Paper Group NANR 117
Beyond Quality, Considerations for an MT solution. MT for L10n: How we build and evaluate MT systems at eBay. Semi-Supervised Neural Machine Translation with Language Models. A Comparison of Machine Translation Paradigms for Use in Black-Box Fuzzy-Match Repair. Goal-Oriented Visual Question Generation via Intermediate Rewards. Survey: Anaphora With …
Beyond Quality, Considerations for an MT solution
Title | Beyond Quality, Considerations for an MT solution |
Authors | Quinn Lam |
Abstract | |
Tasks | Machine Translation |
Published | 2018-03-01 |
URL | https://www.aclweb.org/anthology/W18-1915/ |
https://www.aclweb.org/anthology/W18-1915 | |
PWC | https://paperswithcode.com/paper/beyond-quality-considerations-for-an-mt |
Repo | |
Framework | |
MT for L10n: How we build and evaluate MT systems at eBay
Title | MT for L10n: How we build and evaluate MT systems at eBay |
Authors | Jose S{'a}nchez |
Abstract | |
Tasks | |
Published | 2018-03-01 |
URL | https://www.aclweb.org/anthology/W18-1912/ |
https://www.aclweb.org/anthology/W18-1912 | |
PWC | https://paperswithcode.com/paper/mt-for-l10n-how-we-build-and-evaluate-mt |
Repo | |
Framework | |
Semi-Supervised Neural Machine Translation with Language Models
Title | Semi-Supervised Neural Machine Translation with Language Models |
Authors | Ivan Skorokhodov, Anton Rykachevskiy, Dmitry Emelyanenko, Sergey Slotin, Anton Ponkratov |
Abstract | |
Tasks | Language Modelling, Machine Translation |
Published | 2018-03-01 |
URL | https://www.aclweb.org/anthology/W18-2205/ |
https://www.aclweb.org/anthology/W18-2205 | |
PWC | https://paperswithcode.com/paper/semi-supervised-neural-machine-translation |
Repo | |
Framework | |
A Comparison of Machine Translation Paradigms for Use in Black-Box Fuzzy-Match Repair
Title | A Comparison of Machine Translation Paradigms for Use in Black-Box Fuzzy-Match Repair |
Authors | Rebecca Knowles, John Ortega, Philipp Koehn |
Abstract | |
Tasks | Automatic Post-Editing, Machine Translation |
Published | 2018-03-01 |
URL | https://www.aclweb.org/anthology/W18-2108/ |
https://www.aclweb.org/anthology/W18-2108 | |
PWC | https://paperswithcode.com/paper/a-comparison-of-machine-translation-paradigms |
Repo | |
Framework | |
Goal-Oriented Visual Question Generation via Intermediate Rewards
Title | Goal-Oriented Visual Question Generation via Intermediate Rewards |
Authors | Junjie Zhang, Qi Wu, Chunhua Shen, Jian Zhang, Jianfeng Lu, Anton van den Hengel |
Abstract | Despite significant progress in a variety of vision-and-language problems, developing a method capable of asking intelligent, goal-oriented questions about images is proven to be an inscrutable challenge. Towards this end, we propose a Deep Reinforcement Learning framework based on three new intermediate rewards, namely goal-achieved, progressive and informativeness that encourage the generation of succinct questions, which in turn uncover valuable information towards the overall goal. By directly optimizing for questions that work quickly towards fulfilling the overall goal, we avoid the tendency of existing methods to generate long series of inane queries that add little value. We evaluate our model on the GuessWhat?! dataset and show that the resulting questions can help a standard `Guesser’ identify a specific object in an image at a much higher success rate. | |
Tasks | Question Generation |
Published | 2018-09-01 |
URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Junjie_Zhang_Goal-Oriented_Visual_Question_ECCV_2018_paper.html |
http://openaccess.thecvf.com/content_ECCV_2018/papers/Junjie_Zhang_Goal-Oriented_Visual_Question_ECCV_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/goal-oriented-visual-question-generation-via |
Repo | |
Framework | |
Survey: Anaphora With Non-nominal Antecedents in Computational Linguistics: a Survey
Title | Survey: Anaphora With Non-nominal Antecedents in Computational Linguistics: a Survey |
Authors | Varada Kolhatkar, Adam Roussel, Stefanie Dipper, Heike Zinsmeister |
