Paper Group NANR 24
Cross-lingual and Supervised Models for Morphosyntactic Annotation: a Comparison on Romanian. The Syntax of the Chinese Excessive Resultative Construction. Combining Multiple Classifiers Using Global Ranking for ReachOut.com Post Triage. VENSESEVAL at Semeval-2016 Task 2 iSTS - with a full-fledged rule-based approach. Metrical Annotation of a Large …
Cross-lingual and Supervised Models for Morphosyntactic Annotation: a Comparison on Romanian
| Title | Cross-lingual and Supervised Models for Morphosyntactic Annotation: a Comparison on Romanian |
| Authors | Lauriane Aufrant, Guillaume Wisniewski, Fran{\c{c}}ois Yvon |
| Abstract | Because of the small size of Romanian corpora, the performance of a PoS tagger or a dependency parser trained with the standard supervised methods fall far short from the performance achieved in most languages. That is why, we apply state-of-the-art methods for cross-lingual transfer on Romanian tagging and parsing, from English and several Romance languages. We compare the performance with monolingual systems trained with sets of different sizes and establish that training on a few sentences in target language yields better results than transferring from large datasets in other languages. |
| Tasks | Cross-Lingual Transfer |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1241/ |
| https://www.aclweb.org/anthology/L16-1241 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-and-supervised-models-for |
| Repo | |
| Framework | |
The Syntax of the Chinese Excessive Resultative Construction
| Title | The Syntax of the Chinese Excessive Resultative Construction |
| Authors | Hongyong Liu |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-1007/ |
| https://www.aclweb.org/anthology/Y16-1007 | |
| PWC | https://paperswithcode.com/paper/the-syntax-of-the-chinese-excessive |
| Repo | |
| Framework | |
Combining Multiple Classifiers Using Global Ranking for ReachOut.com Post Triage
| Title | Combining Multiple Classifiers Using Global Ranking for ReachOut.com Post Triage |
| Authors | Chen-Kai Wang, Hong-Jie Dai, Chih-Wei Chen, Jitendra Jonnagaddala, Nai-Wen Chang |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0323/ |
| https://www.aclweb.org/anthology/W16-0323 | |
| PWC | https://paperswithcode.com/paper/combining-multiple-classifiers-using-global |
| Repo | |
| Framework | |
VENSESEVAL at Semeval-2016 Task 2 iSTS - with a full-fledged rule-based approach
| Title | VENSESEVAL at Semeval-2016 Task 2 iSTS - with a full-fledged rule-based approach |
| Authors | Rodolfo Delmonte |
| Abstract | |
| Tasks | Coreference Resolution, Natural Language Inference, Semantic Composition, Semantic Textual Similarity |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1123/ |
| https://www.aclweb.org/anthology/S16-1123 | |
| PWC | https://paperswithcode.com/paper/venseseval-at-semeval-2016-task-2-ists-with-a |
| Repo | |
| Framework | |
Metrical Annotation of a Large Corpus of Spanish Sonnets: Representation, Scansion and Evaluation
| Title | Metrical Annotation of a Large Corpus of Spanish Sonnets: Representation, Scansion and Evaluation |
| Authors | Borja Navarro, Mar{'\i}a Ribes Lafoz, Noelia S{'a}nchez |
| Abstract | In order to analyze metrical and semantics aspects of poetry in Spanish with computational techniques, we have developed a large corpus annotated with metrical information. In this paper we will present and discuss the development of this corpus: the formal representation of metrical patterns, the semi-automatic annotation process based on a new automatic scansion system, the main annotation problems, and the evaluation, in which an inter-annotator agreement of 96{%} has been obtained. The corpus is open and available. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1691/ |
| https://www.aclweb.org/anthology/L16-1691 | |
| PWC | https://paperswithcode.com/paper/metrical-annotation-of-a-large-corpus-of |
| Repo | |
| Framework | |
The Synaesthetic and Metaphorical Uses of 味 wei `taste’ in Chinese Buddhist Suttas
| Title | The Synaesthetic and Metaphorical Uses of 味 wei `taste’ in Chinese Buddhist Suttas | |
| Authors | Jiajuan Xiong, Chu-Ren Huang |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-3021/ |
| https://www.aclweb.org/anthology/Y16-3021 | |
| PWC | https://paperswithcode.com/paper/the-synaesthetic-and-metaphorical-uses-of-a3 |
| Repo | |
| Framework | |
Challenges and Solutions for Latin Named Entity Recognition
| Title | Challenges and Solutions for Latin Named Entity Recognition |
