Paper Group NANR 90
Inducing Cooperation via Learning to reshape rewards in semi-cooperative multi-agent reinforcement learning. Using Semantic Similarity as Reward for Reinforcement Learning in Sentence Generation. Answering questions by learning to rank - Learning to rank by answering questions. Abstractive Timeline Summarization. Empirical Evaluation of Active Lear …
Inducing Cooperation via Learning to reshape rewards in semi-cooperative multi-agent reinforcement learning
| Title | Inducing Cooperation via Learning to reshape rewards in semi-cooperative multi-agent reinforcement learning |
| Authors | David Earl Hostallero, Daewoo Kim, Kyunghwan Son, Yung Yi |
| Abstract | We propose a deep reinforcement learning algorithm for semi-cooperative multi-agent tasks, where agents are equipped with their separate reward functions, yet with willingness to cooperate. Under these semi-cooperative scenarios, popular methods of centralized training with decentralized execution for inducing cooperation and removing the non-stationarity problem do not work well due to lack of a common shared reward as well as inscalability in centralized training. Our algorithm, called Peer-Evaluation based Dual DQN (PED-DQN), proposes to give peer evaluation signals to observed agents, which quantifies how they feel about a certain transition. This exchange of peer evaluation over time turns out to render agents to gradually reshape their reward functions so that their action choices from the myopic best-response tend to result in the good joint action with high cooperation. This evaluation-based method also allows flexible and scalable training by not assuming knowledge of the number of other agents and their observation and action spaces. We provide the performance evaluation of PED-DQN for the scenarios ranging from a simple two-person prisoner’s dilemma to more complex semi-cooperative multi-agent tasks. In special cases where agents share a common reward function as in the centralized training methods, we show that inter-agent evaluation leads to better performance |
| Tasks | Multi-agent Reinforcement Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SyVhg20cK7 |
| https://openreview.net/pdf?id=SyVhg20cK7 | |
| PWC | https://paperswithcode.com/paper/inducing-cooperation-via-learning-to-reshape |
| Repo | |
| Framework | |
Using Semantic Similarity as Reward for Reinforcement Learning in Sentence Generation
| Title | Using Semantic Similarity as Reward for Reinforcement Learning in Sentence Generation |
| Authors | Go Yasui, Yoshimasa Tsuruoka, Masaaki Nagata |
| Abstract | Traditional model training for sentence generation employs cross-entropy loss as the loss function. While cross-entropy loss has convenient properties for supervised learning, it is unable to evaluate sentences as a whole, and lacks flexibility. We present the approach of training the generation model using the estimated semantic similarity between the output and reference sentences to alleviate the problems faced by the training with cross-entropy loss. We use the BERT-based scorer fine-tuned to the Semantic Textual Similarity (STS) task for semantic similarity estimation, and train the model with the estimated scores through reinforcement learning (RL). Our experiments show that reinforcement learning with semantic similarity reward improves the BLEU scores from the baseline LSTM NMT model. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2056/ |
| https://www.aclweb.org/anthology/P19-2056 | |
| PWC | https://paperswithcode.com/paper/using-semantic-similarity-as-reward-for |
| Repo | |
| Framework | |
Answering questions by learning to rank - Learning to rank by answering questions
| Title | Answering questions by learning to rank - Learning to rank by answering questions |
| Authors | George Sebastian Pirtoaca, Traian Rebedea, Stefan Ruseti |
| Abstract | Answering multiple-choice questions in a setting in which no supporting documents are explicitly provided continues to stand as a core problem in natural language processing. The contribution of this article is two-fold. First, it describes a method which can be used to semantically rank documents extracted from Wikipedia or similar natural language corpora. Second, we propose a model employing the semantic ranking that holds the first place in two of the most popular leaderboards for answering multiple-choice questions: ARC Easy and Challenge. To achieve this, we introduce a self-attention based neural network that latently learns to rank documents by their importance related to a given question, whilst optimizing the objective of predicting the correct answer. These documents are considered relevant contexts for the underlying question. We have published the ranked documents so that they can be used off-the-shelf to improve downstream decision models. |
| Tasks | Learning-To-Rank |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1256/ |
| https://www.aclweb.org/anthology/D19-1256 | |
| PWC | https://paperswithcode.com/paper/answering-questions-by-learning-to-rank-1 |
| Repo | |
| Framework | |
Abstractive Timeline Summarization
| Title | Abstractive Timeline Summarization |
| Authors | Julius Steen, Katja Markert |
