Paper Group NANR 106
Cross-Lingual Parser Selection for Low-Resource Languages. Fake News Detection Through Multi-Perspective Speaker Profiles. Leveraging Eventive Information for Better Metaphor Detection and Classification. Proceedings of the MultiLing 2017 Workshop on Summarization and Summary Evaluation Across Source Types and Genres. How Would You Say It? Elicitin …
Cross-Lingual Parser Selection for Low-Resource Languages
| Title | Cross-Lingual Parser Selection for Low-Resource Languages |
| Authors | {\v{Z}}eljko Agi{'c} |
| Abstract | |
| Tasks | Cross-Lingual Transfer, Dependency Parsing, Tokenization, Transfer Learning |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0401/ |
| https://www.aclweb.org/anthology/W17-0401 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-parser-selection-for-low |
| Repo | |
| Framework | |
Fake News Detection Through Multi-Perspective Speaker Profiles
| Title | Fake News Detection Through Multi-Perspective Speaker Profiles |
| Authors | Yunfei Long, Qin Lu, Rong Xiang, Minglei Li, Chu-Ren Huang |
| Abstract | Automatic fake news detection is an important, yet very challenging topic. Traditional methods using lexical features have only very limited success. This paper proposes a novel method to incorporate speaker profiles into an attention based LSTM model for fake news detection. Speaker profiles contribute to the model in two ways. One is to include them in the attention model. The other includes them as additional input data. By adding speaker profiles such as party affiliation, speaker title, location and credit history, our model outperforms the state-of-the-art method by 14.5{%} in accuracy using a benchmark fake news detection dataset. This proves that speaker profiles provide valuable information to validate the credibility of news articles. |
| Tasks | Fake News Detection |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2043/ |
| https://www.aclweb.org/anthology/I17-2043 | |
| PWC | https://paperswithcode.com/paper/fake-news-detection-through-multi-perspective |
| Repo | |
| Framework | |
Leveraging Eventive Information for Better Metaphor Detection and Classification
| Title | Leveraging Eventive Information for Better Metaphor Detection and Classification |
| Authors | I-Hsuan Chen, Yunfei Long, Qin Lu, Chu-Ren Huang |
| Abstract | Metaphor detection has been both challenging and rewarding in natural language processing applications. This study offers a new approach based on eventive information in detecting metaphors by leveraging the Chinese writing system, which is a culturally bound ontological system organized according to the basic concepts represented by radicals. As such, the information represented is available in all Chinese text without pre-processing. Since metaphor detection is another culturally based conceptual representation, we hypothesize that sub-textual information can facilitate the identification and classification of the types of metaphoric events denoted in Chinese text. We propose a set of syntactic conditions crucial to event structures to improve the model based on the classification of radical groups. With the proposed syntactic conditions, the model achieves a performance of 0.8859 in terms of F-scores, making 1.7{%} of improvement than the same classifier with only Bag-of-word features. Results show that eventive information can improve the effectiveness of metaphor detection. Event information is rooted in every language, and thus this approach has a high potential to be applied to metaphor detection in other languages. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1006/ |
| https://www.aclweb.org/anthology/K17-1006 | |
| PWC | https://paperswithcode.com/paper/leveraging-eventive-information-for-better |
| Repo | |
| Framework | |
Proceedings of the MultiLing 2017 Workshop on Summarization and Summary Evaluation Across Source Types and Genres
| Title | Proceedings of the MultiLing 2017 Workshop on Summarization and Summary Evaluation Across Source Types and Genres |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1000/ |
| https://www.aclweb.org/anthology/W17-1000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-multiling-2017-workshop-on |
| Repo | |
| Framework | |
How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing
| Title | How Would You Say It? Eliciting Lexically Diverse Dialogue for Supervised Semantic Parsing |
| Authors | Ravich, Abhilasha er, Thomas Manzini, Matthias Grabmair, Graham Neubig, Jonathan Francis, Eric Nyberg |
