Paper Group NANR 77
Monolingual Phrase Alignment on Parse Forests. Graph Matching via Multiplicative Update Algorithm. Classification based extraction of numeric values from clinical narratives. Interaction Quality Estimation Using Long Short-Term Memories. Enriching the Notion of Path in ISO-Space. Visually Grounded and Textual Semantic Models Differentially Decode B …
Monolingual Phrase Alignment on Parse Forests
| Title | Monolingual Phrase Alignment on Parse Forests |
| Authors | Yuki Arase, Junichi Tsujii |
| Abstract | We propose an efficient method to conduct phrase alignment on parse forests for paraphrase detection. Unlike previous studies, our method identifies syntactic paraphrases under linguistically motivated grammar. In addition, it allows phrases to non-compositionally align to handle paraphrases with non-homographic phrase correspondences. A dataset that provides gold parse trees and their phrase alignments is created. The experimental results confirm that the proposed method conducts highly accurate phrase alignment compared to human performance. |
| Tasks | Semantic Textual Similarity, Sentence Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1001/ |
| https://www.aclweb.org/anthology/D17-1001 | |
| PWC | https://paperswithcode.com/paper/monolingual-phrase-alignment-on-parse-forests |
| Repo | |
| Framework | |
Graph Matching via Multiplicative Update Algorithm
| Title | Graph Matching via Multiplicative Update Algorithm |
| Authors | Bo Jiang, Jin Tang, Chris Ding, Yihong Gong, Bin Luo |
| Abstract | As a fundamental problem in computer vision, graph matching problem can usually be formulated as a Quadratic Programming (QP) problem with doubly stochastic and discrete (integer) constraints. Since it is NP-hard, approximate algorithms are required. In this paper, we present a new algorithm, called Multiplicative Update Graph Matching (MPGM), that develops a multiplicative update technique to solve the QP matching problem. MPGM has three main benefits: (1) theoretically, MPGM solves the general QP problem with doubly stochastic constraint naturally whose convergence and KKT optimality are guaranteed. (2) Em- pirically, MPGM generally returns a sparse solution and thus can also incorporate the discrete constraint approximately. (3) It is efficient and simple to implement. Experimental results show the benefits of MPGM algorithm. |
| Tasks | Graph Matching |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6911-graph-matching-via-multiplicative-update-algorithm |
| http://papers.nips.cc/paper/6911-graph-matching-via-multiplicative-update-algorithm.pdf | |
| PWC | https://paperswithcode.com/paper/graph-matching-via-multiplicative-update |
| Repo | |
| Framework | |
Classification based extraction of numeric values from clinical narratives
| Title | Classification based extraction of numeric values from clinical narratives |
| Authors | Maximilian Zubke |
| Abstract | The robust extraction of numeric values from clinical narratives is a well known problem in clinical data warehouses. In this paper we describe a dynamic and domain-independent approach to deliver numerical described values from clinical narratives. In contrast to alternative systems, we neither use manual defined rules nor any kind of ontologies or nomenclatures. Instead we propose a topic-based system, that tackles the information extraction as a text classification problem. Hence we use machine learning to identify the crucial context features of a topic-specific numeric value by a given set of example sentences, so that the manual effort reduces to the selection of appropriate sample sentences. We describe context features of a certain numeric value by term frequency vectors which are generated by multiple document segmentation procedures. Due to this simultaneous segmentation approaches, there can be more than one context vector for a numeric value. In those cases, we choose the context vector with the highest classification confidence and suppress the rest. To test our approach, we used a dataset from a german hospital containing 12,743 narrative reports about laboratory results of Leukemia patients. We used Support Vector Machines (SVM) for classification and achieved an average accuracy of 96{%} on a manually labeled subset of 2073 documents, using 10-fold cross validation. This is a significant improvement over an alternative rule based system. |
| Tasks | Text Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-8004/ |
| https://doi.org/10.26615/978-954-452-044-1_004 | |