| Authors | Alex Erdmann, er, Christopher Brown, Brian Joseph, Mark Janse, Petra Ajaka, Micha Elsner, Marie-Catherine de Marneffe |
| Abstract | Although spanning thousands of years and genres as diverse as liturgy, historiography, lyric and other forms of prose and poetry, the body of Latin texts is still relatively sparse compared to English. Data sparsity in Latin presents a number of challenges for traditional Named Entity Recognition techniques. Solving such challenges and enabling reliable Named Entity Recognition in Latin texts can facilitate many down-stream applications, from machine translation to digital historiography, enabling Classicists, historians, and archaeologists for instance, to track the relationships of historical persons, places, and groups on a large scale. This paper presents the first annotated corpus for evaluating Named Entity Recognition in Latin, as well as a fully supervised model that achieves over 90{%} F-score on a held-out test set, significantly outperforming a competitive baseline. We also present a novel active learning strategy that predicts how many and which sentences need to be annotated for named entities in order to attain a specified degree of accuracy when recognizing named entities automatically in a given text. This maximizes the productivity of annotators while simultaneously controlling quality. |
| Tasks | Active Learning, Domain Adaptation, Machine Translation, Named Entity Recognition |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4012/ |
| https://www.aclweb.org/anthology/W16-4012 | |
| PWC | https://paperswithcode.com/paper/challenges-and-solutions-for-latin-named |
| Repo | |
| Framework | |
All Mixed Up? Finding the Optimal Feature Set for General Readability Prediction and Its Application to English and Dutch
| Title | All Mixed Up? Finding the Optimal Feature Set for General Readability Prediction and Its Application to English and Dutch |
| Authors | Orph{'e}e De Clercq, V{'e}ronique Hoste |
| Abstract | |
| Tasks | |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/J16-3004/ |
| https://www.aclweb.org/anthology/J16-3004 | |
| PWC | https://paperswithcode.com/paper/all-mixed-up-finding-the-optimal-feature-set |
| Repo | |
| Framework | |
A General Framework for the Annotation of Causality Based on FrameNet
| Title | A General Framework for the Annotation of Causality Based on FrameNet |
| Authors | Laure Vieu, Philippe Muller, C, Marie ito, Marianne Djemaa |
| Abstract | We present here a general set of semantic frames to annotate causal expressions, with a rich lexicon in French and an annotated corpus of about 5000 instances of causal lexical items with their corresponding semantic frames. The aim of our project is to have both the largest possible coverage of causal phenomena in French, across all parts of speech, and have it linked to a general semantic framework such as FN, to benefit in particular from the relations between other semantic frames, e.g., temporal ones or intentional ones, and the underlying upper lexical ontology that enable some forms of reasoning. This is part of the larger ASFALDA French FrameNet project, which focuses on a few different notional domains which are interesting in their own right (Djemma et al., 2016), including cognitive positions and communication frames. In the process of building the French lexicon and preparing the annotation of the corpus, we had to remodel some of the frames proposed in FN based on English data, with hopefully more precise frame definitions to facilitate human annotation. This includes semantic clarifications of frames and frame elements, redundancy elimination, and added coverage. The result is arguably a significant improvement of the treatment of causality in FN itself. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1603/ |
| https://www.aclweb.org/anthology/L16-1603 | |
| PWC | https://paperswithcode.com/paper/a-general-framework-for-the-annotation-of |
| Repo | |
| Framework | |
Equivalences between Ranked and Unranked Weighted Tree Automata via Binarization
| Title | Equivalences between Ranked and Unranked Weighted Tree Automata via Binarization |
| Authors | Toni Dietze |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2401/ |
| https://www.aclweb.org/anthology/W16-2401 | |
| PWC | https://paperswithcode.com/paper/equivalences-between-ranked-and-unranked |
| Repo | |
| Framework | |
DTSim at SemEval-2016 Task 2: Interpreting Similarity of Texts Based on Automated Chunking, Chunk Alignment and Semantic Relation Prediction
| Title | DTSim at SemEval-2016 Task 2: Interpreting Similarity of Texts Based on Automated Chunking, Chunk Alignment and Semantic Relation Prediction |
