May 5, 2019

984 words 5 mins read

Paper Group NANR 18

Vanilla Classifiers for Distinguishing between Similar Languages. Moses & Treex Hybrid MT Systems Bestiary. A Hybrid Approach for Deep Machine Translation. High-Fidelity Lexical Axiom Construction from Verb Glosses. Incorporation of a valency lexicon into a TectoMT pipeline. From distributions to labels: A lexical proficiency analysis using learne …

Vanilla Classifiers for Distinguishing between Similar Languages


Title	Vanilla Classifiers for Distinguishing between Similar Languages
Authors	Sergiu Nisioi, Alina Maria Ciobanu, Liviu P. Dinu
Abstract	In this paper we describe the submission of the UniBuc-NLP team for the Discriminating between Similar Languages Shared Task, DSL 2016. We present and analyze the results we obtained in the closed track of sub-task 1 (Similar languages and language varieties) and sub-task 2 (Arabic dialects). For sub-task 1 we used a logistic regression classifier with tf-idf feature weighting and for sub-task 2 a character-based string kernel with an SVM classifier. Our results show that good accuracy scores can be obtained with limited feature and model engineering. While certain limitations are to be acknowledged, our approach worked surprisingly well for out-of-domain, social media data, with 0.898 accuracy (3rd place) for dataset B1 and 0.838 accuracy (4th place) for dataset B2.
Tasks	Information Retrieval, Language Identification, Question Answering
Published	2016-12-01
URL	https://www.aclweb.org/anthology/W16-4830/
PDF	https://www.aclweb.org/anthology/W16-4830
PWC	https://paperswithcode.com/paper/vanilla-classifiers-for-distinguishing
Repo
Framework

Moses & Treex Hybrid MT Systems Bestiary


Title	Moses & Treex Hybrid MT Systems Bestiary
Authors	Rudolf Rosa, Martin Popel, Ond{\v{r}}ej Bojar, David Mare{\v{c}}ek, Ond{\v{r}}ej Du{\v{s}}ek
Abstract
Tasks	Language Modelling, Machine Translation, Tokenization, Word Alignment
Published	2016-10-01
URL	https://www.aclweb.org/anthology/W16-6401/
PDF	https://www.aclweb.org/anthology/W16-6401
PWC	https://paperswithcode.com/paper/moses-treex-hybrid-mt-systems-bestiary
Repo
Framework

A Hybrid Approach for Deep Machine Translation


Title	A Hybrid Approach for Deep Machine Translation
Authors	Kiril Simov, Petya Osenova
Abstract
Tasks	Machine Translation, Natural Language Inference, Word Sense Disambiguation
Published	2016-10-01
URL	https://www.aclweb.org/anthology/W16-6403/
PDF	https://www.aclweb.org/anthology/W16-6403
PWC	https://paperswithcode.com/paper/a-hybrid-approach-for-deep-machine
Repo
Framework

High-Fidelity Lexical Axiom Construction from Verb Glosses


Title	High-Fidelity Lexical Axiom Construction from Verb Glosses
Authors	Gene Kim, Lenhart Schubert
Abstract
Tasks
Published	2016-08-01
URL	https://www.aclweb.org/anthology/S16-2004/
PDF	https://www.aclweb.org/anthology/S16-2004
PWC	https://paperswithcode.com/paper/high-fidelity-lexical-axiom-construction-from
Repo
Framework

Incorporation of a valency lexicon into a TectoMT pipeline


Title	Incorporation of a valency lexicon into a TectoMT pipeline
Authors	Natalia Klyueva, Vladislav Kubo{\v{n}}
Abstract
Tasks	Machine Translation
Published	2016-10-01
URL	https://www.aclweb.org/anthology/W16-6406/
PDF	https://www.aclweb.org/anthology/W16-6406
PWC	https://paperswithcode.com/paper/incorporation-of-a-valency-lexicon-into-a
Repo
Framework

From distributions to labels: A lexical proficiency analysis using learner corpora


Title	From distributions to labels: A lexical proficiency analysis using learner corpora
Authors	David Alfter, Yuri Bizzoni, Anders Agebj{"o}rn, Elena Volodina, Ildik{'o} Pil{'a}n
Abstract
Tasks
Published	2016-11-01
URL	https://www.aclweb.org/anthology/W16-6501/
PDF	https://www.aclweb.org/anthology/W16-6501
PWC	https://paperswithcode.com/paper/from-distributions-to-labels-a-lexical
Repo
Framework