| Abstract | Building dialogue interfaces for real-world scenarios often entails training semantic parsers starting from zero examples. How can we build datasets that better capture the variety of ways users might phrase their queries, and what queries are actually realistic? Wang et al. (2015) proposed a method to build semantic parsing datasets by generating canonical utterances using a grammar and having crowdworkers paraphrase them into natural wording. A limitation of this approach is that it induces bias towards using similar language as the canonical utterances. In this work, we present a methodology that elicits meaningful and lexically diverse queries from users for semantic parsing tasks. Starting from a seed lexicon and a generative grammar, we pair logical forms with mixed text-image representations and ask crowdworkers to paraphrase and confirm the plausibility of the queries that they generated. We use this method to build a semantic parsing dataset from scratch for a dialog agent in a smart-home simulation. We find evidence that this dataset, which we have named SmartHome, is demonstrably more lexically diverse and difficult to parse than existing domain-specific semantic parsing datasets. |
| Tasks | Semantic Parsing |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5545/ |
| https://www.aclweb.org/anthology/W17-5545 | |
| PWC | https://paperswithcode.com/paper/how-would-you-say-it-eliciting-lexically |
| Repo | |
| Framework | |
Robust Gaussian Graphical Model Estimation with Arbitrary Corruption
| Title | Robust Gaussian Graphical Model Estimation with Arbitrary Corruption |
| Authors | Lingxiao Wang, Quanquan Gu |
| Abstract | We study the problem of estimating the high-dimensional Gaussian graphical model where the data are arbitrarily corrupted. We propose a robust estimator for the sparse precision matrix in the high-dimensional regime. At the core of our method is a robust covariance matrix estimator, which is based on truncated inner product. We establish the statistical guarantee of our estimator on both estimation error and model selection consistency. In particular, we show that provided that the number of corrupted samples $n_2$ for each variable satisfies $n_2 \lesssim \sqrt{n}/\sqrt{\log d}$, where $n$ is the sample size and $d$ is the number of variables, the proposed robust precision matrix estimator attains the same statistical rate as the standard estimator for Gaussian graphical models. In addition, we propose a hypothesis testing procedure to assess the uncertainty of our robust estimator. We demonstrate the effectiveness of our method through extensive experiments on both synthetic data and real-world genomic data. |
| Tasks | Model Selection |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=718 |
| http://proceedings.mlr.press/v70/wang17d/wang17d.pdf | |
| PWC | https://paperswithcode.com/paper/robust-gaussian-graphical-model-estimation |
| Repo | |
| Framework | |
Common Round: Application of Language Technologies to Large-Scale Web Debates
| Title | Common Round: Application of Language Technologies to Large-Scale Web Debates |
| Authors | Hans Uszkoreit, Aleks Gabryszak, ra, Leonhard Hennig, J{"o}rg Steffen, Renlong Ai, Stephan Busemann, Jon Dehdari, Josef van Genabith, Georg Heigold, Nils Rethmeier, Raphael Rubino, Sven Schmeier, Philippe Thomas, He Wang, Feiyu Xu |
| Abstract | Web debates play an important role in enabling broad participation of constituencies in social, political and economic decision-taking. However, it is challenging to organize, structure, and navigate a vast number of diverse argumentations and comments collected from many participants over a long time period. In this paper we demonstrate Common Round, a next generation platform for large-scale web debates, which provides functions for eliciting the semantic content and structures from the contributions of participants. In particular, Common Round applies language technologies for the extraction of semantic essence from textual input, aggregation of the formulated opinions and arguments. The platform also provides a cross-lingual access to debates using machine translation. |
| Tasks | Decision Making, Machine Translation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3002/ |
| https://www.aclweb.org/anthology/E17-3002 | |
| PWC | https://paperswithcode.com/paper/common-round-application-of-language |
| Repo | |
| Framework | |
Predicting Depression for Japanese Blog Text
| Title | Predicting Depression for Japanese Blog Text |
| Authors | Misato Hiraga |
| Abstract | |
| Tasks | Feature Engineering, Text Classification |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3018/ |
