Paper Group NANR 223
Computing and maximizing influence in linear threshold and triggering models. pigeo: A Python Geotagging Tool. Creating Interactive Macaronic Interfaces for Language Learning. Personalized Exercises for Preposition Learning. Strong Associations Can Be Weak: Some Thoughts on Cross-lingual Word Webs for Translation. Towards Automatic Identification o …
Computing and maximizing influence in linear threshold and triggering models
| Title | Computing and maximizing influence in linear threshold and triggering models |
| Authors | Justin T. Khim, Varun Jog, Po-Ling Loh |
| Abstract | We establish upper and lower bounds for the influence of a set of nodes in certain types of contagion models. We derive two sets of bounds, the first designed for linear threshold models, and the second more broadly applicable to a general class of triggering models, which subsumes the popular independent cascade models, as well. We quantify the gap between our upper and lower bounds in the case of the linear threshold model and illustrate the gains of our upper bounds for independent cascade models in relation to existing results. Importantly, our lower bounds are monotonic and submodular, implying that a greedy algorithm for influence maximization is guaranteed to produce a maximizer within a (1 - 1/e)-factor of the truth. Although the problem of exact influence computation is NP-hard in general, our bounds may be evaluated efficiently. This leads to an attractive, highly scalable algorithm for influence maximization with rigorous theoretical guarantees. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6347-computing-and-maximizing-influence-in-linear-threshold-and-triggering-models |
| http://papers.nips.cc/paper/6347-computing-and-maximizing-influence-in-linear-threshold-and-triggering-models.pdf | |
| PWC | https://paperswithcode.com/paper/computing-and-maximizing-influence-in-linear |
| Repo | |
| Framework | |
pigeo: A Python Geotagging Tool
| Title | pigeo: A Python Geotagging Tool |
| Authors | Afshin Rahimi, Trevor Cohn, Timothy Baldwin |
| Abstract | |
| Tasks | Recommendation Systems |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-4022/ |
| https://www.aclweb.org/anthology/P16-4022 | |
| PWC | https://paperswithcode.com/paper/pigeo-a-python-geotagging-tool |
| Repo | |
| Framework | |
Creating Interactive Macaronic Interfaces for Language Learning
| Title | Creating Interactive Macaronic Interfaces for Language Learning |
| Authors | Adithya Renduchintala, Rebecca Knowles, Philipp Koehn, Jason Eisner |
| Abstract | |
| Tasks | Language Acquisition, Machine Translation, Reading Comprehension |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-4023/ |
| https://www.aclweb.org/anthology/P16-4023 | |
| PWC | https://paperswithcode.com/paper/creating-interactive-macaronic-interfaces-for |
| Repo | |
| Framework | |
Personalized Exercises for Preposition Learning
| Title | Personalized Exercises for Preposition Learning |
| Authors | John Lee, Mengqi Luo |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-4020/ |
| https://www.aclweb.org/anthology/P16-4020 | |
| PWC | https://paperswithcode.com/paper/personalized-exercises-for-preposition |
| Repo | |
| Framework | |
Strong Associations Can Be Weak: Some Thoughts on Cross-lingual Word Webs for Translation
| Title | Strong Associations Can Be Weak: Some Thoughts on Cross-lingual Word Webs for Translation |
| Authors | Oi Yee Kwong |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-2023/ |
| https://www.aclweb.org/anthology/Y16-2023 | |
| PWC | https://paperswithcode.com/paper/strong-associations-can-be-weak-some-thoughts |
| Repo | |
| Framework | |
Towards Automatic Identification of Effective Clues for Team Word-Guessing Games
| Title | Towards Automatic Identification of Effective Clues for Team Word-Guessing Games |
| Authors | Eli Pincus, David Traum |