Abstract | This article provides an extensive overview of the literature related to the phenomenon of non-nominal-antecedent anaphora (also known as abstract anaphora or discourse deixis), a type of anaphora in which an anaphor like {}that{''} refers to an antecedent (marked in boldface) that is syntactically non-nominal, such as the first sentence in { }It{'}s way too hot here. That{'}s why I{'}m moving to Alaska.{''} Annotating and automatically resolving these cases of anaphora is interesting in its own right because of the complexities involved in identifying non-nominal antecedents, which typically represent abstract objects such as events, facts, and propositions. There is also practical value in the resolution of non-nominal-antecedent anaphora, as this would help computational systems in machine translation, summarization, and question answering, as well as, conceivably, any other task dependent on some measure of text understanding. Most of the existing approaches to anaphora annotation and resolution focus on nominal-antecedent anaphora, classifying many of the cases where the antecedents are syntactically non-nominal as non-anaphoric. There has been some work done on this topic, but it remains scattered and difficult to collect and assess. With this article, we hope to bring together and synthesize work done in disparate contexts up to now in order to identify fundamental problems and draw conclusions from an overarching perspective. Having a good picture of the current state of the art in this field can help researchers direct their efforts to where they are most necessary. Because of the great variety of theoretical approaches that have been brought to bear on the problem, there is an equally diverse array of terminologies that are used to describe it, so we will provide an overview and discussion of these terminologies. We also describe the linguistic properties of non-nominal-antecedent anaphora, examine previous annotation efforts that have addressed this topic, and present the computational approaches that aim at resolving non-nominal-antecedent anaphora automatically. We close with a review of the remaining open questions in this area and some of our recommendations for future research. |
Tasks | Machine Translation, Question Answering |
Published | 2018-09-01 |
URL | https://www.aclweb.org/anthology/J18-3007/ |
https://www.aclweb.org/anthology/J18-3007 | |
PWC | https://paperswithcode.com/paper/survey-anaphora-with-non-nominal-antecedents |
Repo | |
Framework | |
Probing sentence embeddings for structure-dependent tense
Title | Probing sentence embeddings for structure-dependent tense |
Authors | Geoff Bacon, Terry Regier |
Abstract | Learning universal sentence representations which accurately model sentential semantic content is a current goal of natural language processing research. A prominent and successful approach is to train recurrent neural networks (RNNs) to encode sentences into fixed length vectors. Many core linguistic phenomena that one would like to model in universal sentence representations depend on syntactic structure. Despite the fact that RNNs do not have explicit syntactic structural representations, there is some evidence that RNNs can approximate such structure-dependent phenomena under certain conditions, in addition to their widespread success in practical tasks. In this work, we assess RNNs{'} ability to learn the structure-dependent phenomenon of main clause tense. |
Tasks | Sentence Embeddings |
Published | 2018-11-01 |
URL | https://www.aclweb.org/anthology/W18-5440/ |
https://www.aclweb.org/anthology/W18-5440 | |
PWC | https://paperswithcode.com/paper/probing-sentence-embeddings-for-structure |
Repo | |
Framework | |
Unsupervised Word Influencer Networks from News Streams
Title | Unsupervised Word Influencer Networks from News Streams |
Authors | Ananth Balashankar, Sun Chakraborty, an, Lakshminarayanan Subramanian |
Abstract | In this paper, we propose a new unsupervised learning framework to use news events for predicting trends in stock prices. We present Word Influencer Networks (WIN), a graph framework to extract longitudinal temporal relationships between any pair of informative words from news streams. Using the temporal occurrence of words, WIN measures how the appearance of one word in a news stream influences the emergence of another set of words in the future. The latent word-word influencer relationships in WIN are the building blocks for causal reasoning and predictive modeling. We demonstrate the efficacy of WIN by using it for unsupervised extraction of latent features for stock price prediction and obtain 2 orders lower prediction error compared to a similar causal graph based method. WIN discovered influencer links from seemingly unrelated words from topics like politics to finance. WIN also validated 67{%} of the causal evidence found manually in the text through a direct edge and the rest 33{%} through a path of length 2. |
