May 5, 2019

1283 words 7 mins read

Paper Group NANR 41

Paper Group NANR 41

A New Integrated Open-source Morphological Analyzer for Hungarian. Exploring Semantic Representation in Brain Activity Using Word Embeddings. Finding Definitions in Large Corpora with Sketch Engine. CLPsych 2016 Shared Task: Triaging content in online peer-support forums. Regularizing Text Categorization with Clusters of Words. 基於相依詞向量的剖析結果重估與排序(N- …

A New Integrated Open-source Morphological Analyzer for Hungarian

Title A New Integrated Open-source Morphological Analyzer for Hungarian
Authors Attila Nov{'a}k, Borb{'a}la Sikl{'o}si, Csaba Oravecz
Abstract The goal of a Hungarian research project has been to create an integrated Hungarian natural language processing framework. This infrastructure includes tools for analyzing Hungarian texts, integrated into a standardized environment. The morphological analyzer is one of the core components of the framework. The goal of this paper is to describe a fast and customizable morphological analyzer and its development framework, which synthesizes and further enriches the morphological knowledge implemented in previous tools existing for Hungarian. In addition, we present the method we applied to add semantic knowledge to the lexical database of the morphology. The method utilizes neural word embedding models and morphological and shallow syntactic knowledge.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1209/
PDF https://www.aclweb.org/anthology/L16-1209
PWC https://paperswithcode.com/paper/a-new-integrated-open-source-morphological
Repo
Framework

Exploring Semantic Representation in Brain Activity Using Word Embeddings

Title Exploring Semantic Representation in Brain Activity Using Word Embeddings
Authors Yu-Ping Ruan, Zhen-Hua Ling, Yu Hu
Abstract
Tasks Semantic Textual Similarity, Word Embeddings
Published 2016-11-01
URL https://www.aclweb.org/anthology/D16-1064/
PDF https://www.aclweb.org/anthology/D16-1064
PWC https://paperswithcode.com/paper/exploring-semantic-representation-in-brain
Repo
Framework

Finding Definitions in Large Corpora with Sketch Engine

Title Finding Definitions in Large Corpora with Sketch Engine
Authors Vojt{\v{e}}ch Kov{'a}{\v{r}}, Monika Mo{\v{c}}iarikov{'a}, Pavel Rychl{'y}
Abstract The paper describes automatic definition finding implemented within the leading corpus query and management tool, Sketch Engine. The implementation exploits complex pattern-matching queries in the corpus query language (CQL) and the indexing mechanism of word sketches for finding and storing definition candidates throughout the corpus. The approach is evaluated for Czech and English corpora, showing that the results are usable in practice: precision of the tool ranges between 30 and 75 percent (depending on the major corpus text types) and we were able to extract nearly 2 million definition candidates from an English corpus with 1.4 billion words. The feature is embedded into the interface as a concordance filter, so that users can search for definitions of any query to the corpus, including very specific multi-word queries. The results also indicate that ordinary texts (unlike explanatory texts) contain rather low number of definitions, which is perhaps the most important problem with automatic definition finding in general.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1061/
PDF https://www.aclweb.org/anthology/L16-1061
PWC https://paperswithcode.com/paper/finding-definitions-in-large-corpora-with
Repo
Framework

CLPsych 2016 Shared Task: Triaging content in online peer-support forums

Title CLPsych 2016 Shared Task: Triaging content in online peer-support forums
Authors David N. Milne, Glen Pink, Ben Hachey, Rafael A. Calvo
Abstract
Tasks
Published 2016-06-01
URL https://www.aclweb.org/anthology/W16-0312/
PDF https://www.aclweb.org/anthology/W16-0312
PWC https://paperswithcode.com/paper/clpsych-2016-shared-task-triaging-content-in
Repo
Framework

Regularizing Text Categorization with Clusters of Words

Title Regularizing Text Categorization with Clusters of Words
Authors Konstantinos Skianis, Fran{\c{c}}ois Rousseau, Michalis Vazirgiannis
Abstract
Tasks Language Modelling, Opinion Mining, Structured Prediction, Text Categorization, Text Classification
Published 2016-11-01
URL https://www.aclweb.org/anthology/D16-1188/
PDF https://www.aclweb.org/anthology/D16-1188
PWC https://paperswithcode.com/paper/regularizing-text-categorization-with
Repo
Framework

基於相依詞向量的剖析結果重估與排序(N-best Parse Rescoring Based on Dependency-Based Word Embeddings)

Title 基於相依詞向量的剖析結果重估與排序(N-best Parse Rescoring Based on Dependency-Based Word Embeddings)
Authors Yu-Ming Hsieh, Wei-Yun Ma
Abstract
Tasks Word Embeddings
Published 2016-10-01
URL https://www.aclweb.org/anthology/O16-1010/
PDF https://www.aclweb.org/anthology/O16-1010
PWC https://paperswithcode.com/paper/ao14c-a34eaecacea14eaon-best-parse-rescoring
Repo
Framework

C-WEP―Rich Annotated Collection of Writing Errors by Professionals

Title C-WEP―Rich Annotated Collection of Writing Errors by Professionals
Authors Cerstin Mahlow
Abstract This paper presents C-WEP, the Collection of Writing Errors by Professionals Writers of German. It currently consists of 245 sentences with grammatical errors. All sentences are taken from published texts. All authors are professional writers with high skill levels with respect to German, the genres, and the topics. The purpose of this collection is to provide seeds for more sophisticated writing support tools as only a very small proportion of those errors can be detected by state-of-the-art checkers. C-WEP is annotated on various levels and freely available.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1456/
PDF https://www.aclweb.org/anthology/L16-1456
PWC https://paperswithcode.com/paper/c-weparich-annotated-collection-of-writing
Repo
Framework