| Abstract | Team word-guessing games where one player, the clue-giver, gives clues attempting to elicit a target-word from another player, the receiver, are a popular form of entertainment and also used for educational purposes. Creating an engaging computational agent capable of emulating a talented human clue-giver in a timed word-guessing game depends on the ability to provide effective clues (clues able to elicit a correct guess from a human receiver). There are many available web resources and databases that can be mined for the raw material for clues for target-words; however, a large number of those clues are unlikely to be able to elicit a correct guess from a human guesser. In this paper, we propose a method for automatically filtering a clue corpus for effective clues for an arbitrary target-word from a larger set of potential clues, using machine learning on a set of features of the clues, including point-wise mutual information between a clue{'}s constituent words and a clue{'}s target-word. The results of the experiments significantly improve the average clue quality over previous approaches, and bring quality rates in-line with measures of human clue quality derived from a corpus of human-human interactions. The paper also introduces the data used to develop this method; audio recordings of people making guesses after having heard the clues being spoken by a synthesized voice. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1435/ |
| https://www.aclweb.org/anthology/L16-1435 | |
| PWC | https://paperswithcode.com/paper/towards-automatic-identification-of-effective |
| Repo | |
| Framework | |
Exploring Autism Spectrum Disorders Using HLT
| Title | Exploring Autism Spectrum Disorders Using HLT |
| Authors | Julia Parish-Morris, Mark Liberman, Neville Ryant, Christopher Cieri, Leila Bateman, Emily Ferguson, Robert Schultz |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0308/ |
| https://www.aclweb.org/anthology/W16-0308 | |
| PWC | https://paperswithcode.com/paper/exploring-autism-spectrum-disorders-using-hlt |
| Repo | |
| Framework | |
VerbLexPor: a lexical resource with semantic roles for Portuguese
| Title | VerbLexPor: a lexical resource with semantic roles for Portuguese |
| Authors | Leonardo Zilio, Maria Jos{'e} Bocorny Finatto, Aline Villavicencio |
| Abstract | This paper presents a lexical resource developed for Portuguese. The resource contains sentences annotated with semantic roles. The sentences were extracted from two domains: Cardiology research papers and newspaper articles. Both corpora were analyzed with the PALAVRAS parser and subsequently processed with a subcategorization frames extractor, so that each sentence that contained at least one main verb was stored in a database together with its syntactic organization. The annotation was manually carried out by a linguist using an annotation interface. Both the annotated and non-annotated data were exported to an XML format, which is readily available for download. The reason behind exporting non-annotated data is that there is syntactic information collected from the parser annotation in the non-annotated data, and this could be useful for other researchers. The sentences from both corpora were annotated separately, so that it is possible to access sentences either from the Cardiology or from the newspaper corpus. The full resource presents more than seven thousand semantically annotated sentences, containing 192 different verbs and more than 15 thousand individual arguments and adjuncts. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1422/ |
| https://www.aclweb.org/anthology/L16-1422 | |
| PWC | https://paperswithcode.com/paper/verblexpor-a-lexical-resource-with-semantic |
| Repo | |
| Framework | |
A Latent Variable Recurrent Neural Network for Discourse-Driven Language Models
| Title | A Latent Variable Recurrent Neural Network for Discourse-Driven Language Models |
| Authors | Yangfeng Ji, Gholamreza Haffari, Jacob Eisenstein |
| Abstract | |
| Tasks | Dialog Act Classification, Implicit Discourse Relation Classification, Language Modelling, Relation Classification |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1037/ |
| https://www.aclweb.org/anthology/N16-1037 | |
| PWC | https://paperswithcode.com/paper/a-latent-variable-recurrent-neural-network-1 |
| Repo | |
| Framework | |
Shift-Reduce CCG Parsing using Neural Network Models
| Title | Shift-Reduce CCG Parsing using Neural Network Models |
| Authors | Bharat Ram Ambati, Tejaswini Deoskar, Mark Steedman |
| Abstract | |
| Tasks | CCG Supertagging, Dependency Parsing |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1052/ |
| https://www.aclweb.org/anthology/N16-1052 | |
| PWC | https://paperswithcode.com/paper/shift-reduce-ccg-parsing-using-neural-network |
| Repo | |
| Framework | |
Fast Active Set Methods for Online Spike Inference from Calcium Imaging
| Title | Fast Active Set Methods for Online Spike Inference from Calcium Imaging |
| Authors | Johannes Friedrich, Liam Paninski |
