Paper Group NANR 186
A case study on context-bound referring expression generation. Wasserstein proximal of GANs. The University of Helsinki Submissions to the WMT19 Similar Language Translation Task. Deep Adversarial Learning for NLP. An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors. A Corpus of Negations and their Underlying Pos …
A case study on context-bound referring expression generation
| Title | A case study on context-bound referring expression generation |
| Authors | Maurice Langner |
| Abstract | In recent years, Bayesian models of referring expression generation have gained prominence in order to produce situationally more adequate referring expressions. Basically, these models enable the integration of different parameters into the decision process for using a specific referring expression like the cardinality of the object set, the configuration and complexity of the visual field, and the discriminatory power of available attributes that need to be combined with visual salience and personal preference. This paper describes and discusses the results of an empirical study on the production of referring expressions in visual fields with different object configurations of varying complexity and different contextual premises for using a referring expression. The visual fields are set up using data from the TUNA experiment with plain random or pragmatically enriched configurations which allow for target inference. Different categories of the situational contexts, in which the referring expressions are produced, provide different degrees of cooperativeness, so that generation quality and its relations to contextual user intention can be observed. The results of the study suggest that Bayesian approaches must integrate individual generation preference and the cooperativeness of the situational task in order to model the broad variance between speakers more adequately. |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8603/ |
| https://www.aclweb.org/anthology/W19-8603 | |
| PWC | https://paperswithcode.com/paper/a-case-study-on-context-bound-referring |
| Repo | |
| Framework | |
Wasserstein proximal of GANs
| Title | Wasserstein proximal of GANs |
| Authors | Alex Tong Lin, Wuchen Li, Stanley Osher, Guido Montufar |
| Abstract | We introduce a new method for training GANs by applying the Wasserstein-2 metric proximal on the generators. The approach is based on the gradient operator induced by optimal transport, which connects the geometry of sample space and parameter space in implicit deep generative models. From this theory, we obtain an easy-to-implement regularizer for the parameter updates. Our experiments demonstrate that this method improves the speed and stability in training GANs in terms of wall-clock time and Fr'echet Inception Distance (FID) learning curves. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Bye5OiR5F7 |
| https://openreview.net/pdf?id=Bye5OiR5F7 | |
| PWC | https://paperswithcode.com/paper/wasserstein-proximal-of-gans |
| Repo | |
| Framework | |
The University of Helsinki Submissions to the WMT19 Similar Language Translation Task
| Title | The University of Helsinki Submissions to the WMT19 Similar Language Translation Task |
| Authors | Yves Scherrer, Ra{'u}l V{'a}zquez, Sami Virpioja |
| Abstract | This paper describes the University of Helsinki Language Technology group{'}s participation in the WMT 2019 similar language translation task. We trained neural machine translation models for the language pairs Czech {\textless}-{\textgreater} Polish and Spanish {\textless}-{\textgreater} Portuguese. Our experiments focused on different subword segmentation methods, and in particular on the comparison of a cognate-aware segmentation method, Cognate Morfessor, with character segmentation and unsupervised segmentation methods for which the data from different languages were simply concatenated. We did not observe major benefits from cognate-aware segmentation methods, but further research may be needed to explore larger parts of the parameter space. Character-level models proved to be competitive for translation between Spanish and Portuguese, but they are slower in training and decoding. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5432/ |
| https://www.aclweb.org/anthology/W19-5432 | |
| PWC | https://paperswithcode.com/paper/the-university-of-helsinki-submissions-to-the-3 |
| Repo | |
| Framework | |
Deep Adversarial Learning for NLP
| Title | Deep Adversarial Learning for NLP |
| Authors | William Yang Wang, Sameer Singh, Jiwei Li |
| Abstract | Adversarial learning is a game-theoretic learning paradigm, which has achieved huge successes in the field of Computer Vision recently. Adversarial learning is also a general framework that enables a variety of learning models, including the popular Generative Adversarial Networks (GANs). Due to the discrete nature of language, designing adversarial learning models is still challenging for NLP problems. In this tutorial, we provide a gentle introduction to the foundation of deep adversarial learning, as well as some practical problem formulations and solutions in NLP. We describe recent advances in deep adversarial learning for NLP, with a special focus on generation, adversarial examples {&} rules, and dialogue. We provide an overview of the research area, categorize different types of adversarial learning models, and discuss pros and cons, aiming at providing some practical perspectives on the future of adversarial learning for solving real-world NLP problems. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-5001/ |
