May 5, 2019

1271 words 6 mins read

Paper Group NANR 111

Paper Group NANR 111

The Instantiation Discourse Relation: A Corpus Analysis of Its Properties and Improved Detection. Leveraging FrameNet to Improve Automatic Event Detection. Proceedings of the 2nd Deep Machine Translation Workshop. WTF-LOD - A New Resource for Large-Scale NER Evaluation. A Domain Adaptation Regularization for Denoising Autoencoders. Phonological Pun …

The Instantiation Discourse Relation: A Corpus Analysis of Its Properties and Improved Detection

Title The Instantiation Discourse Relation: A Corpus Analysis of Its Properties and Improved Detection
Authors Junyi Jessy Li, Ani Nenkova
Abstract
Tasks Document Summarization, Sentiment Analysis
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-1141/
PDF https://www.aclweb.org/anthology/N16-1141
PWC https://paperswithcode.com/paper/the-instantiation-discourse-relation-a-corpus
Repo
Framework

Leveraging FrameNet to Improve Automatic Event Detection

Title Leveraging FrameNet to Improve Automatic Event Detection
Authors Shulin Liu, Yubo Chen, Shizhu He, Kang Liu, Jun Zhao
Abstract
Tasks
Published 2016-08-01
URL https://www.aclweb.org/anthology/P16-1201/
PDF https://www.aclweb.org/anthology/P16-1201
PWC https://paperswithcode.com/paper/leveraging-framenet-to-improve-automatic
Repo
Framework

Proceedings of the 2nd Deep Machine Translation Workshop

Title Proceedings of the 2nd Deep Machine Translation Workshop
Authors
Abstract
Tasks Machine Translation
Published 2016-10-01
URL https://www.aclweb.org/anthology/W16-6400/
PDF https://www.aclweb.org/anthology/W16-6400
PWC https://paperswithcode.com/paper/proceedings-of-the-2nd-deep-machine
Repo
Framework

WTF-LOD - A New Resource for Large-Scale NER Evaluation

Title WTF-LOD - A New Resource for Large-Scale NER Evaluation
Authors Lubomir Otrusina, Pavel Smrz
Abstract This paper introduces the Web TextFull linkage to Linked Open Data (WTF-LOD) dataset intended for large-scale evaluation of named entity recognition (NER) systems. First, we present the process of collecting data from the largest publically-available textual corpora, including Wikipedia dumps, monthly runs of the CommonCrawl, and ClueWeb09/12. We discuss similarities and differences of related initiatives such as WikiLinks and WikiReverse. Our work primarily focuses on links from {``}textfull{''} documents (links surrounded by a text that provides a useful context for entity linking), de-duplication of the data and advanced cleaning procedures. Presented statistics demonstrate that the collected data forms one of the largest available resource of its kind. They also prove suitability of the result for complex NER evaluation campaigns, including an analysis of the most ambiguous name mentions appearing in the data. |
Tasks Entity Linking, Named Entity Recognition
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1525/
PDF https://www.aclweb.org/anthology/L16-1525
PWC https://paperswithcode.com/paper/wtf-lod-a-new-resource-for-large-scale-ner
Repo
Framework

A Domain Adaptation Regularization for Denoising Autoencoders

Title A Domain Adaptation Regularization for Denoising Autoencoders
Authors St{'e}phane Clinchant, Gabriela Csurka, Boris Chidlovskii
Abstract
Tasks Denoising, Document Ranking, Domain Adaptation, Machine Translation, Named Entity Recognition, Opinion Mining, Part-Of-Speech Tagging, Text Classification, Topic Models, Transfer Learning, Word Embeddings
Published 2016-08-01
URL https://www.aclweb.org/anthology/P16-2005/
PDF https://www.aclweb.org/anthology/P16-2005
PWC https://paperswithcode.com/paper/a-domain-adaptation-regularization-for
Repo
Framework

