May 5, 2019

1302 words 7 mins read

Paper Group NANR 72

Paper Group NANR 72

Axolotl: a Web Accessible Parallel Corpus for Spanish-Nahuatl. A Corpus of Native, Non-native and Translated Texts. UWB at SemEval-2016 Task 1: Semantic Textual Similarity using Lexical, Syntactic, and Semantic Information. Mapping Ontologies Using Ontologies: Cross-lingual Semantic Role Information Transfer. Lexical and Syntactic cues to identify …

Axolotl: a Web Accessible Parallel Corpus for Spanish-Nahuatl

Title Axolotl: a Web Accessible Parallel Corpus for Spanish-Nahuatl
Authors Ximena Gutierrez-Vasques, Gerardo Sierra, Isaac Hern Pompa, ez
Abstract This paper describes the project called Axolotl which comprises a Spanish-Nahuatl parallel corpus and its search interface. Spanish and Nahuatl are distant languages spoken in the same country. Due to the scarcity of digital resources, we describe the several problems that arose when compiling this corpus: most of our sources were non-digital books, we faced errors when digitizing the sources and there were difficulties in the sentence alignment process, just to mention some. The documents of the parallel corpus are not homogeneous, they were extracted from different sources, there is dialectal, diachronical, and orthographical variation. Additionally, we present a web search interface that allows to make queries through the whole parallel corpus, the system is capable to retrieve the parallel fragments that contain a word or phrase searched by a user in any of the languages. To our knowledge, this is the first Spanish-Nahuatl public available digital parallel corpus. We think that this resource can be useful to develop language technologies and linguistic studies for this language pair.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1666/
PDF https://www.aclweb.org/anthology/L16-1666
PWC https://paperswithcode.com/paper/axolotl-a-web-accessible-parallel-corpus-for
Repo
Framework

A Corpus of Native, Non-native and Translated Texts

Title A Corpus of Native, Non-native and Translated Texts
Authors Sergiu Nisioi, Ella Rabinovich, Liviu P. Dinu, Shuly Wintner
Abstract We describe a monolingual English corpus of original and (human) translated texts, with an accurate annotation of speaker properties, including the original language of the utterances and the speaker{'}s country of origin. We thus obtain three sub-corpora of texts reflecting native English, non-native English, and English translated from a variety of European languages. This dataset will facilitate the investigation of similarities and differences between these kinds of sub-languages. Moreover, it will facilitate a unified comparative study of translations and language produced by (highly fluent) non-native speakers, two closely-related phenomena that have only been studied in isolation so far.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1664/
PDF https://www.aclweb.org/anthology/L16-1664
PWC https://paperswithcode.com/paper/a-corpus-of-native-non-native-and-translated
Repo
Framework

UWB at SemEval-2016 Task 1: Semantic Textual Similarity using Lexical, Syntactic, and Semantic Information

Title UWB at SemEval-2016 Task 1: Semantic Textual Similarity using Lexical, Syntactic, and Semantic Information
Authors Tom{'a}{\v{s}} Brychc{'\i}n, Luk{'a}{\v{s}} Svoboda
Abstract
Tasks Semantic Textual Similarity
Published 2016-06-01
URL https://www.aclweb.org/anthology/S16-1089/
PDF https://www.aclweb.org/anthology/S16-1089
PWC https://paperswithcode.com/paper/uwb-at-semeval-2016-task-1-semantic-textual
Repo
Framework

Mapping Ontologies Using Ontologies: Cross-lingual Semantic Role Information Transfer