| https://www.aclweb.org/anthology/N19-5001 | |
| PWC | https://paperswithcode.com/paper/deep-adversarial-learning-for-nlp |
| Repo | |
| Framework | |
An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors
| Title | An Algorithmic Framework For Differentially Private Data Analysis on Trusted Processors |
| Authors | Joshua Allen, Bolin Ding, Janardhan Kulkarni, Harsha Nori, Olga Ohrimenko, Sergey Yekhanin |
| Abstract | Differential privacy has emerged as the main definition for private data analysis and machine learning. The global model of differential privacy, which assumes that users trust the data collector, provides strong privacy guarantees and introduces small errors in the output. In contrast, applications of differential privacy in commercial systems by Apple, Google, and Microsoft, use the local model. Here, users do not trust the data collector, and hence randomize their data before sending it to the data collector. Unfortunately, local model is too strong for several important applications and hence is limited in its applicability. In this work, we propose a framework based on trusted processors and a new definition of differential privacy called Oblivious Differential Privacy, which combines the best of both local and global models. The algorithms we design in this framework show interesting interplay of ideas from the streaming algorithms, oblivious algorithms, and differential privacy. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9517-an-algorithmic-framework-for-differentially-private-data-analysis-on-trusted-processors |
| http://papers.nips.cc/paper/9517-an-algorithmic-framework-for-differentially-private-data-analysis-on-trusted-processors.pdf | |
| PWC | https://paperswithcode.com/paper/an-algorithmic-framework-for-differentially |
| Repo | |
| Framework | |
A Corpus of Negations and their Underlying Positive Interpretations
| Title | A Corpus of Negations and their Underlying Positive Interpretations |
| Authors | Zahra Sarabi, Erin Killian, Eduardo Blanco, Alexis Palmer |
| Abstract | Negation often conveys implicit positive meaning. In this paper, we present a corpus of negations and their underlying positive interpretations. We work with negations from Simple Wikipedia, automatically generate potential positive interpretations, and then collect manual annotations that effectively rewrite the negation in positive terms. This procedure yields positive interpretations for approximately 77{%} of negations, and the final corpus includes over 5,700 negations and over 5,900 positive interpretations. We also present baseline results using seq2seq neural models. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1017/ |
| https://www.aclweb.org/anthology/S19-1017 | |
| PWC | https://paperswithcode.com/paper/a-corpus-of-negations-and-their-underlying |
| Repo | |
| Framework | |
MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding
| Title | MoRTy: Unsupervised Learning of Task-specialized Word Embeddings by Autoencoding |
| Authors | Nils Rethmeier, Barbara Plank |
| Abstract | Word embeddings have undoubtedly revolutionized NLP. However, pretrained embeddings do not always work for a specific task (or set of tasks), particularly in limited resource setups. We introduce a simple yet effective, self-supervised post-processing method that constructs task-specialized word representations by picking from a menu of reconstructing transformations to yield improved end-task performance (MORTY). The method is complementary to recent state-of-the-art approaches to inductive transfer via fine-tuning, and forgoes costly model architectures and annotation. We evaluate MORTY on a broad range of setups, including different word embedding methods, corpus sizes and end-task semantics. Finally, we provide a surprisingly simple recipe to obtain specialized embeddings that better fit end-tasks. |
| Tasks | Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4307/ |
| https://www.aclweb.org/anthology/W19-4307 | |
| PWC | https://paperswithcode.com/paper/morty-unsupervised-learning-of-task |
| Repo | |
| Framework | |
Acquiring Structured Temporal Representation via Crowdsourcing: A Feasibility Study
| Title | Acquiring Structured Temporal Representation via Crowdsourcing: A Feasibility Study |
| Authors | Yuchen Zhang, Nianwen Xue |
| Abstract | Temporal Dependency Trees are a structured temporal representation that represents temporal relations among time expressions and events in a text as a dependency tree structure. Compared to traditional pair-wise temporal relation representations, temporal dependency trees facilitate efficient annotations, higher inter-annotator agreement, and efficient computations. However, annotations on temporal dependency trees so far have only been done by expert annotators, which is costly and time-consuming. In this paper, we introduce a method to crowdsource temporal dependency tree annotations, and show that this representation is intuitive and can be collected with high accuracy and agreement through crowdsourcing. We produce a corpus of temporal dependency trees, and present a baseline temporal dependency parser, trained and evaluated on this new corpus. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-1019/ |
| https://www.aclweb.org/anthology/S19-1019 | |