| PWC | https://paperswithcode.com/paper/classification-based-extraction-of-numeric |
| Repo | |
| Framework | |
Interaction Quality Estimation Using Long Short-Term Memories
| Title | Interaction Quality Estimation Using Long Short-Term Memories |
| Authors | Niklas Rach, Wolfgang Minker, Stefan Ultes |
| Abstract | For estimating the Interaction Quality (IQ) in Spoken Dialogue Systems (SDS), the dialogue history is of significant importance. Previous works included this information manually in the form of precomputed temporal features into the classification process. Here, we employ a deep learning architecture based on Long Short-Term Memories (LSTM) to extract this information automatically from the data, thus estimating IQ solely by using current exchange features. We show that it is thereby possible to achieve competitive results as in a scenario where manually optimized temporal features have been included. |
| Tasks | Spoken Dialogue Systems |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5520/ |
| https://www.aclweb.org/anthology/W17-5520 | |
| PWC | https://paperswithcode.com/paper/interaction-quality-estimation-using-long |
| Repo | |
| Framework | |
Enriching the Notion of Path in ISO-Space
| Title | Enriching the Notion of Path in ISO-Space |
| Authors | James Pustejovsky, Kiyong Lee |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7415/ |
| https://www.aclweb.org/anthology/W17-7415 | |
| PWC | https://paperswithcode.com/paper/enriching-the-notion-of-path-in-iso-space |
| Repo | |
| Framework | |
Visually Grounded and Textual Semantic Models Differentially Decode Brain Activity Associated with Concrete and Abstract Nouns
| Title | Visually Grounded and Textual Semantic Models Differentially Decode Brain Activity Associated with Concrete and Abstract Nouns |
| Authors | Andrew J. Anderson, Douwe Kiela, Stephen Clark, Massimo Poesio |
| Abstract | Important advances have recently been made using computational semantic models to decode brain activity patterns associated with concepts; however, this work has almost exclusively focused on concrete nouns. How well these models extend to decoding abstract nouns is largely unknown. We address this question by applying state-of-the-art computational models to decode functional Magnetic Resonance Imaging (fMRI) activity patterns, elicited by participants reading and imagining a diverse set of both concrete and abstract nouns. One of the models we use is linguistic, exploiting the recent word2vec skipgram approach trained on Wikipedia. The second is visually grounded, using deep convolutional neural networks trained on Google Images. Dual coding theory considers concrete concepts to be encoded in the brain both linguistically and visually, and abstract concepts only linguistically. Splitting the fMRI data according to human concreteness ratings, we indeed observe that both models significantly decode the most concrete nouns; however, accuracy is significantly greater using the text-based models for the most abstract nouns. More generally this confirms that current computational models are sufficiently advanced to assist in investigating the representational structure of abstract concepts in the brain. |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/Q17-1002/ |
| https://www.aclweb.org/anthology/Q17-1002 | |
| PWC | https://paperswithcode.com/paper/visually-grounded-and-textual-semantic-models |
| Repo | |
| Framework | |
Learning Contextual Embeddings for Structural Semantic Similarity using Categorical Information
| Title | Learning Contextual Embeddings for Structural Semantic Similarity using Categorical Information |
| Authors | Massimo Nicosia, Aless Moschitti, ro |
| Abstract | Tree kernels (TKs) and neural networks are two effective approaches for automatic feature engineering. In this paper, we combine them by modeling context word similarity in semantic TKs. This way, the latter can operate subtree matching by applying neural-based similarity on tree lexical nodes. We study how to learn representations for the words in context such that TKs can exploit more focused information. We found that neural embeddings produced by current methods do not provide a suitable contextual similarity. Thus, we define a new approach based on a Siamese Network, which produces word representations while learning a binary text similarity. We set the latter considering examples in the same category as similar. The experiments on question and sentiment classification show that our semantic TK highly improves previous results. |
