Paper Group NANR 73
Supersense tagging with inter-annotator disagreement. Automatically Inferring Implicit Properties in Similes. Fast and Robust POS tagger for Arabic Tweets Using Agreement-based Bootstrapping. Part-of-speech Tagging of Code-Mixed Social Media Text. Using Word Embeddings for Improving Statistical Machine Translation of Phrasal Verbs. Inferring Morpho …
Supersense tagging with inter-annotator disagreement
| Title | Supersense tagging with inter-annotator disagreement |
| Authors | H{'e}ctor Mart{'\i}nez Alonso, Anders Johannsen, Barbara Plank |
| Abstract | |
| Tasks | |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1706/ |
| https://www.aclweb.org/anthology/W16-1706 | |
| PWC | https://paperswithcode.com/paper/supersense-tagging-with-inter-annotator |
| Repo | |
| Framework | |
Automatically Inferring Implicit Properties in Similes
| Title | Automatically Inferring Implicit Properties in Similes |
| Authors | Ashequl Qadir, Ellen Riloff, Marilyn A. Walker |
| Abstract | |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1146/ |
| https://www.aclweb.org/anthology/N16-1146 | |
| PWC | https://paperswithcode.com/paper/automatically-inferring-implicit-properties |
| Repo | |
| Framework | |
Fast and Robust POS tagger for Arabic Tweets Using Agreement-based Bootstrapping
| Title | Fast and Robust POS tagger for Arabic Tweets Using Agreement-based Bootstrapping |
| Authors | Fahad Albogamy, Allan Ramsay |
| Abstract | Part-of-Speech(POS) tagging is a key step in many NLP algorithms. However, tweets are difficult to POS tag because they are short, are not always written maintaining formal grammar and proper spelling, and abbreviations are often used to overcome their restricted lengths. Arabic tweets also show a further range of linguistic phenomena such as usage of different dialects, romanised Arabic and borrowing foreign words. In this paper, we present an evaluation and a detailed error analysis of state-of-the-art POS taggers for Arabic when applied to Arabic tweets. On the basis of this analysis, we combine normalisation and external knowledge to handle the domain noisiness and exploit bootstrapping to construct extra training data in order to improve POS tagging for Arabic tweets. Our results show significant improvements over the performance of a number of well-known taggers for Arabic. |
| Tasks | Part-Of-Speech Tagging |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1238/ |
| https://www.aclweb.org/anthology/L16-1238 | |
| PWC | https://paperswithcode.com/paper/fast-and-robust-pos-tagger-for-arabic-tweets |
| Repo | |
| Framework | |
Part-of-speech Tagging of Code-Mixed Social Media Text
| Title | Part-of-speech Tagging of Code-Mixed Social Media Text |
| Authors | Souvick Ghosh, Satanu Ghosh, Dipankar Das |
| Abstract | |
| Tasks | Language Identification, Part-Of-Speech Tagging |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-5811/ |
| https://www.aclweb.org/anthology/W16-5811 | |
| PWC | https://paperswithcode.com/paper/part-of-speech-tagging-of-code-mixed-social-1 |
| Repo | |
| Framework | |
Using Word Embeddings for Improving Statistical Machine Translation of Phrasal Verbs
| Title | Using Word Embeddings for Improving Statistical Machine Translation of Phrasal Verbs |
| Authors | Kostadin Cholakov, Valia Kordoni |
| Abstract | |
| Tasks | Machine Translation, Semantic Textual Similarity, Word Embeddings |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-1808/ |
| https://www.aclweb.org/anthology/W16-1808 | |
| PWC | https://paperswithcode.com/paper/using-word-embeddings-for-improving |
| Repo | |
| Framework | |
Inferring Morphotactics from Interlinear Glossed Text: Combining Clustering and Precision Grammars
| Title | Inferring Morphotactics from Interlinear Glossed Text: Combining Clustering and Precision Grammars |
| Authors | Olga Zamaraeva |
| Abstract | |
| Tasks | Morphological Analysis |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2021/ |
| https://www.aclweb.org/anthology/W16-2021 | |
| PWC | https://paperswithcode.com/paper/inferring-morphotactics-from-interlinear |
| Repo | |
| Framework | |
Comparing Translator Acceptability of TM and SMT Outputs
| Title | Comparing Translator Acceptability of TM and SMT Outputs |
| Authors | Joss Moorkens, Andy Way |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/W16-3404/ |
| https://www.aclweb.org/anthology/W16-3404 | |
| PWC | https://paperswithcode.com/paper/comparing-translator-acceptability-of-tm-and |
| Repo | |
| Framework | |
Stand-off Annotation of Web Content as a Legally Safer Alternative to Crawling for Distribution
| Title | Stand-off Annotation of Web Content as a Legally Safer Alternative to Crawling for Distribution |
| Authors | Mikel L. Forcada, Miquel Espl{`a}-Gomis, Juan Antonio P{'e}rez-Ortiz |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-01-01 |
| URL | https://www.aclweb.org/anthology/W16-3405/ |
| https://www.aclweb.org/anthology/W16-3405 | |
| PWC | https://paperswithcode.com/paper/stand-off-annotation-of-web-content-as-a |
| Repo | |
| Framework | |
User Embedding for Scholarly Microblog Recommendation