| https://www.aclweb.org/anthology/P17-3018 | |
| PWC | https://paperswithcode.com/paper/predicting-depression-for-japanese-blog-text |
| Repo | |
| Framework | |
Overview of the 4th Workshop on Asian Translation
| Title | Overview of the 4th Workshop on Asian Translation |
| Authors | Toshiaki Nakazawa, Shohei Higashiyama, Chenchen Ding, Hideya Mino, Isao Goto, Hideto Kazawa, Yusuke Oda, Graham Neubig, Sadao Kurohashi |
| Abstract | This paper presents the results of the shared tasks from the 4th workshop on Asian translation (WAT2017) including J↔E, J↔C scientific paper translation subtasks, C↔J, K↔J, E↔J patent translation subtasks, H↔E mixed domain subtasks, J↔E newswire subtasks and J↔E recipe subtasks. For the WAT2017, 12 institutions participated in the shared tasks. About 300 translation results have been submitted to the automatic evaluation server, and selected submissions were manually evaluated. |
| Tasks | Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5701/ |
| https://www.aclweb.org/anthology/W17-5701 | |
| PWC | https://paperswithcode.com/paper/overview-of-the-4th-workshop-on-asian |
| Repo | |
| Framework | |
Proceedings of the Third Workshop on Computational Linguistics for Uralic Languages
| Title | Proceedings of the Third Workshop on Computational Linguistics for Uralic Languages |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-0600/ |
| https://www.aclweb.org/anthology/W17-0600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-third-workshop-on-3 |
| Repo | |
| Framework | |
Countering Feedback Delays in Multi-Agent Learning
| Title | Countering Feedback Delays in Multi-Agent Learning |
| Authors | Zhengyuan Zhou, Panayotis Mertikopoulos, Nicholas Bambos, Peter W. Glynn, Claire Tomlin |
| Abstract | We consider a model of game-theoretic learning based on online mirror descent (OMD) with asynchronous and delayed feedback information. Instead of focusing on specific games, we consider a broad class of continuous games defined by the general equilibrium stability notion, which we call λ-variational stability. Our first contribution is that, in this class of games, the actual sequence of play induced by OMD-based learning converges to Nash equilibria provided that the feedback delays faced by the players are synchronous and bounded. Subsequently, to tackle fully decentralized, asynchronous environments with (possibly) unbounded delays between actions and feedback, we propose a variant of OMD which we call delayed mirror descent (DMD), and which relies on the repeated leveraging of past information. With this modification, the algorithm converges to Nash equilibria with no feedback synchronicity assumptions and even when the delays grow superlinearly relative to the horizon of play. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7197-countering-feedback-delays-in-multi-agent-learning |
| http://papers.nips.cc/paper/7197-countering-feedback-delays-in-multi-agent-learning.pdf | |
| PWC | https://paperswithcode.com/paper/countering-feedback-delays-in-multi-agent |
| Repo | |
| Framework | |
The Importance of Communities for Learning to Influence
| Title | The Importance of Communities for Learning to Influence |
| Authors | Eric Balkanski, Nicole Immorlica, Yaron Singer |
| Abstract | We consider the canonical problem of influence maximization in social networks. Since the seminal work of Kempe, Kleinberg, and Tardos there have been two, largely disjoint efforts on this problem. The first studies the problem associated with learning the generative model that produces cascades, and the second focuses on the algorithmic challenge of identifying a set of influencers, assuming the generative model is known. Recent results on learning and optimization imply that in general, if the generative model is not known but rather learned from training data, no algorithm for influence maximization can yield a constant factor approximation guarantee using polynomially-many samples, drawn from any distribution. In this paper we describe a simple algorithm for maximizing influence from training data. The main idea behind the algorithm is to leverage the strong community structure of social networks and identify a set of individuals who are influentials but whose communities have little overlap. Although in general, the approximation guarantee of such an algorithm is unbounded, we show that this algorithm performs well experimentally. To analyze its performance, we prove this algorithm obtains a constant factor approximation guarantee on graphs generated through the stochastic block model, traditionally used to model networks with community structure. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/7168-the-importance-of-communities-for-learning-to-influence |