WIKIPARQ: A Tabulated Wikipedia Resource Using the Parquet Format


Title	WIKIPARQ: A Tabulated Wikipedia Resource Using the Parquet Format
Authors	Marcus Klang, Pierre Nugues
Abstract	Wikipedia has become one of the most popular resources in natural language processing and it is used in quantities of applications. However, Wikipedia requires a substantial pre-processing step before it can be used. For instance, its set of nonstandardized annotations, referred to as the wiki markup, is language-dependent and needs specific parsers from language to language, for English, French, Italian, etc. In addition, the intricacies of the different Wikipedia resources: main article text, categories, wikidata, infoboxes, scattered into the article document or in different files make it difficult to have global view of this outstanding resource. In this paper, we describe WikiParq, a unified format based on the Parquet standard to tabulate and package the Wikipedia corpora. In combination with Spark, a map-reduce computing framework, and the SQL query language, WikiParq makes it much easier to write database queries to extract specific information or subcorpora from Wikipedia, such as all the first paragraphs of the articles in French, or all the articles on persons in Spanish, or all the articles on persons that have versions in French, English, and Spanish. WikiParq is available in six language versions and is potentially extendible to all the languages of Wikipedia. The WikiParq files are downloadable as tarball archives from this location: http://semantica.cs.lth.se/wikiparq/.
Tasks
Published	2016-05-01
URL	https://www.aclweb.org/anthology/L16-1654/
PDF	https://www.aclweb.org/anthology/L16-1654
PWC	https://paperswithcode.com/paper/wikiparq-a-tabulated-wikipedia-resource-using
Repo
Framework

Word comprehension and multilingualism among toddlers: A study using touch screens in daycares


Title	Word comprehension and multilingualism among toddlers: A study using touch screens in daycares
Authors	Laia Fibla, Charlotte Maniel, Alej Cristia, rina
Abstract
Tasks	Language Acquisition
Published	2016-11-01
URL	https://www.aclweb.org/anthology/W16-6503/
PDF	https://www.aclweb.org/anthology/W16-6503
PWC	https://paperswithcode.com/paper/word-comprehension-and-multilingualism-among
Repo
Framework

Proceedings of the 9th International Natural Language Generation conference


Title	Proceedings of the 9th International Natural Language Generation conference
Authors
Abstract
Tasks	Text Generation
Published	2016-09-01
URL	https://www.aclweb.org/anthology/W16-6600/
PDF	https://www.aclweb.org/anthology/W16-6600
PWC	https://paperswithcode.com/paper/proceedings-of-the-9th-international-natural
Repo
Framework

Simple, Fast Noise-Contrastive Estimation for Large RNN Vocabularies


Title	Simple, Fast Noise-Contrastive Estimation for Large RNN Vocabularies
Authors	Barret Zoph, Ashish Vaswani, Jonathan May, Kevin Knight
Abstract
Tasks	Language Modelling, Machine Translation, Speech Recognition, Spelling Correction
Published	2016-06-01
URL	https://www.aclweb.org/anthology/N16-1145/
PDF	https://www.aclweb.org/anthology/N16-1145
PWC	https://paperswithcode.com/paper/simple-fast-noise-contrastive-estimation-for
Repo
Framework

Taking the best from the Crowd:Learning Question Passage Classification from Noisy Data


Title	Taking the best from the Crowd:Learning Question Passage Classification from Noisy Data
Authors	Azad Abad, Aless Moschitti, ro
Abstract
Tasks
Published	2016-08-01
URL	https://www.aclweb.org/anthology/S16-2018/
PDF	https://www.aclweb.org/anthology/S16-2018
PWC	https://paperswithcode.com/paper/taking-the-best-from-the-crowdlearning
Repo
Framework

Detecting Stance in Tweets And Analyzing its Interaction with Sentiment


Title	Detecting Stance in Tweets And Analyzing its Interaction with Sentiment
Authors	Parinaz Sobhani, Saif Mohammad, Svetlana Kiritchenko
Abstract
Tasks	Information Retrieval, Natural Language Inference, Sentiment Analysis, Stance Detection, Text Summarization
Published	2016-08-01
URL	https://www.aclweb.org/anthology/S16-2021/
PDF	https://www.aclweb.org/anthology/S16-2021
PWC	https://paperswithcode.com/paper/detecting-stance-in-tweets-and-analyzing-its
Repo
Framework

Generating English from Abstract Meaning Representations


Title	Generating English from Abstract Meaning Representations
Authors	Nima Pourdamghani, Kevin Knight, Ulf Hermjakob
Abstract
Tasks	Machine Translation, Text Generation
Published	2016-09-01
URL	https://www.aclweb.org/anthology/W16-6603/
PDF	https://www.aclweb.org/anthology/W16-6603
PWC	https://paperswithcode.com/paper/generating-english-from-abstract-meaning
Repo
Framework

Discourse-Driven Narrative Generation With Bipartite Planning


Title	Discourse-Driven Narrative Generation With Bipartite Planning
Authors	David Winer, R. Michael Young
Abstract
Tasks	Text Generation
Published	2016-09-01
URL	https://www.aclweb.org/anthology/W16-6602/
PDF	https://www.aclweb.org/anthology/W16-6602
PWC	https://paperswithcode.com/paper/discourse-driven-narrative-generation-with
Repo
Framework

Evaluative Pattern Extraction for Automated Text Generation


Title	Evaluative Pattern Extraction for Automated Text Generation
Authors	Chia-Chen Lee, Shu-Kai Hsieh
Abstract
Tasks	Sentiment Analysis, Text Generation
Published	2016-09-01
URL	https://www.aclweb.org/anthology/W16-6617/
PDF	https://www.aclweb.org/anthology/W16-6617
PWC	https://paperswithcode.com/paper/evaluative-pattern-extraction-for-automated
Repo
Framework