| Authors | Rajendra Banjade, Nabin Maharjan, Nobal Bikram Niraula, Vasile Rus |
| Abstract | |
| Tasks | Chunking, Semantic Textual Similarity |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/S16-1125/ |
| https://www.aclweb.org/anthology/S16-1125 | |
| PWC | https://paperswithcode.com/paper/dtsim-at-semeval-2016-task-2-interpreting |
| Repo | |
| Framework | |
The BAS Speech Data Repository
| Title | The BAS Speech Data Repository |
| Authors | Uwe Reichel, Florian Schiel, Thomas Kisler, Christoph Draxler, Nina P{"o}rner |
| Abstract | The BAS CLARIN speech data repository is introduced. At the current state it comprises 31 pre-dominantly German corpora of spoken language. It is compliant to the CLARIN-D as well as the OLAC requirements. This enables its embedding into several infrastructures. We give an overview over its structure, its implementation as well as the corpora it contains. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1126/ |
| https://www.aclweb.org/anthology/L16-1126 | |
| PWC | https://paperswithcode.com/paper/the-bas-speech-data-repository |
| Repo | |
| Framework | |
Adaptive Smoothed Online Multi-Task Learning
| Title | Adaptive Smoothed Online Multi-Task Learning |
| Authors | Keerthiram Murugesan, Hanxiao Liu, Jaime Carbonell, Yiming Yang |
| Abstract | This paper addresses the challenge of jointly learning both the per-task model parameters and the inter-task relationships in a multi-task online learning setting. The proposed algorithm features probabilistic interpretation, efficient updating rules and flexible modulation on whether learners focus on their specific task or on jointly address all tasks. The paper also proves a sub-linear regret bound as compared to the best linear predictor in hindsight. Experiments over three multi-task learning benchmark datasets show advantageous performance of the proposed approach over several state-of-the-art online multi-task learning baselines. |
| Tasks | Multi-Task Learning |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6434-adaptive-smoothed-online-multi-task-learning |
| http://papers.nips.cc/paper/6434-adaptive-smoothed-online-multi-task-learning.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-smoothed-online-multi-task-learning |
| Repo | |
| Framework | |
Predicting the Spelling Difficulty of Words for Language Learners
| Title | Predicting the Spelling Difficulty of Words for Language Learners |
| Authors | Lisa Beinborn, Torsten Zesch, Iryna Gurevych |
| Abstract | |
| Tasks | Cross-Lingual Transfer |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0508/ |
| https://www.aclweb.org/anthology/W16-0508 | |
| PWC | https://paperswithcode.com/paper/predicting-the-spelling-difficulty-of-words |
| Repo | |
| Framework | |
The IFCASL Corpus of French and German Non-native and Native Read Speech
| Title | The IFCASL Corpus of French and German Non-native and Native Read Speech |
| Authors | Juergen Trouvain, Anne Bonneau, Vincent Colotte, Camille Fauth, Dominique Fohr, Denis Jouvet, Jeanin J{"u}gler, Yves Laprie, Odile Mella, Bernd M{"o}bius, Frank Zimmerer |
| Abstract | The IFCASL corpus is a French-German bilingual phonetic learner corpus designed, recorded and annotated in a project on individualized feedback in computer-assisted spoken language learning. The motivation for setting up this corpus was that there is no phonetically annotated and segmented corpus for this language pair of comparable of size and coverage. In contrast to most learner corpora, the IFCASL corpus incorporate data for a language pair in both directions, i.e. in our case French learners of German, and German learners of French. In addition, the corpus is complemented by two sub-corpora of native speech by the same speakers. The corpus provides spoken data by about 100 speakers with comparable productions, annotated and segmented on the word and the phone level, with more than 50{%} manually corrected data. The paper reports on inter-annotator agreement and the optimization of the acoustic models for forced speech-text alignment in exercises for computer-assisted pronunciation training. Example studies based on the corpus data with a phonetic focus include topics such as the realization of /h/ and glottal stop, final devoicing of obstruents, vowel quantity and quality, pitch range, and tempo. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1212/ |
| https://www.aclweb.org/anthology/L16-1212 | |
| PWC | https://paperswithcode.com/paper/the-ifcasl-corpus-of-french-and-german-non |
| Repo | |
| Framework | |
