Paper Group NANR 119
Observational Comparison of Geo-tagged and Randomly-drawn Tweets. On the Importance of Label Quality for Semantic Segmentation. Target Foresight Based Attention for Neural Machine Translation. Interoperability of Language-related Information: Mapping the BLL Thesaurus to Lexvo and Glottolog. Learning to play slot cars and Atari 2600 games in just m …
Observational Comparison of Geo-tagged and Randomly-drawn Tweets
| Title | Observational Comparison of Geo-tagged and Randomly-drawn Tweets |
| Authors | Tom Lippincott, Annabelle Carrell |
| Abstract | Twitter is a ubiquitous source of micro-blog social media data, providing the academic, industrial, and public sectors real-time access to actionable information. A particularly attractive property of some tweets is geo-tagging, where a user account has opted-in to attaching their current location to each message. Unfortunately (from a researcher{'}s perspective) only a fraction of Twitter accounts agree to this, and these accounts are likely to have systematic diffences with the general population. This work is an exploratory study of these differences across the full range of Twitter content, and complements previous studies that focus on the English-language subset. Additionally, we compare methods for querying users by self-identified properties, finding that the constrained semantics of the {``}description{''} field provides cleaner, higher-volume results than more complex regular expressions. | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1107/ |
| https://www.aclweb.org/anthology/W18-1107 | |
| PWC | https://paperswithcode.com/paper/observational-comparison-of-geo-tagged-and |
| Repo | |
| Framework | |
On the Importance of Label Quality for Semantic Segmentation
| Title | On the Importance of Label Quality for Semantic Segmentation |
| Authors | Aleksandar Zlateski, Ronnachai Jaroensri, Prafull Sharma, Frédo Durand |
| Abstract | Convolutional networks (ConvNets) have become the dominant approach to semantic image segmentation. Producing accurate, pixel–level labels required for this task is a tedious and time consuming process; however, producing approximate, coarse labels could take only a fraction of the time and effort. We investigate the relationship between the quality of labels and the performance of ConvNets for semantic segmentation. We create a very large synthetic dataset with perfectly labeled street view scenes. From these perfect labels, we synthetically coarsen labels with different qualities and estimate human–hours required for producing them. We perform a series of experiments by training ConvNets with a varying number of training images and label quality. We found that the performance of ConvNets mostly depends on the time spent creating the training labels. That is, a larger coarsely–annotated dataset can yield the same performance as a smaller finely–annotated one. Furthermore, fine–tuning coarsely pre–trained ConvNets with few finely-annotated labels can yield comparable or superior performance to training it with a large amount of finely-annotated labels alone, at a fraction of the labeling cost. We demonstrate that our result is also valid for different network architectures, and various object classes in an urban scene. |
| Tasks | Semantic Segmentation |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Zlateski_On_the_Importance_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Zlateski_On_the_Importance_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-importance-of-label-quality-for |
| Repo | |
| Framework | |
Target Foresight Based Attention for Neural Machine Translation
| Title | Target Foresight Based Attention for Neural Machine Translation |
| Authors | Xintong Li, Lemao Liu, Zhaopeng Tu, Shuming Shi, Max Meng |
| Abstract | In neural machine translation, an attention model is used to identify the aligned source words for a target word (target foresight word) in order to select translation context, but it does not make use of any information of this target foresight word at all. Previous work proposed an approach to improve the attention model by explicitly accessing this target foresight word and demonstrated the substantial gains in alignment task. However, this approach is useless in machine translation task on which the target foresight word is unavailable. In this paper, we propose a new attention model enhanced by the implicit information of target foresight word oriented to both alignment and translation tasks. Empirical experiments on Chinese-to-English and Japanese-to-English datasets show that the proposed attention model delivers significant improvements in terms of both alignment error rate and BLEU. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1125/ |