| Abstract | Timeline summarization (TLS) automatically identifies key dates of major events and provides short descriptions of what happened on these dates. Previous approaches to TLS have focused on extractive methods. In contrast, we suggest an abstractive timeline summarization system. Our system is entirely unsupervised, which makes it especially suited to TLS where there are very few gold summaries available for training of supervised systems. In addition, we present the first abstractive oracle experiments for TLS. Our system outperforms extractive competitors in terms of ROUGE when the number of input documents is high and the output requires strong compression. In these cases, our oracle experiments confirm that our approach also has a higher upper bound for ROUGE scores than extractive methods. A study with human judges shows that our abstractive system also produces output that is easy to read and understand. |
| Tasks | Timeline Summarization |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5403/ |
| https://www.aclweb.org/anthology/D19-5403 | |
| PWC | https://paperswithcode.com/paper/abstractive-timeline-summarization |
| Repo | |
| Framework | |
Empirical Evaluation of Active Learning Techniques for Neural MT
| Title | Empirical Evaluation of Active Learning Techniques for Neural MT |
| Authors | Xiangkai Zeng, Sarthak Garg, Rajen Chatterjee, Udhyakumar Nallasamy, Matthias Paulik |
| Abstract | Active learning (AL) for machine translation (MT) has been well-studied for the phrase-based MT paradigm. Several AL algorithms for data sampling have been proposed over the years. However, given the rapid advancement in neural methods, these algorithms have not been thoroughly investigated in the context of neural MT (NMT). In this work, we address this missing aspect by conducting a systematic comparison of different AL methods in a simulated AL framework. Our experimental setup to compare different AL methods uses: i) State-of-the-art NMT architecture to achieve realistic results; and ii) the same dataset (WMT{'}13 English-Spanish) to have fair comparison across different methods. We then demonstrate how recent advancements in unsupervised pre-training and paraphrastic embedding can be used to improve existing AL methods. Finally, we propose a neural extension for an AL sampling method used in the context of phrase-based MT - Round Trip Translation Likelihood (RTTL). RTTL uses a bidirectional translation model to estimate the loss of information during translation and outperforms previous methods. |
| Tasks | Active Learning, Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6110/ |
| https://www.aclweb.org/anthology/D19-6110 | |
| PWC | https://paperswithcode.com/paper/empirical-evaluation-of-active-learning |
| Repo | |
| Framework | |
Decentralized sketching of low rank matrices
| Title | Decentralized sketching of low rank matrices |
| Authors | Rakshith Sharma Srinivasa, Kiryung Lee, Marius Junge, Justin Romberg |
| Abstract | We address a low-rank matrix recovery problem where each column of a rank-r matrix X of size (d1,d2) is compressed beyond the point of recovery to size L with L « d1. Leveraging the joint structure between the columns, we propose a method to recover the matrix to within an epsilon relative error in the Frobenius norm from a total of O(r(d_1 + d_2)\log^6(d_1 + d_2)/\epsilon^2) observations. This guarantee holds uniformly for all incoherent matrices of rank r. In our method, we propose to use a novel matrix norm called the mixed-norm along with the maximum l2 norm of the columns to design a novel convex relaxation for low-rank recovery that is tailored to our observation model. We also show that our proposed mixed-norm, the standard nuclear norm, and the max-norm are particular instances of convex regularization of low-rankness via tensor norms. Finally, we provide a scalable ADMM algorithm for the mixed-norm based method and demonstrate its empirical performance via large-scale simulations. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9200-decentralized-sketching-of-low-rank-matrices |
| http://papers.nips.cc/paper/9200-decentralized-sketching-of-low-rank-matrices.pdf | |
| PWC | https://paperswithcode.com/paper/decentralized-sketching-of-low-rank-matrices |
| Repo | |
| Framework | |
Monocular Piecewise Depth Estimation in Dynamic Scenes by Exploiting Superpixel Relations
| Title | Monocular Piecewise Depth Estimation in Dynamic Scenes by Exploiting Superpixel Relations |
| Authors | Yan Di, Henrique Morimitsu, Shan Gao, Xiangyang Ji |
| Abstract | In this paper, we propose a novel and specially designed method for piecewise dense monocular depth estimation in dynamic scenes. We utilize spatial relations between neighboring superpixels to solve the inherent relative scale ambiguity (RSA) problem and smooth the depth map. However, directly estimating spatial relations is an ill-posed problem. Our core idea is to predict spatial relations based on the corresponding motion relations. Given two or more consecutive frames, we first compute semi-dense (CPM) or dense (optical flow) point matches between temporally neighboring images. Then we develop our method in four main stages: superpixel relations analysis, motion selection, reconstruction, and refinement. The final refinement process helps to improve the quality of the reconstruction at pixel level. Our method does not require per-object segmentation, template priors or training sets, which ensures flexibility in various applications. Extensive experiments on both synthetic and real datasets demonstrate that our method robustly handles different dynamic situations and presents competitive results to the state-of-the-art methods while running much faster than them. |