Title Mapping Ontologies Using Ontologies: Cross-lingual Semantic Role Information Transfer
Authors Bal{'a}zs Indig, M{'a}rton Mih{'a}ltz, Andr{'a}s Simonyi
Abstract This paper presents the process of enriching the verb frame database of a Hungarian natural language parser to enable the assignment of semantic roles. We accomplished this by linking the parser{'}s verb frame database to existing linguistic resources such as VerbNet and WordNet, and automatically transferring back semantic knowledge. We developed OWL ontologies that map the various constraint description formalisms of the linked resources and employed a logical reasoning device to facilitate the linking procedure. We present results and discuss the challenges and pitfalls that arose from this undertaking.
Tasks
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1384/
PDF https://www.aclweb.org/anthology/L16-1384
PWC https://paperswithcode.com/paper/mapping-ontologies-using-ontologies-cross
Repo
Framework

Lexical and Syntactic cues to identify Reference Scope of Citance

Title Lexical and Syntactic cues to identify Reference Scope of Citance
Authors Peeyush Aggarwal, Richa Sharma
Abstract
Tasks Document Summarization
Published 2016-06-01
URL https://www.aclweb.org/anthology/W16-1512/
PDF https://www.aclweb.org/anthology/W16-1512
PWC https://paperswithcode.com/paper/lexical-and-syntactic-cues-to-identify
Repo
Framework

Making Sense of Massive Amounts of Scientific Publications: the Scientific Knowledge Miner Project

Title Making Sense of Massive Amounts of Scientific Publications: the Scientific Knowledge Miner Project
Authors Francesco Ronzano, Ana Freire, Diego Saez-Trumper, Horacio Saggion
Abstract
Tasks Document Summarization, Information Retrieval, Opinion Mining, Recommendation Systems, Text Summarization
Published 2016-06-01
URL https://www.aclweb.org/anthology/W16-1505/
PDF https://www.aclweb.org/anthology/W16-1505
PWC https://paperswithcode.com/paper/making-sense-of-massive-amounts-of-scientific
Repo
Framework

Extending Monolingual Semantic Textual Similarity Task to Multiple Cross-lingual Settings

Title Extending Monolingual Semantic Textual Similarity Task to Multiple Cross-lingual Settings
Authors Yoshihiko Hayashi, Wentao Luo
Abstract This paper describes our independent effort for extending the monolingual semantic textual similarity (STS) task setting to multiple cross-lingual settings involving English, Japanese, and Chinese. So far, we have adopted a {``}monolingual similarity after translation{''} strategy to predict the semantic similarity between a pair of sentences in different languages. With this strategy, a monolingual similarity method is applied after having (one of) the target sentences translated into a pivot language. Therefore, this paper specifically details the required and developed resources to implement this framework, while presenting our current results for English-Japanese-Chinese cross-lingual STS tasks that may exemplify the validity of the framework. |
Tasks Semantic Similarity, Semantic Textual Similarity
Published 2016-05-01
URL https://www.aclweb.org/anthology/L16-1196/
PDF https://www.aclweb.org/anthology/L16-1196
PWC https://paperswithcode.com/paper/extending-monolingual-semantic-textual
Repo
Framework

UWB at SemEval-2016 Task 7: Novel Method for Automatic Sentiment Intensity Determination

Title UWB at SemEval-2016 Task 7: Novel Method for Automatic Sentiment Intensity Determination
Authors Ladislav Lenc, Pavel Kr{'a}l, V{'a}clav Rajtmajer
Abstract
Tasks Opinion Mining, Sentiment Analysis, Text Categorization, Word Embeddings
Published 2016-06-01
URL https://www.aclweb.org/anthology/S16-1078/
PDF https://www.aclweb.org/anthology/S16-1078
PWC https://paperswithcode.com/paper/uwb-at-semeval-2016-task-7-novel-method-for
Repo
Framework

Stating the Obvious: Extracting Visual Common Sense Knowledge

Title Stating the Obvious: Extracting Visual Common Sense Knowledge
Authors Mark Yatskar, Vicente Ordonez, Ali Farhadi
Abstract
Tasks Common Sense Reasoning, Object Detection
Published 2016-06-01
URL https://www.aclweb.org/anthology/N16-1023/
PDF https://www.aclweb.org/anthology/N16-1023
PWC https://paperswithcode.com/paper/stating-the-obvious-extracting-visual-common
Repo
Framework

