Paper Group NANR 78
Parsing Graphs with Regular Graph Grammars. Similarity-Aware Spectral Sparsification by Edge Filtering. Towards Universal Dependencies for Learner Chinese. Text Sentiment Analysis based on Fusion of Structural Information and Serialization Information. Multiword expressions and lexicalism: the view from LFG. IITP at SemEval-2017 Task 8 : A Supervis …
Parsing Graphs with Regular Graph Grammars
| Title | Parsing Graphs with Regular Graph Grammars |
| Authors | Sorcha Gilroy, Adam Lopez, Sebastian Maneth |
| Abstract | Recently, several datasets have become available which represent natural language phenomena as graphs. Hyperedge Replacement Languages (HRL) have been the focus of much attention as a formalism to represent the graphs in these datasets. Chiang et al. (2013) prove that HRL graphs can be parsed in polynomial time with respect to the size of the input graph. We believe that HRL are more expressive than is necessary to represent semantic graphs and we propose the use of Regular Graph Languages (RGL; Courcelle 1991), which is a subfamily of HRL, as a possible alternative. We provide a top-down parsing algorithm for RGL that runs in time linear in the size of the input graph. |
| Tasks | Machine Translation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1024/ |
| https://www.aclweb.org/anthology/S17-1024 | |
| PWC | https://paperswithcode.com/paper/parsing-graphs-with-regular-graph-grammars |
| Repo | |
| Framework | |
Similarity-Aware Spectral Sparsification by Edge Filtering
| Title | Similarity-Aware Spectral Sparsification by Edge Filtering |
| Authors | Zhuo Feng |
| Abstract | In recent years, spectral graph sparsification techniques that can compute ultra-sparse graph proxies have been extensively studied for accelerating various numerical and graph-related applications. Prior nearly-linear-time spectral sparsification methods first extract low-stretch spanning tree from the original graph to form the backbone of the sparsifier, and then recover small portions of spectrally-critical off-tree edges to the spanning tree to significantly improve the approximation quality. However, it is not clear how many off-tree edges should be recovered for achieving a desired spectral similarity level within the sparsifier. Motivated by recent graph signal processing techniques, this paper proposes a similarity-aware spectral graph sparsification framework that leverages efficient spectral off-tree edge embedding and filtering schemes to construct spectral sparsifiers with guaranteed spectral similarity (relative condition number) level. An iterative graph densification scheme is introduced to facilitate efficient and effective filtering of off-tree edges for highly ill-conditioned problems. The proposed method has been validated using various kinds of graphs obtained from public domain sparse matrix collections relevant to VLSI CAD, finite element analysis, as well as social and data networks frequently studied in many machine learning and data mining applications. |
| Tasks | |
| Published | 2017-11-14 |
| URL | https://arxiv.org/abs/1711.05135 |
| https://arxiv.org/abs/1711.05135 | |
| PWC | https://paperswithcode.com/paper/similarity-aware-spectral-sparsification-by |
| Repo | |
| Framework | |
Towards Universal Dependencies for Learner Chinese
| Title | Towards Universal Dependencies for Learner Chinese |
| Authors | John Lee, Herman Leung, Keying Li |
| Abstract | |
| Tasks | Grammatical Error Correction |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0408/ |
| https://www.aclweb.org/anthology/W17-0408 | |
| PWC | https://paperswithcode.com/paper/towards-universal-dependencies-for-learner |
| Repo | |
| Framework | |
Text Sentiment Analysis based on Fusion of Structural Information and Serialization Information
| Title | Text Sentiment Analysis based on Fusion of Structural Information and Serialization Information |
| Authors | Ling Gan, Houyu Gong |
| Abstract | Tree-structured Long Short-Term Memory (Tree-LSTM) has been proved to be an effective method in the sentiment analysis task. It extracts structural information on text, and uses Long Short-Term Memory (LSTM) cell to prevent gradient vanish. However, though combining the LSTM cell, it is still a kind of model that extracts the structural information and almost not extracts serialization information. In this paper, we propose three new models in order to combine those two kinds of information: the structural information generated by the Constituency Tree-LSTM and the serialization information generated by Long-Short Term Memory neural network. Our experiments show that combining those two kinds of information can give contributes to the performance of the sentiment analysis task compared with the single Constituency Tree-LSTM model and the LSTM model. |
| Tasks | Opinion Mining, Sentiment Analysis |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-1034/ |
| https://www.aclweb.org/anthology/I17-1034 | |
| PWC | https://paperswithcode.com/paper/text-sentiment-analysis-based-on-fusion-of |
| Repo | |
| Framework | |
Multiword expressions and lexicalism: the view from LFG
| Title | Multiword expressions and lexicalism: the view from LFG |
| Authors | Jamie Y. Findlay |
| Abstract | Multiword expressions (MWEs) pose a problem for lexicalist theories like Lexical Functional Grammar (LFG), since they are prima facie counterexamples to a strong form of the lexical integrity principle, which entails that a lexical item can only be realised as a single, syntactically atomic word. In this paper, I demonstrate some of the problems facing any strongly lexicalist account of MWEs, and argue that the lexical integrity principle must be weakened. I conclude by sketching a formalism which integrates a Tree Adjoining Grammar into the LFG architecture, taking advantage of this relaxation. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1709/ |
