Paper Group NANR 171
Variation Autoencoder Based Network Representation Learning for Classification. Enabling Transitivity for Lexical Inference on Chinese Verbs Using Probabilistic Soft Logic. Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison. Cross-lingual tagger evaluation without test data. Annotating errors in student texts: First …
Variation Autoencoder Based Network Representation Learning for Classification
| Title | Variation Autoencoder Based Network Representation Learning for Classification |
| Authors | Hang Li, Haozheng Wang, Zhenglu Yang, Masato Odagaki |
| Abstract | |
| Tasks | Document Classification, Information Retrieval, Recommendation Systems, Representation Learning |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3010/ |
| https://www.aclweb.org/anthology/P17-3010 | |
| PWC | https://paperswithcode.com/paper/variation-autoencoder-based-network |
| Repo | |
| Framework | |
Enabling Transitivity for Lexical Inference on Chinese Verbs Using Probabilistic Soft Logic
| Title | Enabling Transitivity for Lexical Inference on Chinese Verbs Using Probabilistic Soft Logic |
| Authors | Wei-Chung Wang, Lun-Wei Ku |
| Abstract | To learn more knowledge, enabling transitivity is a vital step for lexical inference. However, most of the lexical inference models with good performance are for nouns or noun phrases, which cannot be directly applied to the inference on events or states. In this paper, we construct the largest Chinese verb lexical inference dataset containing 18,029 verb pairs, where for each pair one of four inference relations are annotated. We further build a probabilistic soft logic (PSL) model to infer verb lexicons using the logic language. With PSL, we easily enable transitivity in two layers, the observed layer and the feature layer, which are included in the knowledge base. We further discuss the effect of transitives within and between these layers. Results show the performance of the proposed PSL model can be improved at least 3.5{%} (relative) when the transitivity is enabled. Furthermore, experiments show that enabling transitivity in the observed layer benefits the most. |
| Tasks | Natural Language Inference, Open-Domain Question Answering, Question Answering, Text Generation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1012/ |
| https://www.aclweb.org/anthology/I17-1012 | |
| PWC | https://paperswithcode.com/paper/enabling-transitivity-for-lexical-inference |
| Repo | |
| Framework | |
Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison
| Title | Word Sense Disambiguation: A Unified Evaluation Framework and Empirical Comparison |
| Authors | Aless Raganato, ro, Jose Camacho-Collados, Roberto Navigli |
| Abstract | Word Sense Disambiguation is a long-standing task in Natural Language Processing, lying at the core of human language understanding. However, the evaluation of automatic systems has been problematic, mainly due to the lack of a reliable evaluation framework. In this paper we develop a unified evaluation framework and analyze the performance of various Word Sense Disambiguation systems in a fair setup. The results show that supervised systems clearly outperform knowledge-based models. Among the supervised systems, a linear classifier trained on conventional local features still proves to be a hard baseline to beat. Nonetheless, recent approaches exploiting neural networks on unlabeled corpora achieve promising results, surpassing this hard baseline in most test sets. |
| Tasks | Word Sense Disambiguation |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1010/ |
| https://www.aclweb.org/anthology/E17-1010 | |
| PWC | https://paperswithcode.com/paper/word-sense-disambiguation-a-unified |
| Repo | |
| Framework | |
Cross-lingual tagger evaluation without test data
| Title | Cross-lingual tagger evaluation without test data |
| Authors | {\v{Z}}eljko Agi{'c}, Barbara Plank, Anders S{\o}gaard |
| Abstract | We address the challenge of cross-lingual POS tagger evaluation in absence of manually annotated test data. We put forth and evaluate two dictionary-based metrics. On the tasks of accuracy prediction and system ranking, we reveal that these metrics are reliable enough to approximate test set-based evaluation, and at the same time lean enough to support assessment for truly low-resource languages. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2040/ |
| https://www.aclweb.org/anthology/E17-2040 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-tagger-evaluation-without-test |
| Repo | |
| Framework | |
Annotating errors in student texts: First experiences and experiments
| Title | Annotating errors in student texts: First experiences and experiments |
| Authors | Sara Stymne, Eva Pettersson, Be{'a}ta Megyesi, Anne Palm{'e}r |
| Abstract | |
| Tasks | Language Acquisition, Spelling Correction |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0306/ |