| http://papers.nips.cc/paper/7168-the-importance-of-communities-for-learning-to-influence.pdf | |
| PWC | https://paperswithcode.com/paper/the-importance-of-communities-for-learning-to |
| Repo | |
| Framework | |
Proceedings of the First Workshop on Language technology for Digital Humanities in Central and (South-)Eastern Europe
| Title | Proceedings of the First Workshop on Language technology for Digital Humanities in Central and (South-)Eastern Europe |
| Authors | Anca Dinu, Petya Osenova, Cristina Vertan |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/papers/W17-8100/w17-8100 |
| https://www.aclweb.org/anthology/W17-8100 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-language |
| Repo | |
| Framework | |
Improving Japanese-to-English Neural Machine Translation by Paraphrasing the Target Language
| Title | Improving Japanese-to-English Neural Machine Translation by Paraphrasing the Target Language |
| Authors | Yuuki Sekizawa, Tomoyuki Kajiwara, Mamoru Komachi |
| Abstract | Neural machine translation (NMT) produces sentences that are more fluent than those produced by statistical machine translation (SMT). However, NMT has a very high computational cost because of the high dimensionality of the output layer. Generally, NMT restricts the size of vocabulary, which results in infrequent words being treated as out-of-vocabulary (OOV) and degrades the performance of the translation. In evaluation, we achieved a statistically significant BLEU score improvement of 0.55-0.77 over the baselines including the state-of-the-art method. |
| Tasks | Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5703/ |
| https://www.aclweb.org/anthology/W17-5703 | |
| PWC | https://paperswithcode.com/paper/improving-japanese-to-english-neural-machine |
| Repo | |
| Framework | |
A Comprehensive Analysis of Bilingual Lexicon Induction
| Title | A Comprehensive Analysis of Bilingual Lexicon Induction |
| Authors | Ann Irvine, Chris Callison-Burch |
| Abstract | Bilingual lexicon induction is the task of inducing word translations from monolingual corpora in two languages. In this article we present the most comprehensive analysis of bilingual lexicon induction to date. We present experiments on a wide range of languages and data sizes. We examine translation into English from 25 foreign languages: Albanian, Azeri, Bengali, Bosnian, Bulgarian, Cebuano, Gujarati, Hindi, Hungarian, Indonesian, Latvian, Nepali, Romanian, Serbian, Slovak, Somali, Spanish, Swedish, Tamil, Telugu, Turkish, Ukrainian, Uzbek, Vietnamese, and Welsh. We analyze the behavior of bilingual lexicon induction on low-frequency words, rather than testing solely on high-frequency words, as previous research has done. Low-frequency words are more relevant to statistical machine translation, where systems typically lack translations of rare words that fall outside of their training data. We systematically explore a wide range of features and phenomena that affect the quality of the translations discovered by bilingual lexicon induction. We provide illustrative examples of the highest ranking translations for orthogonal signals of translation equivalence like contextual similarity and temporal similarity. We analyze the effects of frequency and burstiness, and the sizes of the seed bilingual dictionaries and the monolingual training corpora. Additionally, we introduce a novel discriminative approach to bilingual lexicon induction. Our discriminative model is capable of combining a wide variety of features that individually provide only weak indications of translation equivalence. When feature weights are discriminatively set, these signals produce dramatically higher translation quality than previous approaches that combined signals in an unsupervised fashion (e.g., using minimum reciprocal rank). We also directly compare our model{'}s performance against a sophisticated generative approach, the matching canonical correlation analysis (MCCA) algorithm used by Haghighi et al. (2008). Our algorithm achieves an accuracy of 42{%} versus MCCA{'}s 15{%}. |
| Tasks | Machine Translation |
| Published | 2017-06-01 |
| URL | https://www.aclweb.org/anthology/J17-2001/ |
| https://www.aclweb.org/anthology/J17-2001 | |
| PWC | https://paperswithcode.com/paper/a-comprehensive-analysis-of-bilingual-lexicon |
| Repo | |
| Framework | |