Phonological Pun-derstanding

Title Phonological Pun-derstanding
Authors Aaron Jaech, Rik Koncel-Kedziorski, Mari Ostendorf
Abstract
Tasks Speech Recognition
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-1079/
PDF https://www.aclweb.org/anthology/N16-1079
PWC https://paperswithcode.com/paper/phonological-pun-derstanding
Repo
Framework

Normalized Log-Linear Interpolation of Backoff Language Models is Efficient

Title Normalized Log-Linear Interpolation of Backoff Language Models is Efficient
Authors Kenneth Heafield, Chase Geigle, Sean Massung, Lane Schwartz
Abstract
Tasks Language Modelling
Published 2016-08-01
URL https://www.aclweb.org/anthology/P16-1083/
PDF https://www.aclweb.org/anthology/P16-1083
PWC https://paperswithcode.com/paper/normalized-log-linear-interpolation-of
Repo
Framework

Assembling Narratives with Associative Threads

Title Assembling Narratives with Associative Threads
Authors Pierre-Luc Vaudry, Guy Lapalme
Abstract
Tasks Text Generation
Published 2016-09-01
URL https://www.aclweb.org/anthology/W16-5501/
PDF https://www.aclweb.org/anthology/W16-5501
PWC https://paperswithcode.com/paper/assembling-narratives-with-associative
Repo
Framework

Bag of What? Simple Noun Phrase Extraction for Text Analysis

Title Bag of What? Simple Noun Phrase Extraction for Text Analysis
Authors H, Abram ler, Matthew Denny, Hanna Wallach, Brendan O{'}Connor
Abstract
Tasks Text Classification
Published 2016-11-01
URL https://www.aclweb.org/anthology/W16-5615/
PDF https://www.aclweb.org/anthology/W16-5615
PWC https://paperswithcode.com/paper/bag-of-what-simple-noun-phrase-extraction-for
Repo
Framework

Part-of-speech Tagging of Code-mixed Social Media Content: Pipeline, Stacking and Joint Modelling

Title Part-of-speech Tagging of Code-mixed Social Media Content: Pipeline, Stacking and Joint Modelling
Authors Utsab Barman, Joachim Wagner, Jennifer Foster
Abstract
Tasks Language Identification, Part-Of-Speech Tagging
Published 2016-11-01
URL https://www.aclweb.org/anthology/W16-5804/
PDF https://www.aclweb.org/anthology/W16-5804
PWC https://paperswithcode.com/paper/part-of-speech-tagging-of-code-mixed-social
Repo
Framework

Context-aware Natural Language Generation for Spoken Dialogue Systems

Title Context-aware Natural Language Generation for Spoken Dialogue Systems
Authors Hao Zhou, Minlie Huang, Xiaoyan Zhu
Abstract Natural language generation (NLG) is an important component of question answering(QA) systems which has a significant impact on system quality. Most tranditional QA systems based on templates or rules tend to generate rigid and stylised responses without the natural variation of human language. Furthermore, such methods need an amount of work to generate the templates or rules. To address this problem, we propose a Context-Aware LSTM model for NLG. The model is completely driven by data without manual designed templates or rules. In addition, the context information, including the question to be answered, semantic values to be addressed in the response, and the dialogue act type during interaction, are well approached in the neural network model, which enables the model to produce variant and informative responses. The quantitative evaluation and human evaluation show that CA-LSTM obtains state-of-the-art performance.
Tasks Dialogue Generation, Question Answering, Spoken Dialogue Systems, Text Generation
Published 2016-12-01
URL https://www.aclweb.org/anthology/C16-1191/
PDF https://www.aclweb.org/anthology/C16-1191
PWC https://paperswithcode.com/paper/context-aware-natural-language-generation-for
Repo
Framework

Blind Regression: Nonparametric Regression for Latent Variable Models via Collaborative Filtering