| https://www.aclweb.org/anthology/N18-1125 | |
| PWC | https://paperswithcode.com/paper/target-foresight-based-attention-for-neural |
| Repo | |
| Framework | |
Interoperability of Language-related Information: Mapping the BLL Thesaurus to Lexvo and Glottolog
| Title | Interoperability of Language-related Information: Mapping the BLL Thesaurus to Lexvo and Glottolog |
| Authors | Vanya Dimitrova, Christian F{"a}th, Christian Chiarcos, Heike Renner-Westermann, Frank Abromeit |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1721/ |
| https://www.aclweb.org/anthology/L18-1721 | |
| PWC | https://paperswithcode.com/paper/interoperability-of-language-related |
| Repo | |
| Framework | |
Learning to play slot cars and Atari 2600 games in just minutes
| Title | Learning to play slot cars and Atari 2600 games in just minutes |
| Authors | Lionel Cordesses, Omar Bentahar, Julien Page |
| Abstract | Machine learning algorithms for controlling devices will need to learn quickly, with few trials. Such a goal can be attained with concepts borrowed from continental philosophy and formalized using tools from the mathematical theory of categories. Illustrations of this approach are presented on a cyberphysical system: the slot car game, and also on Atari 2600 games. |
| Tasks | Atari Games |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SyF7Erp6W |
| https://openreview.net/pdf?id=SyF7Erp6W | |
| PWC | https://paperswithcode.com/paper/learning-to-play-slot-cars-and-atari-2600 |
| Repo | |
| Framework | |
AnlamVer: Semantic Model Evaluation Dataset for Turkish - Word Similarity and Relatedness
| Title | AnlamVer: Semantic Model Evaluation Dataset for Turkish - Word Similarity and Relatedness |
| Authors | G{"o}khan Ercan, Olcay Taner Y{\i}ld{\i}z |
| Abstract | In this paper, we present AnlamVer, which is a semantic model evaluation dataset for Turkish designed to evaluate word similarity and word relatedness tasks while discriminating those two relations from each other. Our dataset consists of 500 word-pairs annotated by 12 human subjects, and each pair has two distinct scores for similarity and relatedness. Word-pairs are selected to enable the evaluation of distributional semantic models by multiple attributes of words and word-pair relations such as frequency, morphology, concreteness and relation types (e.g., synonymy, antonymy). Our aim is to provide insights to semantic model researchers by evaluating models in multiple attributes. We balance dataset word-pairs by their frequencies to evaluate the robustness of semantic models concerning out-of-vocabulary and rare words problems, which are caused by the rich derivational and inflectional morphology of the Turkish language. |
| Tasks | Machine Translation, Named Entity Recognition, Word Sense Disambiguation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1323/ |
| https://www.aclweb.org/anthology/C18-1323 | |
| PWC | https://paperswithcode.com/paper/anlamver-semantic-model-evaluation-dataset |
| Repo | |
| Framework | |
Distributed Multitask Reinforcement Learning with Quadratic Convergence
| Title | Distributed Multitask Reinforcement Learning with Quadratic Convergence |
| Authors | Rasul Tutunov, Dongho Kim, Haitham Bou Ammar |
| Abstract | Multitask reinforcement learning (MTRL) suffers from scalability issues when the number of tasks or trajectories grows large. The main reason behind this drawback is the reliance on centeralised solutions. Recent methods exploited the connection between MTRL and general consensus to propose scalable solutions. These methods, however, suffer from two drawbacks. First, they rely on predefined objectives, and, second, exhibit linear convergence guarantees. In this paper, we improve over state-of-the-art by deriving multitask reinforcement learning from a variational inference perspective. We then propose a novel distributed solver for MTRL with quadratic convergence guarantees. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8106-distributed-multitask-reinforcement-learning-with-quadratic-convergence |
| http://papers.nips.cc/paper/8106-distributed-multitask-reinforcement-learning-with-quadratic-convergence.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-multitask-reinforcement-learning |
| Repo | |
| Framework | |