| PWC | https://paperswithcode.com/paper/acquiring-structured-temporal-representation |
| Repo | |
| Framework | |
Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts
| Title | Comparing and Developing Tools to Measure the Readability of Domain-Specific Texts |
| Authors | Elissa Redmiles, Lisa Maszkiewicz, Emily Hwang, Dhruv Kuchhal, Everest Liu, Miraida Morales, Denis Peskov, Sudha Rao, Rock Stevens, Kristina Gligori{'c}, Sean Kross, Michelle Mazurek, Hal Daum{'e} III |
| Abstract | The readability of a digital text can influence people{'}s ability to learn new things about a range topics from digital resources (e.g., Wikipedia, WebMD). Readability also impacts search rankings, and is used to evaluate the performance of NLP systems. Despite this, we lack a thorough understanding of how to validly measure readability at scale, especially for domain-specific texts. In this work, we present a comparison of the validity of well-known readability measures and introduce a novel approach, Smart Cloze, which is designed to address shortcomings of existing measures. We compare these approaches across four different corpora: crowdworker-generated stories, Wikipedia articles, security and privacy advice, and health information. On these corpora, we evaluate the convergent and content validity of each measure, and detail tradeoffs in score precision, domain-specificity, and participant burden. These results provide a foundation for more accurate readability measurements and better evaluation of new natural-language-processing systems and tools. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1489/ |
| https://www.aclweb.org/anthology/D19-1489 | |
| PWC | https://paperswithcode.com/paper/comparing-and-developing-tools-to-measure-the |
| Repo | |
| Framework | |
Evaluating adversarial attacks against multiple fact verification systems
| Title | Evaluating adversarial attacks against multiple fact verification systems |
| Authors | James Thorne, Andreas Vlachos, Christos Christodoulopoulos, Arpit Mittal |
| Abstract | Automated fact verification has been progressing owing to advancements in modeling and availability of large datasets. Due to the nature of the task, it is critical to understand the vulnerabilities of these systems against adversarial instances designed to make them predict incorrectly. We introduce two novel scoring metrics, attack potency and system resilience which take into account the correctness of the adversarial instances, an aspect often ignored in adversarial evaluations. We consider six fact verification systems from the recent Fact Extraction and VERification (FEVER) challenge: the four best-scoring ones and two baselines. We evaluate adversarial instances generated by a recently proposed state-of-the-art method, a paraphrasing method, and rule-based attacks devised for fact verification. We find that our rule-based attacks have higher potency, and that while the rankings among the top systems changed, they exhibited higher resilience than the baselines. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1292/ |
| https://www.aclweb.org/anthology/D19-1292 | |
| PWC | https://paperswithcode.com/paper/evaluating-adversarial-attacks-against |
| Repo | |
| Framework | |
Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning Model
| Title | Language-Driven Temporal Activity Localization: A Semantic Matching Reinforcement Learning Model |
| Authors | Weining Wang, Yan Huang, Liang Wang |
| Abstract | Current studies on action detection in untrimmed videos are mostly designed for action classes, where an action is described at word level such as jumping, tumbling, swing, etc. This paper focuses on a rarely investigated problem of localizing an activity via a sentence query which would be more challenging and practical. Considering that current methods are generally time-consuming due to the dense frame-processing manner, we propose a recurrent neural network based reinforcement learning model which selectively observes a sequence of frames and associates the given sentence with video content in a matching-based manner. However, directly matching sentences with video content performs poorly due to the large visual-semantic discrepancy. Thus, we extend the method to a semantic matching reinforcement learning (SM-RL) model by extracting semantic concepts of videos and then fusing them with global context features. Extensive experiments on three benchmark datasets, TACoS, Charades-STA and DiDeMo, show that our method achieves the state-of-the-art performance with a high detection speed, demonstrating both effectiveness and efficiency of our method. |
| Tasks | Action Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wang_Language-Driven_Temporal_Activity_Localization_A_Semantic_Matching_Reinforcement_Learning_Model_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wang_Language-Driven_Temporal_Activity_Localization_A_Semantic_Matching_Reinforcement_Learning_Model_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/language-driven-temporal-activity |
| Repo | |
| Framework | |
Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning
| Title | Learning the Extraction Order of Multiple Relational Facts in a Sentence with Reinforcement Learning |
| Authors | Xiangrong Zeng, Shizhu He, Daojian Zeng, Kang Liu, Shengping Liu, Jun Zhao |