Tasks | Relationship Extraction (Distant Supervised), Stock Price Prediction |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/W18-3109/ |
https://www.aclweb.org/anthology/W18-3109 | |
PWC | https://paperswithcode.com/paper/unsupervised-word-influencer-networks-from |
Repo | |
Framework | |
MirasText: An Automatically Generated Text Corpus for Persian
Title | MirasText: An Automatically Generated Text Corpus for Persian |
Authors | Behnam Sabeti, Hossein Abedi Firouzjaee, Ali Janalizadeh Choobbasti, S.H.E. Mortazavi Najafabadi, Amir Vaheb |
Abstract | |
Tasks | Keyword Extraction, Language Modelling |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1188/ |
https://www.aclweb.org/anthology/L18-1188 | |
PWC | https://paperswithcode.com/paper/mirastext-an-automatically-generated-text |
Repo | |
Framework | |
TSix: A Human-involved-creation Dataset for Tweet Summarization
Title | TSix: A Human-involved-creation Dataset for Tweet Summarization |
Authors | Minh-Tien Nguyen, Dac Viet Lai, Huy-Tien Nguyen, Le-Minh Nguyen |
Abstract | |
Tasks | Document Summarization, Text Summarization |
Published | 2018-05-01 |
URL | https://www.aclweb.org/anthology/L18-1506/ |
https://www.aclweb.org/anthology/L18-1506 | |
PWC | https://paperswithcode.com/paper/tsix-a-human-involved-creation-dataset-for |
Repo | |
Framework | |
Generating Reasonable and Diversified Story Ending Using Sequence to Sequence Model with Adversarial Training
Title | Generating Reasonable and Diversified Story Ending Using Sequence to Sequence Model with Adversarial Training |
Authors | Zhongyang Li, Xiao Ding, Ting Liu |
Abstract | Story generation is a challenging problem in artificial intelligence (AI) and has received a lot of interests in the natural language processing (NLP) community. Most previous work tried to solve this problem using Sequence to Sequence (Seq2Seq) model trained with Maximum Likelihood Estimation (MLE). However, the pure MLE training objective much limits the power of Seq2Seq model in generating high-quality storys. In this paper, we propose using adversarial training augmented Seq2Seq model to generate reasonable and diversified story endings given a story context. Our model includes a generator that defines the policy of generating a story ending, and a discriminator that labels story endings as human-generated or machine-generated. Carefully designed human and automatic evaluation metrics demonstrate that our adversarial training augmented Seq2Seq model can generate more reasonable and diversified story endings compared to purely MLE-trained Seq2Seq model. Moreover, our model achieves better performance on the task of Story Cloze Test with an accuracy of 62.6{%} compared with state-of-the-art baseline methods. |
Tasks | Information Retrieval |
Published | 2018-08-01 |
URL | https://www.aclweb.org/anthology/C18-1088/ |
https://www.aclweb.org/anthology/C18-1088 | |
PWC | https://paperswithcode.com/paper/generating-reasonable-and-diversified-story |
Repo | |
Framework | |
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Title | Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) |
Authors | |
Abstract | |
Tasks | |
Published | 2018-07-01 |
URL | https://www.aclweb.org/anthology/P18-2000/ |
https://www.aclweb.org/anthology/P18-2000 | |
PWC | https://paperswithcode.com/paper/proceedings-of-the-56th-annual-meeting-of-the-1 |
Repo | |
Framework | |
Non-delusional Q-learning and value-iteration
Title | Non-delusional Q-learning and value-iteration |
Authors | Tyler Lu, Dale Schuurmans, Craig Boutilier |