| https://www.aclweb.org/anthology/W17-0306 | |
| PWC | https://paperswithcode.com/paper/annotating-errors-in-student-texts-first |
| Repo | |
| Framework | |
OCR and post-correction of historical Finnish texts
| Title | OCR and post-correction of historical Finnish texts |
| Authors | Senka Drobac, Pekka Kauppinen, Krister Lind{'e}n |
| Abstract | |
| Tasks | Optical Character Recognition, Spelling Correction |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0209/ |
| https://www.aclweb.org/anthology/W17-0209 | |
| PWC | https://paperswithcode.com/paper/ocr-and-post-correction-of-historical-finnish |
| Repo | |
| Framework | |
Using Twitter Language to Predict the Real Estate Market
| Title | Using Twitter Language to Predict the Real Estate Market |
| Authors | Mohammadzaman Zamani, H. Andrew Schwartz |
| Abstract | We explore whether social media can provide a window into community real estate -foreclosure rates and price changes- beyond that of traditional economic and demographic variables. We find language use in Twitter not only predicts real estate outcomes as well as traditional variables across counties, but that including Twitter language in traditional models leads to a significant improvement (e.g. from Pearson r = :50 to r = :59 for price changes). We overcome the challenge of the relative sparsity and noise in Twitter language variables by showing that training on the residual error of the traditional models leads to more accurate overall assessments. Finally, we discover that it is Twitter language related to business (e.g. {}company{'}, {}marketing{'}) and technology (e.g. {}technology{'}, {}internet{'}), among others, that yield predictive power over economics. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2005/ |
| https://www.aclweb.org/anthology/E17-2005 | |
| PWC | https://paperswithcode.com/paper/using-twitter-language-to-predict-the-real |
| Repo | |
| Framework | |
The Content Types Dataset: a New Resource to Explore Semantic and Functional Characteristics of Texts
| Title | The Content Types Dataset: a New Resource to Explore Semantic and Functional Characteristics of Texts |
| Authors | Rachele Sprugnoli, Tommaso Caselli, Sara Tonelli, Giovanni Moretti |
| Abstract | This paper presents a new resource, called Content Types Dataset, to promote the analysis of texts as a composition of units with specific semantic and functional roles. By developing this dataset, we also introduce a new NLP task for the automatic classification of Content Types. The annotation scheme and the dataset are described together with two sets of classification experiments. |
| Tasks | Sentiment Analysis |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2042/ |
| https://www.aclweb.org/anthology/E17-2042 | |
| PWC | https://paperswithcode.com/paper/the-content-types-dataset-a-new-resource-to |
| Repo | |
| Framework | |
Using Gaze to Predict Text Readability
| Title | Using Gaze to Predict Text Readability |
| Authors | Ana Valeria Gonz{'a}lez-Gardu{~n}o, Anders S{\o}gaard |
| Abstract | We show that text readability prediction improves significantly from hard parameter sharing with models predicting first pass duration, total fixation duration and regression duration. Specifically, we induce multi-task Multilayer Perceptrons and Logistic Regression models over sentence representations that capture various aggregate statistics, from two different text readability corpora for English, as well as the Dundee eye-tracking corpus. Our approach leads to significant improvements over Single task learning and over previous systems. In addition, our improvements are consistent across train sample sizes, making our approach especially applicable to small datasets. |
| Tasks | Eye Tracking, Machine Translation, Multi-Task Learning, Text Generation, Text Simplification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5050/ |
| https://www.aclweb.org/anthology/W17-5050 | |
| PWC | https://paperswithcode.com/paper/using-gaze-to-predict-text-readability |
| Repo | |
| Framework | |
Projection of Argumentative Corpora from Source to Target Languages
| Title | Projection of Argumentative Corpora from Source to Target Languages |
| Authors | Ahmet Aker, Huangpan Zhang |
| Abstract | Argumentative corpora are costly to create and are available in only few languages with English dominating the area. In this paper we release the first publicly available Mandarin argumentative corpus. The corpus is created by exploiting the idea of comparable corpora from Statistical Machine Translation. We use existing corpora in English and manually map the claims and premises to comparable corpora in Mandarin. We also implement a simple solution to automate this approach with the view of creating argumentative corpora in other less-resourced languages. In this way we introduce a new task of multi-lingual argument mapping that can be evaluated using our English-Mandarin argumentative corpus. The preliminary results of our automatic argument mapper mirror the simplicity of our approach, but provide a baseline for further improvements. |