| Tasks | Feature Engineering, Question Answering, Relation Extraction, Semantic Similarity, Semantic Textual Similarity, Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/K17-1027/ |
| https://www.aclweb.org/anthology/K17-1027 | |
| PWC | https://paperswithcode.com/paper/learning-contextual-embeddings-for-structural |
| Repo | |
| Framework | |
Annotation schemes in North S'ami dependency parsing
| Title | Annotation schemes in North S'ami dependency parsing |
| Authors | Francis M. Tyers, Mariya Sheyanova |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-0607/ |
| https://www.aclweb.org/anthology/W17-0607 | |
| PWC | https://paperswithcode.com/paper/annotation-schemes-in-north-sami-dependency |
| Repo | |
| Framework | |
Recursive Sampling for the Nystrom Method
| Title | Recursive Sampling for the Nystrom Method |
| Authors | Cameron Musco, Christopher Musco |
| Abstract | We give the first algorithm for kernel Nystrom approximation that runs in linear time in the number of training points and is provably accurate for all kernel matrices, without dependence on regularity or incoherence conditions. The algorithm projects the kernel onto a set of s landmark points sampled by their ridge leverage scores, requiring just O(ns) kernel evaluations and O(ns^2) additional runtime. While leverage score sampling has long been known to give strong theoretical guarantees for Nystrom approximation, by employing a fast recursive sampling scheme, our algorithm is the first to make the approach scalable. Empirically we show that it finds more accurate kernel approximations in less time than popular techniques such as classic Nystrom approximation and the random Fourier features method. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6973-recursive-sampling-for-the-nystrom-method |
| http://papers.nips.cc/paper/6973-recursive-sampling-for-the-nystrom-method.pdf | |
| PWC | https://paperswithcode.com/paper/recursive-sampling-for-the-nystrom-method-1 |
| Repo | |
| Framework | |
Annotation, Modelling and Analysis of Fine-Grained Emotions on a Stance and Sentiment Detection Corpus
| Title | Annotation, Modelling and Analysis of Fine-Grained Emotions on a Stance and Sentiment Detection Corpus |
| Authors | Hendrik Schuff, Jeremy Barnes, Julian Mohme, Sebastian Pad{'o}, Roman Klinger |
| Abstract | There is a rich variety of data sets for sentiment analysis (viz., polarity and subjectivity classification). For the more challenging task of detecting discrete emotions following the definitions of Ekman and Plutchik, however, there are much fewer data sets, and notably no resources for the social media domain. This paper contributes to closing this gap by extending the \textit{SemEval 2016 stance and sentiment dataset}with emotion annotation. We (a) analyse annotation reliability and annotation merging; (b) investigate the relation between emotion annotation and the other annotation layers (stance, sentiment); (c) report modelling results as a baseline for future work. |
| Tasks | Emotion Recognition, Sentiment Analysis, Stance Detection |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5203/ |
| https://www.aclweb.org/anthology/W17-5203 | |
| PWC | https://paperswithcode.com/paper/annotation-modelling-and-analysis-of-fine |
| Repo | |
| Framework | |
SSN_MLRG1 at SemEval-2017 Task 5: Fine-Grained Sentiment Analysis Using Multiple Kernel Gaussian Process Regression Model
| Title | SSN_MLRG1 at SemEval-2017 Task 5: Fine-Grained Sentiment Analysis Using Multiple Kernel Gaussian Process Regression Model |
| Authors | Angel Deborah S, S Milton Rajendram, T T Mirnalinee |
| Abstract | The system developed by the SSN{_}MLRG1 team for Semeval-2017 task 5 on fine-grained sentiment analysis uses Multiple Kernel Gaussian Process for identifying the optimistic and pessimistic sentiments associated with companies and stocks. Since the comments made at different times about the same companies and stocks may display different emotions, their properties such as smoothness and periodicity may vary. Our experiments show that while single kernel Gaussian Process can learn certain properties well, Multiple Kernel Gaussian Process are effective in learning the presence of different properties simultaneously. |
| Tasks | Decision Making, Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2139/ |
| https://www.aclweb.org/anthology/S17-2139 | |
| PWC | https://paperswithcode.com/paper/ssn_mlrg1-at-semeval-2017-task-5-fine-grained |
| Repo | |
| Framework | |