Learning to Identify Metaphors from a Corpus of Proverbs

Title Learning to Identify Metaphors from a Corpus of Proverbs
Authors G{"o}zde {"O}zbal, Carlo Strapparava, Serra Sinem Tekiro{\u{g}}lu, Daniele Pighin
Abstract
Tasks
Published 2016-11-01
URL https://www.aclweb.org/anthology/D16-1220/
PDF https://www.aclweb.org/anthology/D16-1220
PWC https://paperswithcode.com/paper/learning-to-identify-metaphors-from-a-corpus
Repo
Framework

A Challenge Proposal for Narrative Generation Using CNLs

Title A Challenge Proposal for Narrative Generation Using CNLs
Authors Eugenio Concepci{'o}n, Gonzalo M{'e}ndez, Pablo Gerv{'a}s, Carlos Le{'o}n
Abstract
Tasks Text Generation
Published 2016-09-01
URL https://www.aclweb.org/anthology/W16-6628/
PDF https://www.aclweb.org/anthology/W16-6628
PWC https://paperswithcode.com/paper/a-challenge-proposal-for-narrative-generation
Repo
Framework

Mixed vine copulas as joint models of spike counts and local field potentials

Title Mixed vine copulas as joint models of spike counts and local field potentials
Authors Arno Onken, Stefano Panzeri
Abstract Concurrent measurements of neural activity at multiple scales, sometimes performed with multimodal techniques, become increasingly important for studying brain function. However, statistical methods for their concurrent analysis are currently lacking. Here we introduce such techniques in a framework based on vine copulas with mixed margins to construct multivariate stochastic models. These models can describe detailed mixed interactions between discrete variables such as neural spike counts, and continuous variables such as local field potentials. We propose efficient methods for likelihood calculation, inference, sampling and mutual information estimation within this framework. We test our methods on simulated data and demonstrate applicability on mixed data generated by a biologically realistic neural network. Our methods hold the promise to considerably improve statistical analysis of neural data recorded simultaneously at different scales.
Tasks
Published 2016-12-01
URL http://papers.nips.cc/paper/6069-mixed-vine-copulas-as-joint-models-of-spike-counts-and-local-field-potentials
PDF http://papers.nips.cc/paper/6069-mixed-vine-copulas-as-joint-models-of-spike-counts-and-local-field-potentials.pdf
PWC https://paperswithcode.com/paper/mixed-vine-copulas-as-joint-models-of-spike
Repo
Framework

Individual Variation in the Choice of Referential Form

Title Individual Variation in the Choice of Referential Form
Authors Thiago Castro Ferreira, Emiel Krahmer, S Wubben, er
Abstract
Tasks Text Generation
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-1048/
PDF https://www.aclweb.org/anthology/N16-1048
PWC https://paperswithcode.com/paper/individual-variation-in-the-choice-of
Repo
Framework

以多層感知器辨識情緒於國台客語料庫 (Use Multilayer Perceptron To Recognize Emotion in Mandarin,Taiwanese and Hakka Database) [In Chinese]

Title 以多層感知器辨識情緒於國台客語料庫 (Use Multilayer Perceptron To Recognize Emotion in Mandarin,Taiwanese and Hakka Database) [In Chinese]
Authors Chia-Hsien Chan, Chia-Ping Chen
Abstract
Tasks
Published 2016-10-01
URL https://www.aclweb.org/anthology/O16-1004/
PDF https://www.aclweb.org/anthology/O16-1004
PWC https://paperswithcode.com/paper/aaaca-e34-ec14aaaeaao-use-multilayer
Repo
Framework

The Role of Context in Neural Morphological Disambiguation

Title The Role of Context in Neural Morphological Disambiguation
Authors Qinlan Shen, Daniel Clothiaux, Emily Tagtow, Patrick Littell, Chris Dyer
Abstract Languages with rich morphology often introduce sparsity in language processing tasks. While morphological analyzers can reduce this sparsity by providing morpheme-level analyses for words, they will often introduce ambiguity by returning multiple analyses for the same surface form. The problem of disambiguating between these morphological parses is further complicated by the fact that a correct parse for a word is not only be dependent on the surface form but also on other words in its context. In this paper, we present a language-agnostic approach to morphological disambiguation. We address the problem of using context in morphological disambiguation by presenting several LSTM-based neural architectures that encode long-range surface-level and analysis-level contextual dependencies. We applied our approach to Turkish, Russian, and Arabic to compare effectiveness across languages, matching state-of-the-art results in two of the three languages. Our results also demonstrate that while context plays a role in learning how to disambiguate, the type and amount of context needed varies between languages.
Tasks
Published 2016-12-01
URL https://www.aclweb.org/anthology/C16-1018/
PDF https://www.aclweb.org/anthology/C16-1018
PWC https://paperswithcode.com/paper/the-role-of-context-in-neural-morphological
Repo
Framework

Argumentative texts and clause types

Title Argumentative texts and clause types
Authors Maria Becker, Alexis Palmer, Anette Frank
Abstract
Tasks Argument Mining, Language Modelling
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2803/
PDF https://www.aclweb.org/anthology/W16-2803
PWC https://paperswithcode.com/paper/argumentative-texts-and-clause-types
Repo
Framework

Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)

Title Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
Authors
Abstract
Tasks
Published 2016-08-01
URL https://www.aclweb.org/anthology/P16-2000/
PDF https://www.aclweb.org/anthology/P16-2000
PWC https://paperswithcode.com/paper/proceedings-of-the-54th-annual-meeting-of-the-1
Repo
Framework
comments powered by Disqus