| Abstract | Fluorescent calcium indicators are a popular means for observing the spiking activity of large neuronal populations. Unfortunately, extracting the spike train of each neuron from raw fluorescence calcium imaging data is a nontrivial problem. We present a fast online active set method to solve this sparse nonnegative deconvolution problem. Importantly, the algorithm progresses through each time series sequentially from beginning to end, thus enabling real-time online spike inference during the imaging session. Our algorithm is a generalization of the pool adjacent violators algorithm (PAVA) for isotonic regression and inherits its linear-time computational complexity. We gain remarkable increases in processing speed: more than one order of magnitude compared to currently employed state of the art convex solvers relying on interior point methods. Our method can exploit warm starts; therefore optimizing model hyperparameters only requires a handful of passes through the data. The algorithm enables real-time simultaneous deconvolution of $O(10^5)$ traces of whole-brain zebrafish imaging data on a laptop. |
| Tasks | Time Series |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6505-fast-active-set-methods-for-online-spike-inference-from-calcium-imaging |
| http://papers.nips.cc/paper/6505-fast-active-set-methods-for-online-spike-inference-from-calcium-imaging.pdf | |
| PWC | https://paperswithcode.com/paper/fast-active-set-methods-for-online-spike |
| Repo | |
| Framework | |
``Making the News’': Identifying Noteworthy Events in News Articles
| Title | ``Making the News’': Identifying Noteworthy Events in News Articles | |
| Authors | Shyam Upadhyay, Christos Christodoulopoulos, Dan Roth |
| Abstract | |
| Tasks | Document Summarization |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-1001/ |
| https://www.aclweb.org/anthology/W16-1001 | |
| PWC | https://paperswithcode.com/paper/making-the-news-identifying-noteworthy-events |
| Repo | |
| Framework | |
Event Linking with Sentential Features from Convolutional Neural Networks
| Title | Event Linking with Sentential Features from Convolutional Neural Networks |
| Authors | Sebastian Krause, Feiyu Xu, Hans Uszkoreit, Dirk Weissenborn |
| Abstract | |
| Tasks | Coreference Resolution, Slot Filling |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/K16-1024/ |
| https://www.aclweb.org/anthology/K16-1024 | |
| PWC | https://paperswithcode.com/paper/event-linking-with-sentential-features-from |
| Repo | |
| Framework | |
Leveraging Annotators’ Gaze Behaviour for Coreference Resolution
| Title | Leveraging Annotators’ Gaze Behaviour for Coreference Resolution |
| Authors | Joe Cheri, Abhijit Mishra, Pushpak Bhattacharyya |
| Abstract | |
| Tasks | Coreference Resolution, Information Retrieval, Sentiment Analysis, Word Sense Disambiguation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1904/ |
| https://www.aclweb.org/anthology/W16-1904 | |
| PWC | https://paperswithcode.com/paper/leveraging-annotators-gaze-behaviour-for |
| Repo | |
| Framework | |
A Rule-based Shallow-transfer Machine Translation System for Scots and English
| Title | A Rule-based Shallow-transfer Machine Translation System for Scots and English |
| Authors | Gavin Abercrombie |
| Abstract | An open-source rule-based machine translation system is developed for Scots, a low-resourced minor language closely related to English and spoken in Scotland and Ireland. By concentrating on translation for assimilation (gist comprehension) from Scots to English, it is proposed that the development of dictionaries designed to be used with in the Apertium platform will be sufficient to produce translations that improve non-Scots speakers understanding of the language. Mono- and bilingual Scots dictionaries are constructed using lexical items gathered from a variety of resources across several domains. Although the primary goal of this project is translation for gisting, the system is evaluated for both assimilation and dissemination (publication-ready translations). A variety of evaluation methods are used, including a cloze test undertaken by human volunteers. While evaluation results are comparable to, and in some cases superior to, those of other language pairs within the Apertium platform, room for improvement is identified in several areas of the system. |
| Tasks | Machine Translation |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1092/ |
| https://www.aclweb.org/anthology/L16-1092 | |
| PWC | https://paperswithcode.com/paper/a-rule-based-shallow-transfer-machine |
| Repo | |
| Framework | |