Abstract | We identify a fundamental source of error in Q-learning and other forms of dynamic programming with function approximation. Delusional bias arises when the approximation architecture limits the class of expressible greedy policies. Since standard Q-updates make globally uncoordinated action choices with respect to the expressible policy class, inconsistent or even conflicting Q-value estimates can result, leading to pathological behaviour such as over/under-estimation, instability and even divergence. To solve this problem, we introduce a new notion of policy consistency and define a local backup process that ensures global consistency through the use of information sets—sets that record constraints on policies consistent with backed-up Q-values. We prove that both the model-based and model-free algorithms using this backup remove delusional bias, yielding the first known algorithms that guarantee optimal results under general conditions. These algorithms furthermore only require polynomially many information sets (from a potentially exponential support). Finally, we suggest other practical heuristics for value-iteration and Q-learning that attempt to reduce delusional bias. |
Tasks | Q-Learning |
Published | 2018-12-01 |
URL | http://papers.nips.cc/paper/8200-non-delusional-q-learning-and-value-iteration |
http://papers.nips.cc/paper/8200-non-delusional-q-learning-and-value-iteration.pdf | |
PWC | https://paperswithcode.com/paper/non-delusional-q-learning-and-value-iteration |
Repo | |
Framework | |
Good View Hunting: Learning Photo Composition From Dense View Pairs
Title | Good View Hunting: Learning Photo Composition From Dense View Pairs |
Authors | Zijun Wei, Jianming Zhang, Xiaohui Shen, Zhe Lin, RadomÃr Mech, Minh Hoai, Dimitris Samaras |
Abstract | Finding views with good photo composition is a challenging task for machine learning methods. A key difficulty is the lack of well annotated large scale datasets. Most existing datasets only provide a limited number of annotations for good views, while ignoring the comparative nature of view selection. In this work, we present the first large scale Comparative Photo Composition dataset, which contains over one million comparative view pairs annotated using a cost-effective crowdsourcing workflow. We show that these comparative view annotations are essential for training a robust neural network model for composition. In addition, we propose a novel knowledge transfer framework to train a fast view proposal network, which runs at 75+ FPS and achieves state-of-the-art performance in image cropping and thumbnail generation tasks on three benchmark datasets. The superiority of our method is also demonstrated in a user study on a challenging experiment, where our method significantly outperforms the baseline methods in producing diversified well-composed views. |
Tasks | Image Cropping, Transfer Learning |
Published | 2018-06-01 |
URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Wei_Good_View_Hunting_CVPR_2018_paper.html |
http://openaccess.thecvf.com/content_cvpr_2018/papers/Wei_Good_View_Hunting_CVPR_2018_paper.pdf | |
PWC | https://paperswithcode.com/paper/good-view-hunting-learning-photo-composition |
Repo | |
Framework | |
Minimax Concave Penalized Multi-Armed Bandit Model with High-Dimensional Covariates
Title | Minimax Concave Penalized Multi-Armed Bandit Model with High-Dimensional Covariates |
Authors | Xue Wang, Mingcheng Wei, Tao Yao |
Abstract | In this paper, we propose a Minimax Concave Penalized Multi-Armed Bandit (MCP-Bandit) algorithm for a decision-maker facing high-dimensional data with latent sparse structure in an online learning and decision-making process. We demonstrate that the MCP-Bandit algorithm asymptotically achieves the optimal cumulative regret in sample size T, O(log T), and further attains a tighter bound in both covariates dimension d and the number of significant covariates s, O(s^2 (s + log d). In addition, we develop a linear approximation method, the 2-step Weighted Lasso procedure, to identify the MCP estimator for the MCP-Bandit algorithm under non-i.i.d. samples. Using this procedure, the MCP estimator matches the oracle estimator with high probability. Finally, we present two experiments to benchmark our proposed the MCP-Bandit algorithm to other bandit algorithms. Both experiments demonstrate that the MCP-Bandit algorithm performs favorably over other benchmark algorithms, especially when there is a high level of data sparsity or when the sample size is not too small. |
Tasks | Decision Making |
Published | 2018-07-01 |
URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2469 |
http://proceedings.mlr.press/v80/wang18j/wang18j.pdf | |
PWC | https://paperswithcode.com/paper/minimax-concave-penalized-multi-armed-bandit |
Repo | |
Framework | |