | |
| Framework | |
Sheffield Submissions for the WMT18 Quality Estimation Shared Task
| Title | Sheffield Submissions for the WMT18 Quality Estimation Shared Task |
| Authors | Julia Ive, Carolina Scarton, Fr{'e}d{'e}ric Blain, Lucia Specia |
| Abstract | In this paper we present the University of Sheffield submissions for the WMT18 Quality Estimation shared task. We discuss our submissions to all four sub-tasks, where ours is the only team to participate in all language pairs and variations (37 combinations). Our systems show competitive results and outperform the baseline in nearly all cases. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6463/ |
| https://www.aclweb.org/anthology/W18-6463 | |
| PWC | https://paperswithcode.com/paper/sheffield-submissions-for-the-wmt18-quality |
| Repo | |
| Framework | |
Self-Supervised Learning of Object Motion Through Adversarial Video Prediction
| Title | Self-Supervised Learning of Object Motion Through Adversarial Video Prediction |
| Authors | Alex X. Lee, Frederik Ebert, Richard Zhang, Chelsea Finn, Pieter Abbeel, Sergey Levine |
| Abstract | Can we build models that automatically learn about object motion from raw, unlabeled videos? In this paper, we study the problem of multi-step video prediction, where the goal is to predict a sequence of future frames conditioned on a short context. We focus specifically on two aspects of video prediction: accurately modeling object motion, and producing naturalistic image predictions. Our model is based on a flow-based generator network with a discriminator used to improve prediction quality. The implicit flow in the generator can be examined to determine its accuracy, and the predicted images can be evaluated for image quality. We argue that these two metrics are critical for understanding whether the model has effectively learned object motion, and propose a novel evaluation benchmark based on ground truth object flow. Our network achieves state-of-the-art results in terms of both the realism of the predicted images, as determined by human judges, and the accuracy of the predicted flow. Videos and full results can be viewed on the supplementary website: \url{https://sites.google.com/site/omvideoprediction}. |
| Tasks | Video Prediction |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=HJrJpzZRZ |
| https://openreview.net/pdf?id=HJrJpzZRZ | |
| PWC | https://paperswithcode.com/paper/self-supervised-learning-of-object-motion |
| Repo | |
| Framework | |
Cyberbullying Detection Task: the EBSI-LIA-UNAM System (ELU) at COLING’18 TRAC-1
| Title | Cyberbullying Detection Task: the EBSI-LIA-UNAM System (ELU) at COLING’18 TRAC-1 |
| Authors | Ignacio Arroyo-Fern{'a}ndez, Dominic Forest, Juan-Manuel Torres-Moreno, Mauricio Carrasco-Ruiz, Thomas Legeleux, Karen Joannette |
| Abstract | The phenomenon of cyberbullying has growing in worrying proportions with the development of social networks. Forums and chat rooms are spaces where serious damage can now be done to others, while the tools for avoiding on-line spills are still limited. This study aims to assess the ability that both classical and state-of-the-art vector space modeling methods provide to well known learning machines to identify aggression levels in social network cyberbullying (i.e. social network posts manually labeled as Overtly Aggressive, Covertly Aggressive and Non-aggressive). To this end, an exploratory stage was performed first in order to find relevant settings to test, i.e. by using training and development samples, we trained multiple learning machines using multiple vector space modeling methods and discarded the less informative configurations. Finally, we selected the two best settings and their voting combination to form three competing systems. These systems were submitted to the competition of the TRACK-1 task of the Workshop on Trolling, Aggression and Cyberbullying. Our voting combination system resulted second place in predicting Aggression levels on a test set of untagged social network posts. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4417/ |
| https://www.aclweb.org/anthology/W18-4417 | |
| PWC | https://paperswithcode.com/paper/cyberbullying-detection-task-the-ebsi-lia |
| Repo | |
| Framework | |
Improving Moderation of Online Discussions via Interpretable Neural Models
| Title | Improving Moderation of Online Discussions via Interpretable Neural Models |
| Authors | Andrej {\v{S}}vec, Mat{'u}{\v{s}} Pikuliak, Mari{'a}n {\v{S}}imko, M{'a}ria Bielikov{'a} |
| Abstract | Growing amount of comments make online discussions difficult to moderate by human moderators only. Antisocial behavior is a common occurrence that often discourages other users from participating in discussion. We propose a neural network based method that partially automates the moderation process. It consists of two steps. First, we detect inappropriate comments for moderators to see. Second, we highlight inappropriate parts within these comments to make the moderation faster. We evaluated our method on data from a major Slovak news discussion platform. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5108/ |
| https://www.aclweb.org/anthology/W18-5108 | |
| PWC | https://paperswithcode.com/paper/improving-moderation-of-online-discussions-1 |
| Repo | |
| Framework | |
A LSTM Approach with Sub-Word Embeddings for Mongolian Phrase Break Prediction
| Title | A LSTM Approach with Sub-Word Embeddings for Mongolian Phrase Break Prediction |
| Authors | Rui Liu, Feilong Bao, Guanglai Gao, Hui Zhang, Yonghe Wang |
| Abstract | In this paper, we first utilize the word embedding that focuses on sub-word units to the Mongolian Phrase Break (PB) prediction task by using Long-Short-Term-Memory (LSTM) model. Mongolian is an agglutinative language. Each root can be followed by several suffixes to form probably millions of words, but the existing Mongolian corpus is not enough to build a robust entire word embedding, thus it suffers a serious data sparse problem and brings a great difficulty for Mongolian PB prediction. To solve this problem, we look at sub-word units in Mongolian word, and encode their information to a meaningful representation, then fed it to LSTM to decode the best corresponding PB label. Experimental results show that the proposed model significantly outperforms traditional CRF model using manually features and obtains 7.49{%} F-Measure gain. |
| Tasks | Dictionary Learning, Machine Translation, Question Answering, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1207/ |
| https://www.aclweb.org/anthology/C18-1207 | |
| PWC | https://paperswithcode.com/paper/a-lstm-approach-with-sub-word-embeddings-for |
| Repo | |
| Framework | |
The Effects of User Features on Twitter Hate Speech Detection
| Title | The Effects of User Features on Twitter Hate Speech Detection |
| Authors | Elise Fehn Unsv{\aa}g, Bj{"o}rn Gamb{"a}ck |
| Abstract | The paper investigates the potential effects user features have on hate speech classification. A quantitative analysis of Twitter data was conducted to better understand user characteristics, but no correlations were found between hateful text and the characteristics of the users who had posted it. However, experiments with a hate speech classifier based on datasets from three different languages showed that combining certain user features with textual features gave slight improvements of classification performance. While the incorporation of user features resulted in varying impact on performance for the different datasets used, user network-related features provided the most consistent improvements. |
| Tasks | Hate Speech Detection, Text Classification |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5110/ |
| https://www.aclweb.org/anthology/W18-5110 | |
| PWC | https://paperswithcode.com/paper/the-effects-of-user-features-on-twitter-hate |
| Repo | |
| Framework | |