ECNU at SemEval-2018 Task 12: An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task
| Title | ECNU at SemEval-2018 Task 12: An End-to-End Attention-based Neural Network for the Argument Reasoning Comprehension Task |
| Authors | Junfeng Tian, Man Lan, Yuanbin Wu |
| Abstract | This paper presents our submissions to SemEval 2018 Task 12: the Argument Reasoning Comprehension Task. We investigate an end-to-end attention-based neural network to represent the two lexically close candidate warrants. On the one hand, we extract their different parts as attention vectors to obtain distinguishable representations. On the other hand, we use their surrounds (i.e., claim, reason, debate context) as another attention vectors to get contextual representations, which work as final clues to select the correct warrant. Our model achieves 60.4{%} accuracy and ranks 3rd among 22 participating systems. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1184/ |
| https://www.aclweb.org/anthology/S18-1184 | |
| PWC | https://paperswithcode.com/paper/ecnu-at-semeval-2018-task-12-an-end-to-end |
| Repo | |
| Framework | |
Avoiding Catastrophic States with Intrinsic Fear
| Title | Avoiding Catastrophic States with Intrinsic Fear |
| Authors | Zachary C. Lipton, Kamyar Azizzadenesheli, Abhishek Kumar, Lihong Li, Jianfeng Gao, Li Deng |
| Abstract | Many practical reinforcement learning problems contain catastrophic states that the optimal policy visits infrequently or never. Even on toy problems, deep reinforcement learners periodically revisit these states, once they are forgotten under a new policy. In this paper, we introduce intrinsic fear, a learned reward shaping that accelerates deep reinforcement learning and guards oscillating policies against periodic catastrophes. Our approach incorporates a second model trained via supervised learning to predict the probability of imminent catastrophe. This score acts as a penalty on the Q-learning objective. Our theoretical analysis demonstrates that the perturbed objective yields the same average return under strong assumptions and an $\epsilon$-close average return under weaker assumptions. Our analysis also shows robustness to classification errors. Equipped with intrinsic fear, our DQNs solve the toy environments and improve on the Atari games Seaquest, Asteroids, and Freeway. |
| Tasks | Atari Games, Q-Learning |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=B16yEqkCZ |
| https://openreview.net/pdf?id=B16yEqkCZ | |
| PWC | https://paperswithcode.com/paper/avoiding-catastrophic-states-with-intrinsic |
| Repo | |
| Framework | |
Frustrated, Polite, or Formal: Quantifying Feelings and Tone in Email
| Title | Frustrated, Polite, or Formal: Quantifying Feelings and Tone in Email |
| Authors | Niyati Chhaya, Kushal Chawla, Tanya Goyal, Ch, Projjal a, Jaya Singh |
| Abstract | Email conversations are the primary mode of communication in enterprises. The email content expresses an individual{'}s needs, requirements and intentions. Affective information in the email text can be used to get an insight into the sender{'}s mood or emotion. We present a novel approach to model human frustration in text. We identify linguistic features that influence human perception of frustration and model it as a supervised learning task. The paper provides a detailed comparison across traditional regression and word distribution-based models. We report a mean-squared error (MSE) of 0.018 against human-annotated frustration for the best performing model. The approach establishes the importance of affect features in frustration prediction for email data. We further evaluate the efficacy of the proposed feature set and model in predicting other tone or affects in text, namely formality and politeness; results demonstrate a comparable performance against the state-of-the-art baselines. |
| Tasks | Emotion Recognition |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1111/ |
| https://www.aclweb.org/anthology/W18-1111 | |
| PWC | https://paperswithcode.com/paper/frustrated-polite-or-formal-quantifying |
| Repo | |
| Framework | |
基於基因演算法的組合式多文件摘要方法 (An Ensemble Approach for Multi-document Summarization using Genetic Algorithms) [In Chinese]
| Title | 基於基因演算法的組合式多文件摘要方法 (An Ensemble Approach for Multi-document Summarization using Genetic Algorithms) [In Chinese] |
| Authors | Chun-Chang Chen, Yu-Hang Chung, Cheng-Zen Yang, Jhih-Sheng Fan, Chao-Yuan Lee |
| Abstract | |
| Tasks | Document Summarization, Multi-Document Summarization, Text Summarization |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/O18-1008/ |