| Title | User Embedding for Scholarly Microblog Recommendation |
| Authors | Yang Yu, Xiaojun Wan, Xinjie Zhou |
| Abstract | |
| Tasks | Collaborative Ranking |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2073/ |
| https://www.aclweb.org/anthology/P16-2073 | |
| PWC | https://paperswithcode.com/paper/user-embedding-for-scholarly-microblog |
| Repo | |
| Framework | |
A Comparative Study of Minimally Supervised Morphological Segmentation
| Title | A Comparative Study of Minimally Supervised Morphological Segmentation |
| Authors | Teemu Ruokolainen, Oskar Kohonen, Kairit Sirts, Stig-Arne Gr{"o}nroos, Mikko Kurimo, Sami Virpioja |
| Abstract | |
| Tasks | Boundary Detection |
| Published | 2016-03-01 |
| URL | https://www.aclweb.org/anthology/J16-1003/ |
| https://www.aclweb.org/anthology/J16-1003 | |
| PWC | https://paperswithcode.com/paper/a-comparative-study-of-minimally-supervised |
| Repo | |
| Framework | |
Fast and highly parallelizable phrase table for statistical machine translation
| Title | Fast and highly parallelizable phrase table for statistical machine translation |
| Authors | Nikolay Bogoychev, Hieu Hoang |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2211/ |
| https://www.aclweb.org/anthology/W16-2211 | |
| PWC | https://paperswithcode.com/paper/fast-and-highly-parallelizable-phrase-table |
| Repo | |
| Framework | |
ParFDA for Instance Selection for Statistical Machine Translation
| Title | ParFDA for Instance Selection for Statistical Machine Translation |
| Authors | Ergun Bi{\c{c}}ici |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2306/ |
| https://www.aclweb.org/anthology/W16-2306 | |
| PWC | https://paperswithcode.com/paper/parfda-for-instance-selection-for-statistical-1 |
| Repo | |
| Framework | |
A Wizard-of-Oz Study on A Non-Task-Oriented Dialog Systems That Reacts to User Engagement
| Title | A Wizard-of-Oz Study on A Non-Task-Oriented Dialog Systems That Reacts to User Engagement |
| Authors | Zhou Yu, Leah Nicolich-Henkin, Alan W Black, Alex Rudnicky, er |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2016-09-01 |
| URL | https://www.aclweb.org/anthology/W16-3608/ |
| https://www.aclweb.org/anthology/W16-3608 | |
| PWC | https://paperswithcode.com/paper/a-wizard-of-oz-study-on-a-non-task-oriented |
| Repo | |
| Framework | |
What does this Emoji Mean? A Vector Space Skip-Gram Model for Twitter Emojis
| Title | What does this Emoji Mean? A Vector Space Skip-Gram Model for Twitter Emojis |
| Authors | Francesco Barbieri, Francesco Ronzano, Horacio Saggion |
| Abstract | Emojis allow us to describe objects, situations and even feelings with small images, providing a visual and quick way to communicate. In this paper, we analyse emojis used in Twitter with distributional semantic models. We retrieve 10 millions tweets posted by USA users, and we build several skip gram word embedding models by mapping in the same vectorial space both words and emojis. We test our models with semantic similarity experiments, comparing the output of our models with human assessment. We also carry out an exhaustive qualitative evaluation, showing interesting results. |
| Tasks | Semantic Similarity, Semantic Textual Similarity |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1626/ |
| https://www.aclweb.org/anthology/L16-1626 | |
| PWC | https://paperswithcode.com/paper/what-does-this-emoji-mean-a-vector-space-skip |
| Repo | |
| Framework | |
SPLIT: Smart Preprocessing (Quasi) Language Independent Tool
| Title | SPLIT: Smart Preprocessing (Quasi) Language Independent Tool |
| Authors | Mohamed Al-Badrashiny, Arfath Pasha, Mona Diab, Nizar Habash, Owen Rambow, Wael Salloum, Esk, Ramy er |
| Abstract | Text preprocessing is an important and necessary task for all NLP applications. A simple variation in any preprocessing step may drastically affect the final results. Moreover replicability and comparability, as much as feasible, is one of the goals of our scientific enterprise, thus building systems that can ensure the consistency in our various pipelines would contribute significantly to our goals. The problem has become quite pronounced with the abundance of NLP tools becoming more and more available yet with different levels of specifications. In this paper, we present a dynamic unified preprocessing framework and tool, SPLIT, that is highly configurable based on user requirements which serves as a preprocessing tool for several tools at once. SPLIT aims to standardize the implementations of the most important preprocessing steps by allowing for a unified API that could be exchanged across different researchers to ensure complete transparency in replication. The user is able to select the required preprocessing tasks among a long list of preprocessing steps. The user is also able to specify the order of execution which in turn affects the final preprocessing output. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1640/ |
| https://www.aclweb.org/anthology/L16-1640 | |
| PWC | https://paperswithcode.com/paper/split-smart-preprocessing-quasi-language |
| Repo | |
| Framework | |