Enriching a Valency Lexicon by Deverbative Nouns

Title Enriching a Valency Lexicon by Deverbative Nouns
Authors Eva Fu{\v{c}}{'\i}kov{'a}, Jan Haji{\v{c}}, Zde{\v{n}}ka Ure{\v{s}}ov{'a}
Abstract We present an attempt to automatically identify Czech deverbative nouns using several methods that use large corpora as well as existing lexical resources. The motivation for the task is to extend a verbal valency (i.e., predicate-argument) lexicon by adding nouns that share the valency properties with the base verb, assuming their properties can be derived (even if not trivially) from the underlying verb by deterministic grammatical rules. At the same time, even in inflective languages, not all deverbatives are simply created from their underlying base verb by regular lexical derivation processes. We have thus developed hybrid techniques that use both large parallel corpora and several standard lexical resources. Thanks to the use of parallel corpora, the resulting sets contain also synonyms, which the lexical derivation rules cannot get. For evaluation, we have manually created a small, 100-verb gold data since no such dataset was initially available for Czech.
Tasks
Published 2016-12-01
URL https://www.aclweb.org/anthology/W16-3810/
PDF https://www.aclweb.org/anthology/W16-3810
PWC https://paperswithcode.com/paper/enriching-a-valency-lexicon-by-deverbative
Repo
Framework

Character based String Kernels for Bio-Entity Relation Detection

Title Character based String Kernels for Bio-Entity Relation Detection
Authors Ritambhara Singh, Yanjun Qi
Abstract
Tasks Decision Making, Question Answering, Relation Extraction
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2908/
PDF https://www.aclweb.org/anthology/W16-2908
PWC https://paperswithcode.com/paper/character-based-string-kernels-for-bio-entity
Repo
Framework

``What Is Your Evidence?’’ A Study of Controversial Topics on Social Media

Title ``What Is Your Evidence?’’ A Study of Controversial Topics on Social Media |
Authors Aseel Addawood, Masooda Bashir
Abstract
Tasks Argument Mining, Opinion Mining, Sentiment Analysis
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-2801/
PDF https://www.aclweb.org/anthology/W16-2801
PWC https://paperswithcode.com/paper/what-is-your-evidence-a-study-of
Repo
Framework

Talking with ERICA, an autonomous android

Title Talking with ERICA, an autonomous android
Authors Koji Inoue, Pierrick Milhorat, Divesh Lala, Tianyu Zhao, Tatsuya Kawahara
Abstract
Tasks
Published 2016-09-01
URL https://www.aclweb.org/anthology/W16-3625/
PDF https://www.aclweb.org/anthology/W16-3625
PWC https://paperswithcode.com/paper/talking-with-erica-an-autonomous-android
Repo
Framework

Overview of the Bacteria Biotope Task at BioNLP Shared Task 2016

Title Overview of the Bacteria Biotope Task at BioNLP Shared Task 2016
Authors Louise Del{'e}ger, Robert Bossy, Estelle Chaix, Mouhamadou Ba, Arnaud Ferr{'e}, Philippe Bessi{`e}res, Claire N{'e}dellec
Abstract
Tasks
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-3002/
PDF https://www.aclweb.org/anthology/W16-3002
PWC https://paperswithcode.com/paper/overview-of-the-bacteria-biotope-task-at
Repo
Framework

Sparsifying Word Representations for Deep Unordered Sentence Modeling

Title Sparsifying Word Representations for Deep Unordered Sentence Modeling
Authors Prasanna Sattigeri, Jayaraman J. Thiagarajan
Abstract
Tasks Document Classification, Representation Learning, Sentence Embeddings, Word Embeddings
Published 2016-08-01
URL https://www.aclweb.org/anthology/W16-1624/
PDF https://www.aclweb.org/anthology/W16-1624
PWC https://paperswithcode.com/paper/sparsifying-word-representations-for-deep
Repo
Framework
comments powered by Disqus