| https://www.aclweb.org/anthology/W17-1709 | |
| PWC | https://paperswithcode.com/paper/multiword-expressions-and-lexicalism-the-view |
| Repo | |
| Framework | |
IITP at SemEval-2017 Task 8 : A Supervised Approach for Rumour Evaluation
| Title | IITP at SemEval-2017 Task 8 : A Supervised Approach for Rumour Evaluation |
| Authors | Vikram Singh, Sunny Narayan, Md Shad Akhtar, Asif Ekbal, Pushpak Bhattacharyya |
| Abstract | This paper describes our system participation in the SemEval-2017 Task 8 {`}RumourEval: Determining rumour veracity and support for rumours{'}. The objective of this task was to predict the stance and veracity of the underlying rumour. We propose a supervised classification approach employing several lexical, content and twitter specific features for learning. Evaluation shows promising results for both the problems. | |
| Tasks | Decision Making, Rumour Detection |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2087/ |
| https://www.aclweb.org/anthology/S17-2087 | |
| PWC | https://paperswithcode.com/paper/iitp-at-semeval-2017-task-8-a-supervised |
| Repo | |
| Framework | |
Deciphering Related Languages
| Title | Deciphering Related Languages |
| Authors | Nima Pourdamghani, Kevin Knight |
| Abstract | We present a method for translating texts between close language pairs. The method does not require parallel data, and it does not require the languages to be written in the same script. We show results for six language pairs: Afrikaans/Dutch, Bosnian/Serbian, Danish/Swedish, Macedonian/Bulgarian, Malaysian/Indonesian, and Polish/Belorussian. We report BLEU scores showing our method to outperform others that do not use parallel data. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1266/ |
| https://www.aclweb.org/anthology/D17-1266 | |
| PWC | https://paperswithcode.com/paper/deciphering-related-languages |
| Repo | |
| Framework | |
Evaluative Language Beyond Bags of Words: Linguistic Insights and Computational Applications
| Title | Evaluative Language Beyond Bags of Words: Linguistic Insights and Computational Applications |
| Authors | Farah Benamara, Maite Taboada, Yannick Mathieu |
| Abstract | The study of evaluation, affect, and subjectivity is a multidisciplinary enterprise, including sociology, psychology, economics, linguistics, and computer science. A number of excellent computational linguistics and linguistic surveys of the field exist. Most surveys, however, do not bring the two disciplines together to show how methods from linguistics can benefit computational sentiment analysis systems. In this survey, we show how incorporating linguistic insights, discourse information, and other contextual phenomena, in combination with the statistical exploitation of data, can result in an improvement over approaches that take advantage of only one of these perspectives. We first provide a comprehensive introduction to evaluative language from both a linguistic and computational perspective. We then argue that the standard computational definition of the concept of evaluative language neglects the dynamic nature of evaluation, in which the interpretation of a given evaluation depends on linguistic and extra-linguistic contextual factors. We thus propose a dynamic definition that incorporates update functions. The update functions allow for different contextual aspects to be incorporated into the calculation of sentiment for evaluative words or expressions, and can be applied at all levels of discourse. We explore each level and highlight which linguistic aspects contribute to accurate extraction of sentiment. We end the review by outlining what we believe the future directions of sentiment analysis are, and the role that discourse and contextual information need to play. |
| Tasks | Sentiment Analysis |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/J17-1006/ |
| https://www.aclweb.org/anthology/J17-1006 | |
| PWC | https://paperswithcode.com/paper/evaluative-language-beyond-bags-of-words |
| Repo | |
| Framework | |
Building and using language resources and infrastructure to develop e-learning programs for a minority language
| Title | Building and using language resources and infrastructure to develop e-learning programs for a minority language |
| Authors | Heli Uibo, Jack Rueter, Sulev Iva |
| Abstract | |
| Tasks | Language Acquisition, Speech Synthesis |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0307/ |
| https://www.aclweb.org/anthology/W17-0307 | |
| PWC | https://paperswithcode.com/paper/building-and-using-language-resources-and |
| Repo | |
| Framework | |
A Network Framework for Noisy Label Aggregation in Social Media
| Title | A Network Framework for Noisy Label Aggregation in Social Media |
| Authors | Xueying Zhan, Yaowei Wang, Yanghui Rao, Haoran Xie, Qing Li, Fu Lee Wang, Tak-Lam Wong |
| Abstract | This paper focuses on the task of noisy label aggregation in social media, where users with different social or culture backgrounds may annotate invalid or malicious tags for documents. To aggregate noisy labels at a small cost, a network framework is proposed by calculating the matching degree of a document{'}s topics and the annotators{'} meta-data. Unlike using the back-propagation algorithm, a probabilistic inference approach is adopted to estimate network parameters. Finally, a new simulation method is designed for validating the effectiveness of the proposed framework in aggregating noisy labels. |
| Tasks | Image Classification, Learning-To-Rank, Topic Models |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2077/ |
| https://www.aclweb.org/anthology/P17-2077 | |
| PWC | https://paperswithcode.com/paper/a-network-framework-for-noisy-label |
| Repo | |
| Framework | |
Cross-lingual Name Tagging and Linking for 282 Languages
| Title | Cross-lingual Name Tagging and Linking for 282 Languages |