| Abstract | The multiple relation extraction task tries to extract all relational facts from a sentence. Existing works didn{'}t consider the extraction order of relational facts in a sentence. In this paper we argue that the extraction order is important in this task. To take the extraction order into consideration, we apply the reinforcement learning into a sequence-to-sequence model. The proposed model could generate relational facts freely. Widely conducted experiments on two public datasets demonstrate the efficacy of the proposed method. |
| Tasks | Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1035/ |
| https://www.aclweb.org/anthology/D19-1035 | |
| PWC | https://paperswithcode.com/paper/learning-the-extraction-order-of-multiple |
| Repo | |
| Framework | |
Annotation of Rhetorical Moves in Biochemistry Articles
| Title | Annotation of Rhetorical Moves in Biochemistry Articles |
| Authors | Mohammed Alliheedi, Robert E. Mercer, Robin Cohen |
| Abstract | This paper focuses on the real world application of scientific writing and on determining rhetorical moves, an important step in establishing the argument structure of biomedical articles. Using the observation that the structure of scholarly writing in laboratory-based experimental sciences closely follows laboratory procedures, we examine most closely the Methods section of the texts and adopt an approach of identifying rhetorical moves that are procedure-oriented. We also propose a verb-centric frame semantics with an effective set of semantic roles in order to support the analysis. These components are designed to support a computational model that extends a promising proposal of appropriate rhetorical moves for this domain, but one which is merely descriptive. Our work also contributes to the understanding of argument-related annotation schemes. In particular, we conduct a detailed study with human annotators to confirm that our selection of semantic roles is effective in determining the underlying rhetorical structure of existing biomedical articles in an extensive dataset. The annotated dataset that we produce provides the important knowledge needed for our ultimate goal of analyzing biochemistry articles. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4514/ |
| https://www.aclweb.org/anthology/W19-4514 | |
| PWC | https://paperswithcode.com/paper/annotation-of-rhetorical-moves-in |
| Repo | |
| Framework | |
Improving Relation Classification by Entity Pair Graph
| Title | Improving Relation Classification by Entity Pair Graph |
| Authors | Yi Zhao, Huaiyu Wan, Jianwei Gao, Youfang Lin |
| Abstract | Relation classification is one of the most important tasks in the field of information extraction, and also a key component of systems that require relational understanding of unstructured text. Existing relation classification approaches mainly rely on exploiting external resources and background knowledge to improve the performance and ignore the correlations between entity pairs which are helpful for relation classification. We present the concept of entity pair graph to represent the correlations between entity pairs and propose a novel entity pair graph based neural network (EPGNN) model, relying on graph convolutional network to capture the topological features of an entity pair graph. EPGNN combines sentence semantic features generated by pre-trained BERT model with graph topological features for relation classification. Our proposed model makes full use of a given corpus and forgoes the need of external resources and background knowledge. The experimental results on two widely used dataset: SemEval 2010 Task 8 and ACE 2005, show that our method outperforms the state-of-the-art approaches. |
| Tasks | Relation Classification, Relation Extraction |
| Published | 2019-11-17 |
| URL | http://proceedings.mlr.press/v101/zhao19a.html |
| http://proceedings.mlr.press/v101/zhao19a/zhao19a.pdf | |
| PWC | https://paperswithcode.com/paper/improving-relation-classification-by-entity |
| Repo | |
| Framework | |
Maximum Entropy Monte-Carlo Planning
| Title | Maximum Entropy Monte-Carlo Planning |
| Authors | Chenjun Xiao, Ruitong Huang, Jincheng Mei, Dale Schuurmans, Martin Müller |
| Abstract | We develop a new algorithm for online planning in large scale sequential decision problems that improves upon the worst case efficiency of UCT. The idea is to augment Monte-Carlo Tree Search (MCTS) with maximum entropy policy optimization, evaluating each search node by softmax values back-propagated from simulation. To establish the effectiveness of this approach, we first investigate the single-step decision problem, stochastic softmax bandits, and show that softmax values can be estimated at an optimal convergence rate in terms of mean squared error. We then extend this approach to general sequential decision making by developing a general MCTS algorithm, Maximum Entropy for Tree Search (MENTS). We prove that the probability of MENTS failing to identify the best decision at the root decays exponentially, which fundamentally improves the polynomial convergence rate of UCT. Our experimental results also demonstrate that MENTS is more sample efficient than UCT in both synthetic problems and Atari 2600 games. |
| Tasks | Atari Games, Decision Making |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9148-maximum-entropy-monte-carlo-planning |
| http://papers.nips.cc/paper/9148-maximum-entropy-monte-carlo-planning.pdf | |
| PWC | https://paperswithcode.com/paper/maximum-entropy-monte-carlo-planning |
| Repo | |
| Framework | |