| Tasks | Depth Estimation, Monocular Depth Estimation, Optical Flow Estimation, Semantic Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Di_Monocular_Piecewise_Depth_Estimation_in_Dynamic_Scenes_by_Exploiting_Superpixel_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Di_Monocular_Piecewise_Depth_Estimation_in_Dynamic_Scenes_by_Exploiting_Superpixel_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/monocular-piecewise-depth-estimation-in |
| Repo | |
| Framework | |
Unsupervised Induction of Ukrainian Morphological Paradigms for the New Lexicon: Extending Coverage for Named Entities and Neologisms using Inflection Tables and Unannotated Corpora
| Title | Unsupervised Induction of Ukrainian Morphological Paradigms for the New Lexicon: Extending Coverage for Named Entities and Neologisms using Inflection Tables and Unannotated Corpora |
| Authors | Bogdan Babych |
| Abstract | The paper presents an unsupervised method for quickly extending a Ukrainian lexicon by generating paradigms and morphological feature structures for new Named Entities and neologisms, which are not covered by existing static morphological resources. This approach addresses a practical problem of modelling paradigms for entities created by the dynamic processes in the lexicon: this problem is especially serious for highly-inflected languages in domains with specialised or quickly changing lexicon. The method uses an unannotated Ukrainian corpus and a small fixed set of inflection tables, which can be found in traditional grammar textbooks. The advantage of the proposed approach is that updating the morphological lexicon does not require training or linguistic annotation, allowing fast knowledge-light extension of an existing static lexicon to improve morphological coverage on a specific corpus. The method is implemented in an open-source package on a GitHub repository. It can be applied to other low-resourced inflectional languages which have internet corpora and linguistic descriptions of their inflection system, following the example of inflection tables for Ukrainian. Evaluation results shows consistent improvements in coverage for Ukrainian corpora of different corpus types. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3701/ |
| https://www.aclweb.org/anthology/W19-3701 | |
| PWC | https://paperswithcode.com/paper/unsupervised-induction-of-ukrainian |
| Repo | |
| Framework | |
Multispectral Imaging for Fine-Grained Recognition of Powders on Complex Backgrounds
| Title | Multispectral Imaging for Fine-Grained Recognition of Powders on Complex Backgrounds |
| Authors | Tiancheng Zhi, Bernardo R. Pires, Martial Hebert, Srinivasa G. Narasimhan |
| Abstract | Hundreds of materials, such as drugs, explosives, makeup, food additives, are in the form of powder. Recognizing such powders is important for security checks, criminal identification, drug control, and quality assessment. However, powder recognition has drawn little attention in the computer vision community. Powders are hard to distinguish: they are amorphous, appear matte, have little color or texture variation and blend with surfaces they are deposited on in complex ways. To address these challenges, we present the first comprehensive dataset and approach for powder recognition using multi-spectral imaging. By using Shortwave Infrared (SWIR) multi-spectral imaging together with visible light (RGB) and Near Infrared (NIR), powders can be discriminated with reasonable accuracy. We present a method to select discriminative spectral bands to significantly reduce acquisition time while improving recognition accuracy. We propose a blending model to synthesize images of powders of various thickness deposited on a wide range of surfaces. Incorporating band selection and image synthesis, we conduct fine-grained recognition of 100 powders on complex backgrounds, and achieve 60% 70% accuracy on recognition with known powder location, and over 40% mean IoU without known location. |
| Tasks | Image Generation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhi_Multispectral_Imaging_for_Fine-Grained_Recognition_of_Powders_on_Complex_Backgrounds_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhi_Multispectral_Imaging_for_Fine-Grained_Recognition_of_Powders_on_Complex_Backgrounds_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multispectral-imaging-for-fine-grained |
| Repo | |
| Framework | |
Nonconvex Low-Rank Tensor Completion from Noisy Data
| Title | Nonconvex Low-Rank Tensor Completion from Noisy Data |
| Authors | Changxiao Cai, Gen Li, H. Vincent Poor, Yuxin Chen |
| Abstract | We study a completion problem of broad practical interest: the reconstruction of a low-rank symmetric tensor from highly incomplete and randomly corrupted observations of its entries. While a variety of prior work has been dedicated to this problem, prior algorithms either are computationally too expensive for large-scale applications, or come with sub-optimal statistical guarantees. Focusing on ``incoherent’’ and well-conditioned tensors of a constant CP rank, we propose a two-stage nonconvex algorithm — (vanilla) gradient descent following a rough initialization — that achieves the best of both worlds. Specifically, the proposed nonconvex algorithm faithfully completes the tensor and retrieves all low-rank tensor factors within nearly linear time, while at the same time enjoying near-optimal statistical guarantees (i.e.~minimal sample complexity and optimal $\ell_2$ and $\ell_{\infty}$ statistical accuracy). The insights conveyed through our analysis of nonconvex optimization might have implications for other tensor estimation problems. | |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8462-nonconvex-low-rank-tensor-completion-from-noisy-data |