| Authors | Xiaoman Pan, Boliang Zhang, Jonathan May, Joel Nothman, Kevin Knight, Heng Ji |
| Abstract | The ambitious goal of this work is to develop a cross-lingual name tagging and linking framework for 282 languages that exist in Wikipedia. Given a document in any of these languages, our framework is able to identify name mentions, assign a coarse-grained or fine-grained type to each mention, and link it to an English Knowledge Base (KB) if it is linkable. We achieve this goal by performing a series of new KB mining methods: generating {``}silver-standard{''} annotations by transferring annotations from English to other languages through cross-lingual links and KB properties, refining annotations through self-training and topic selection, deriving language-specific morphology features from anchor links, and mining word translation pairs from cross-lingual links. Both name tagging and linking results for 282 languages are promising on Wikipedia data and on-Wikipedia data. | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1178/ |
| https://www.aclweb.org/anthology/P17-1178 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-name-tagging-and-linking-for |
| Repo | |
| Framework | |
Improved Recognition and Normalisation of Polish Temporal Expressions
| Title | Improved Recognition and Normalisation of Polish Temporal Expressions |
| Authors | Jan Koco{'n}, Micha{\l} Marci{'n}czuk |
| Abstract | In this article we present the result of the recent research in the recognition and normalisation of Polish temporal expressions. The temporal information extracted from the text plays major role in many information extraction systems, like question answering, event recognition or discourse analysis. We proposed a new method for the temporal expressions normalisation, called Cascade of Partial Rules. Here we describe results achieved by updated version of Liner2 machine learning system. |
| Tasks | Question Answering |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1051/ |
| https://doi.org/10.26615/978-954-452-049-6_051 | |
| PWC | https://paperswithcode.com/paper/improved-recognition-and-normalisation-of |
| Repo | |
| Framework | |
Word Sense Disambiguation with Recurrent Neural Networks
| Title | Word Sense Disambiguation with Recurrent Neural Networks |
| Authors | Alex Popov, er |
| Abstract | This paper presents a neural network architecture for word sense disambiguation (WSD). The architecture employs recurrent neural layers and more specifically LSTM cells, in order to capture information about word order and to easily incorporate distributed word representations (embeddings) as features, without having to use a fixed window of text. The paper demonstrates that the architecture is able to compete with the most successful supervised systems for WSD and that there is an abundance of possible improvements to take it to the current state of the art. In addition, it explores briefly the potential of combining different types of embeddings as input features; it also discusses possible ways for generating {``}artificial corpora{''} from knowledge bases {–} for the purpose of producing training data and in relation to possible applications of embedding lemmas and word senses in the same space. | |
| Tasks | Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-2004/ |
| https://doi.org/10.26615/issn.1314-9156.2017_004 | |
| PWC | https://paperswithcode.com/paper/word-sense-disambiguation-with-recurrent |
| Repo | |
| Framework | |
Natural Language Processing Technologies for Document Profiling
| Title | Natural Language Processing Technologies for Document Profiling |
| Authors | Antonio Guill{'e}n, Yoan Guti{'e}rrez, Rafael Mu{~n}oz |
| Abstract | Nowadays, search for documents on the Internet is becoming increasingly difficult. The reason is the amount of content published by users (articles, comments, blogs, reviews). How to facilitate that the users can find their required documents? What would be necessary to provide useful document meta-data for supporting search engines? In this article, we present a study of some Natural Language Processing (NLP) technologies that can be useful for facilitating the proper identification of documents according to the user needs. For this purpose, it is designed a document profile that will be able to represent semantic meta-data extracted from documents by using NLP technologies. The research is basically focused on the study of different NLP technologies in order to support the creation our novel document profile proposal from semantic perspectives. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1039/ |
| https://doi.org/10.26615/978-954-452-049-6_039 | |
| PWC | https://paperswithcode.com/paper/natural-language-processing-technologies-for |
| Repo | |
| Framework | |
Pyramid-based Summary Evaluation Using Abstract Meaning Representation
| Title | Pyramid-based Summary Evaluation Using Abstract Meaning Representation |
| Authors | Josef Steinberger, Peter Krejzl, Tom{'a}{\v{s}} Brychc{'\i}n |
| Abstract | We propose a novel metric for evaluating summary content coverage. The evaluation framework follows the Pyramid approach to measure how many summarization content units, considered important by human annotators, are contained in an automatic summary. Our approach automatizes the evaluation process, which does not need any manual intervention on the evaluated summary side. Our approach compares abstract meaning representations of each content unit mention and each summary sentence. We found that the proposed metric complements well the widely-used ROUGE metrics. |
| Tasks | Graph Similarity |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1090/ |
| https://doi.org/10.26615/978-954-452-049-6_090 | |
| PWC | https://paperswithcode.com/paper/pyramid-based-summary-evaluation-using |
| Repo | |
| Framework | |