Leveraging intra and inter-dataset variations for robust face alignment
| Title | Leveraging intra and inter-dataset variations for robust face alignment |
| Authors | Wenyan Wu, Shuo Yang |
| Abstract | Face alignment is a critical topic in the computer vision community. Numerous efforts have been made and various benchmark datasets have been released in recent decades. However, two significant issues remain in recent datasets, e.g., Intra-Dataset Variation and Inter-Dataset Variation. Inter-Dataset Variation refers to bias on expression, head pose, etc. inside one certain dataset, while Intra-Dataset Variation refers to different bias across different datasets. To address the mentioned problems, we proposed a novel Deep Variation Leveraging Network (DVLN), which consists of two strong coupling sub-networks, e.g., Dataset-Across Network (DA-Net) and Candidate-Decision Network (CD-Net). Extensive evaluations show that our approach demonstrates real-time performance and dramatically outperforms state-of-the-art methods on the challenging 300-W dataset. |
| Tasks | Face Alignment, Robust Face Alignment |
| Published | 2017-07-21 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017_workshops/w33/html/Wu_Leveraging_Intra_and_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017_workshops/w33/papers/Wu_Leveraging_Intra_and_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/leveraging-intra-and-inter-dataset-variations |
| Repo | |
| Framework | |
Automatic Generation of Situation Models for Plan Recognition Problems
| Title | Automatic Generation of Situation Models for Plan Recognition Problems |
| Authors | Kristina Yordanova |
| Abstract | Recent attempts at behaviour understanding through language grounding have shown that it is possible to automatically generate models for planning problems from textual instructions. One drawback of these approaches is that they either do not make use of the semantic structure behind the model elements identified in the text, or they manually incorporate a collection of concepts with semantic relationships between them. We call this collection of knowledge situation model. The situation model introduces additional context information to the model. It could also potentially reduce the complexity of the planning problem compared to models that do not use situation models. To address this problem, we propose an approach that automatically generates the situation model from textual instructions. The approach is able to identify various hierarchical, spatial, directional, and causal relations. We use the situation model to automatically generate planning problems in a PDDL notation and we show that the situation model reduces the complexity of the PDDL model in terms of number of operators and branching factor compared to planning models that do not make use of situation models. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1105/ |
| https://doi.org/10.26615/978-954-452-049-6_105 | |
| PWC | https://paperswithcode.com/paper/automatic-generation-of-situation-models-for |
| Repo | |
| Framework | |
Dish Classification using Knowledge based Dietary Conflict Detection
| Title | Dish Classification using Knowledge based Dietary Conflict Detection |
| Authors | Nadia Clairet |
| Abstract | The present paper considers the problem of dietary conflict detection from dish titles. The proposed method explores the semantics associated with the dish title in order to discover a certain or possible incompatibility of a particular dish with a particular diet. Dish titles are parts of the elusive and metaphoric gastronomy language, their processing can be viewed as a combination of short text and domain-specific texts analysis. We build our algorithm on the basis of a common knowledge lexical semantic network and show how such network can be used for domain specific short text processing. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-2001/ |
| https://doi.org/10.26615/issn.1314-9156.2017_001 | |
| PWC | https://paperswithcode.com/paper/dish-classification-using-knowledge-based |
| Repo | |
| Framework | |
Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies (UDW 2017)
| Title | Proceedings of the NoDaLiDa 2017 Workshop on Universal Dependencies (UDW 2017) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-05-01 |
| URL | https://www.aclweb.org/anthology/W17-0400/ |
| https://www.aclweb.org/anthology/W17-0400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-nodalida-2017-workshop-on |
| Repo | |
| Framework | |