| http://papers.nips.cc/paper/8462-nonconvex-low-rank-tensor-completion-from-noisy-data.pdf | |
| PWC | https://paperswithcode.com/paper/nonconvex-low-rank-tensor-completion-from |
| Repo | |
| Framework | |
Online Sentence Segmentation for Simultaneous Interpretation using Multi-Shifted Recurrent Neural Network
| Title | Online Sentence Segmentation for Simultaneous Interpretation using Multi-Shifted Recurrent Neural Network |
| Authors | Xiaolin Wang, Masao Utiyama, Eiichiro Sumita |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6601/ |
| https://www.aclweb.org/anthology/W19-6601 | |
| PWC | https://paperswithcode.com/paper/online-sentence-segmentation-for-simultaneous |
| Repo | |
| Framework | |
Selecting Informative Context Sentence by Forced Back-Translation
| Title | Selecting Informative Context Sentence by Forced Back-Translation |
| Authors | Ryuichiro Kimura, Shohei Iida, Hongyi Cui, Po-Hsuan Hung, Takehito Utsuro, Masaaki Nagata |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6616/ |
| https://www.aclweb.org/anthology/W19-6616 | |
| PWC | https://paperswithcode.com/paper/selecting-informative-context-sentence-by |
| Repo | |
| Framework | |
Controlling the Reading Level of Machine Translation Output
| Title | Controlling the Reading Level of Machine Translation Output |
| Authors | Kelly Marchisio, Jialiang Guo, Cheng-I Lai, Philipp Koehn |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6619/ |
| https://www.aclweb.org/anthology/W19-6619 | |
| PWC | https://paperswithcode.com/paper/controlling-the-reading-level-of-machine |
| Repo | |
| Framework | |
When the whole is greater than the sum of its parts: Multiword expressions and idiomaticity
| Title | When the whole is greater than the sum of its parts: Multiword expressions and idiomaticity |
| Authors | Aline Villavicencio |
| Abstract | Multiword expressions (MWEs) feature prominently in the mental lexicon of native speakers (Jackendoff, 1997) in all languages and domains, from informal to technical contexts (Biber et al., 1999) with about four MWEs being produced per minute of discourse (Glucksberg, 1989). MWEs come in all shapes and forms, including idioms like rock the boat (as cause problems or disturb a situation) and compound nouns like monkey business (as dishonest behaviour). Their accurate detection and understanding may often require more than knowledge about individual words and how they can be combined (Fillmore, 1979), as they may display various degrees of idiosyncrasy, including lexical, syntactic, semantic and statistical (Sag et al., 2002; Baldwin and Kim, 2010), which provide new challenges and opportunities for language processing (Constant et al., 2017). For instance, while for some combinations the meaning can be inferred from their parts like olive oil (oil made of olives) this is not always the case, as in dark horse (meaning an unknown candidate who unexpectedly succeeds), and when processing a sentence some of the challenges are to identify which words form an expression (Ramisch, 2015), and whether the expression is idiomatic (Cordeiro et al., 2019). In this talk I will give an overview of advances on the identification and treatment of multiword expressions, in particular concentrating on techniques for identifying their degree of idiomaticity. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5101/ |
| https://www.aclweb.org/anthology/W19-5101 | |
| PWC | https://paperswithcode.com/paper/when-the-whole-is-greater-than-the-sum-of-its |
| Repo | |
| Framework | |
A Japanese Word Segmentation Proposal
| Title | A Japanese Word Segmentation Proposal |
| Authors | Stalin Aguirre, Josaf{'a} Aguiar |
| Abstract | Current Japanese word segmentation methods, that use a morpheme-based approach, may produce different segmentations for the same strings. This occurs when these strings appear in different sentences. The cause is the influence of different contexts around these strings affecting the probabilistic models used in segmentation algorithms. This paper presents an alternative to the current morpheme-based scheme for Japanese word segmentation. The proposed scheme focuses on segmenting inflections as single words instead of separating the auxiliary verbs and other morphemes from the stems. Some morphological segmentation rules are presented for each type of word and these rules are implemented in a program which is properly described. The program is used to generate a segmentation of a sentence corpus, whose consistency is calculated and compared with the current morpheme-based segmentation of the same corpus. The experiments show that this method produces a much more consistent segmentation than the morpheme-based one. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2060/ |
| https://www.aclweb.org/anthology/P19-2060 | |
| PWC | https://paperswithcode.com/paper/a-japanese-word-segmentation-proposal |
| Repo | |
| Framework | |