Title Blind Regression: Nonparametric Regression for Latent Variable Models via Collaborative Filtering
Authors Dogyoon Song, Christina E. Lee, Yihua Li, Devavrat Shah
Abstract We introduce the framework of {\em blind regression} motivated by {\em matrix completion} for recommendation systems: given $m$ users, $n$ movies, and a subset of user-movie ratings, the goal is to predict the unobserved user-movie ratings given the data, i.e., to complete the partially observed matrix. Following the framework of non-parametric statistics, we posit that user $u$ and movie $i$ have features $x_1(u)$ and $x_2(i)$ respectively, and their corresponding rating $y(u,i)$ is a noisy measurement of $f(x_1(u), x_2(i))$ for some unknown function $f$. In contrast with classical regression, the features $x = (x_1(u), x_2(i))$ are not observed, making it challenging to apply standard regression methods to predict the unobserved ratings. Inspired by the classical Taylor’s expansion for differentiable functions, we provide a prediction algorithm that is consistent for all Lipschitz functions. In fact, the analysis through our framework naturally leads to a variant of collaborative filtering, shedding insight into the widespread success of collaborative filtering in practice. Assuming each entry is sampled independently with probability at least $\max(m^{-1+\delta},n^{-1/2+\delta})$ with $\delta > 0$, we prove that the expected fraction of our estimates with error greater than $\epsilon$ is less than $\gamma^2 / \epsilon^2$ plus a polynomially decaying term, where $\gamma^2$ is the variance of the additive entry-wise noise term. Experiments with the MovieLens and Netflix datasets suggest that our algorithm provides principled improvements over basic collaborative filtering and is competitive with matrix factorization methods.
Tasks Latent Variable Models, Matrix Completion, Recommendation Systems
Published 2016-12-01
URL http://papers.nips.cc/paper/6108-blind-regression-nonparametric-regression-for-latent-variable-models-via-collaborative-filtering
PDF http://papers.nips.cc/paper/6108-blind-regression-nonparametric-regression-for-latent-variable-models-via-collaborative-filtering.pdf
PWC https://paperswithcode.com/paper/blind-regression-nonparametric-regression-for
Repo
Framework

A Dutch Dysarthric Speech Database for Individualized Speech Therapy Research

Title A Dutch Dysarthric Speech Database for Individualized Speech Therapy Research
Authors Emre Yilmaz, Mario Ganzeboom, Lilian Beijer, Catia Cucchiarini, Helmer Strik
Abstract We present a new Dutch dysarthric speech database containing utterances of neurological patients with Parkinson{'}s disease, traumatic brain injury and cerebrovascular accident. The speech content is phonetically and linguistically diversified by using numerous structured sentence and word lists. Containing more than 6 hours of mildly to moderately dysarthric speech, this database can be used for research on dysarthria and for developing and testing speech-to-text systems designed for medical applications. Current activities aimed at extending this database are also discussed.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1127/
PDF https://www.aclweb.org/anthology/L16-1127
PWC https://paperswithcode.com/paper/a-dutch-dysarthric-speech-database-for
Repo
Framework

Proceedings of the Seventh International Workshop on Health Text Mining and Information Analysis

Title Proceedings of the Seventh International Workshop on Health Text Mining and Information Analysis
Authors
Abstract
Tasks
Published 2016-11-01
URL https://www.aclweb.org/anthology/W16-6100/
PDF https://www.aclweb.org/anthology/W16-6100
PWC https://paperswithcode.com/paper/proceedings-of-the-seventh-international
Repo
Framework

Visualizing the Content of a Children’s Story in a Virtual World: Lessons Learned

Title Visualizing the Content of a Children’s Story in a Virtual World: Lessons Learned
Authors Quynh Ngoc Thi Do, Steven Bethard, Marie-Francine Moens
Abstract
Tasks Language Modelling, Semantic Role Labeling
Published 2016-11-01
URL https://www.aclweb.org/anthology/W16-6009/
PDF https://www.aclweb.org/anthology/W16-6009
PWC https://paperswithcode.com/paper/visualizing-the-content-of-a-childrenas-story
Repo
Framework
comments powered by Disqus