| https://www.aclweb.org/anthology/O18-1008 | |
| PWC | https://paperswithcode.com/paper/ao14aoa-14c3ccaa14aae13-an-ensemble-approach |
| Repo | |
| Framework | |
Key2Vec: Automatic Ranked Keyphrase Extraction from Scientific Articles using Phrase Embeddings
| Title | Key2Vec: Automatic Ranked Keyphrase Extraction from Scientific Articles using Phrase Embeddings |
| Authors | Debanjan Mahata, John Kuriakose, Rajiv Ratn Shah, Roger Zimmermann |
| Abstract | Keyphrase extraction is a fundamental task in natural language processing that facilitates mapping of documents to a set of representative phrases. In this paper, we present an unsupervised technique (Key2Vec) that leverages phrase embeddings for ranking keyphrases extracted from scientific articles. Specifically, we propose an effective way of processing text documents for training multi-word phrase embeddings that are used for thematic representation of scientific articles and ranking of keyphrases extracted from them using theme-weighted PageRank. Evaluations are performed on benchmark datasets producing state-of-the-art results. |
| Tasks | Chunking, Named Entity Recognition, Part-Of-Speech Tagging, Semantic Role Labeling, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2100/ |
| https://www.aclweb.org/anthology/N18-2100 | |
| PWC | https://paperswithcode.com/paper/key2vec-automatic-ranked-keyphrase-extraction |
| Repo | |
| Framework | |
Multi-task learning for interpretable cause of death classification using key phrase prediction
| Title | Multi-task learning for interpretable cause of death classification using key phrase prediction |
| Authors | Serena Jeblee, Mireille Gomes, Graeme Hirst |
| Abstract | We introduce a multi-task learning model for cause-of-death classification of verbal autopsy narratives that jointly learns to output interpretable key phrases. Adding these key phrases outperforms the baseline model and topic modeling features. |
| Tasks | Multi-Task Learning, Text Classification |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2302/ |
| https://www.aclweb.org/anthology/W18-2302 | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-for-interpretable-cause |
| Repo | |
| Framework | |
Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics
| Title | Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2000/ |
| https://www.aclweb.org/anthology/S18-2000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-seventh-joint-conference |
| Repo | |
| Framework | |
Bidirectional Generative Adversarial Networks for Neural Machine Translation
| Title | Bidirectional Generative Adversarial Networks for Neural Machine Translation |
| Authors | Zhirui Zhang, Shujie Liu, Mu Li, Ming Zhou, Enhong Chen |
| Abstract | Generative Adversarial Network (GAN) has been proposed to tackle the exposure bias problem of Neural Machine Translation (NMT). However, the discriminator typically results in the instability of the GAN training due to the inadequate training problem: the search space is so huge that sampled translations are not sufficient for discriminator training. To address this issue and stabilize the GAN training, in this paper, we propose a novel Bidirectional Generative Adversarial Network for Neural Machine Translation (BGAN-NMT), which aims to introduce a generator model to act as the discriminator, whereby the discriminator naturally considers the entire translation space so that the inadequate training problem can be alleviated. To satisfy this property, generator and discriminator are both designed to model the joint probability of sentence pairs, with the difference that, the generator decomposes the joint probability with a source language model and a source-to-target translation model, while the discriminator is formulated as a target language model and a target-to-source translation model. To further leverage the symmetry of them, an auxiliary GAN is introduced and adopts generator and discriminator models of original one as its own discriminator and generator respectively. Two GANs are alternately trained to update the parameters. Experiment results on German-English and Chinese-English translation tasks demonstrate that our method not only stabilizes GAN training but also achieves significant improvements over baseline systems. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/K18-1019/ |
| https://www.aclweb.org/anthology/K18-1019 | |
| PWC | https://paperswithcode.com/paper/bidirectional-generative-adversarial-networks |
| Repo | |
| Framework | |