| Tasks | Argument Mining, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5108/ |
| https://www.aclweb.org/anthology/W17-5108 | |
| PWC | https://paperswithcode.com/paper/projection-of-argumentative-corpora-from |
| Repo | |
| Framework | |
TWINE: A real-time system for TWeet analysis via INformation Extraction
| Title | TWINE: A real-time system for TWeet analysis via INformation Extraction |
| Authors | Debora Nozza, Fausto Ristagno, Matteo Palmonari, Elisabetta Fersini, Manch, Pikakshi a, Enza Messina |
| Abstract | In the recent years, the amount of user generated contents shared on the Web has significantly increased, especially in social media environment, e.g. Twitter, Facebook, Google+. This large quantity of data has generated the need of reactive and sophisticated systems for capturing and understanding the underlying information enclosed in them. In this paper we present TWINE, a real-time system for the big data analysis and exploration of information extracted from Twitter streams. The proposed system based on a Named Entity Recognition and Linking pipeline and a multi-dimensional spatial geo-localization is managed by a scalable and flexible architecture for an interactive visualization of micropost streams insights. The demo is available at \url{http://twine-mind.cloudapp.net/streaming}. |
| Tasks | Named Entity Recognition |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3007/ |
| https://www.aclweb.org/anthology/E17-3007 | |
| PWC | https://paperswithcode.com/paper/twine-a-real-time-system-for-tweet-analysis |
| Repo | |
| Framework | |
Don’t Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency Parsers
| Title | Don’t Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency Parsers |
| Authors | Lauriane Aufrant, Guillaume Wisniewski, Fran{\c{c}}ois Yvon |
| Abstract | This paper formalizes a sound extension of dynamic oracles to global training, in the frame of transition-based dependency parsers. By dispensing with the pre-computation of references, this extension widens the training strategies that can be entertained for such parsers; we show this by revisiting two standard training procedures, early-update and max-violation, to correct some of their search space sampling biases. Experimentally, on the SPMRL treebanks, this improvement increases the similarity between the train and test distributions and yields performance improvements up to 0.7 UAS, without any computation overhead. |
| Tasks | Active Learning, Dependency Parsing |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2051/ |
| https://www.aclweb.org/anthology/E17-2051 | |
| PWC | https://paperswithcode.com/paper/dont-stop-me-now-using-global-dynamic-oracles |
| Repo | |
| Framework | |
Can We Create a Tool for General Domain Event Analysis?
| Title | Can We Create a Tool for General Domain Event Analysis? |
| Authors | Siim Orasmaa, Heiki-Jaan Kaalep |
| Abstract | |
| Tasks | Morphological Analysis, Question Answering |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0222/ |
| https://www.aclweb.org/anthology/W17-0222 | |
| PWC | https://paperswithcode.com/paper/can-we-create-a-tool-for-general-domain-event |
| Repo | |
| Framework | |
The Lemlat 3.0 Package for Morphological Analysis of Latin
| Title | The Lemlat 3.0 Package for Morphological Analysis of Latin |
| Authors | Marco Passarotti, Marco Budassi, Eleonora Litta, Paolo Ruffolo |
| Abstract | |
| Tasks | Morphological Analysis |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0506/ |
| https://www.aclweb.org/anthology/W17-0506 | |
| PWC | https://paperswithcode.com/paper/the-lemlat-30-package-for-morphological |
| Repo | |
| Framework | |
The arText prototype: An automatic system for writing specialized texts
| Title | The arText prototype: An automatic system for writing specialized texts |
| Authors | Iria da Cunha, M. Amor Montan{'e}, Luis Hysa |
| Abstract | This article describes an automatic system for writing specialized texts in Spanish. The arText prototype is a free online text editor that includes different types of linguistic information. It is designed for a variety of end users and domains, including specialists and university students working in the fields of medicine and tourism, and laypersons writing to the public administration. ArText provides guidance on how to structure a text, prompts users to include all necessary contents in each section, and detects lexical and discourse problems in the text. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-3015/ |
| https://www.aclweb.org/anthology/E17-3015 | |
| PWC | https://paperswithcode.com/paper/the-artext-prototype-an-automatic-system-for |
| Repo | |
| Framework | |
