Paper Group NANR 65
Visual Denotations for Recognizing Textual Entailment. The strange geometry of skip-gram with negative sampling. Multitask Learning for Mental Health Conditions with Limited Social Media Data. Merging the Trees - Building a Morphological Treebank for German from Two Resources. Towards a dependency-annotated treebank for Bambara. Dangerous Relations …
Visual Denotations for Recognizing Textual Entailment
| Title | Visual Denotations for Recognizing Textual Entailment |
| Authors | Dan Han, Pascual Mart{'\i}nez-G{'o}mez, Koji Mineshima |
| Abstract | In the logic approach to Recognizing Textual Entailment, identifying phrase-to-phrase semantic relations is still an unsolved problem. Resources such as the Paraphrase Database offer limited coverage despite their large size whereas unsupervised distributional models of meaning often fail to recognize phrasal entailments. We propose to map phrases to their visual denotations and compare their meaning in terms of their images. We show that our approach is effective in the task of Recognizing Textual Entailment when combined with specific linguistic and logic features. |
| Tasks | Natural Language Inference, Semantic Composition |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1305/ |
| https://www.aclweb.org/anthology/D17-1305 | |
| PWC | https://paperswithcode.com/paper/visual-denotations-for-recognizing-textual |
| Repo | |
| Framework | |
The strange geometry of skip-gram with negative sampling
| Title | The strange geometry of skip-gram with negative sampling |
| Authors | David Mimno, Laure Thompson |
| Abstract | Despite their ubiquity, word embeddings trained with skip-gram negative sampling (SGNS) remain poorly understood. We find that vector positions are not simply determined by semantic similarity, but rather occupy a narrow cone, diametrically opposed to the context vectors. We show that this geometric concentration depends on the ratio of positive to negative examples, and that it is neither theoretically nor empirically inherent in related embedding algorithms. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1308/ |
| https://www.aclweb.org/anthology/D17-1308 | |
| PWC | https://paperswithcode.com/paper/the-strange-geometry-of-skip-gram-with |
| Repo | |
| Framework | |
Multitask Learning for Mental Health Conditions with Limited Social Media Data
| Title | Multitask Learning for Mental Health Conditions with Limited Social Media Data |
| Authors | Adrian Benton, Margaret Mitchell, Dirk Hovy |
| Abstract | |
| Tasks | Gender Prediction, Multi-Task Learning |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/papers/E17-1015/e17-1015 |
| https://www.aclweb.org/anthology/E17-1015v2 | |
| PWC | https://paperswithcode.com/paper/multitask-learning-for-mental-health |
| Repo | |
| Framework | |
Merging the Trees - Building a Morphological Treebank for German from Two Resources
| Title | Merging the Trees - Building a Morphological Treebank for German from Two Resources |
| Authors | Petra Steiner |
| Abstract | |
| Tasks | Information Retrieval, Morphological Analysis |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7619/ |
| https://www.aclweb.org/anthology/W17-7619 | |
| PWC | https://paperswithcode.com/paper/merging-the-trees-building-a-morphological |
| Repo | |
| Framework | |
Towards a dependency-annotated treebank for Bambara
| Title | Towards a dependency-annotated treebank for Bambara |
| Authors | Ekaterina Aplonova, Francis M. Tyers |
| Abstract | |
| Tasks | Dependency Parsing |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7618/ |
| https://www.aclweb.org/anthology/W17-7618 | |
| PWC | https://paperswithcode.com/paper/towards-a-dependency-annotated-treebank-for |
| Repo | |
| Framework | |
Dangerous Relations in Dependency Treebanks
| Title | Dangerous Relations in Dependency Treebanks |
| Authors | Chiara Alzetta, Felice Dell{'}Orletta, Simonetta Montemagni, Giulia Venturi |
| Abstract | |
| Tasks | Dependency Parsing, Machine Translation |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-7624/ |
| https://www.aclweb.org/anthology/W17-7624 | |
| PWC | https://paperswithcode.com/paper/dangerous-relations-in-dependency-treebanks |
| Repo | |
| Framework | |
ECNU at SemEval-2017 Task 7: Using Supervised and Unsupervised Methods to Detect and Locate English Puns
| Title | ECNU at SemEval-2017 Task 7: Using Supervised and Unsupervised Methods to Detect and Locate English Puns |
| Authors | Yuhuan Xiu, Man Lan, Yuanbin Wu |
| Abstract | This paper describes our submissions to task 7 in SemEval 2017, i.e., Detection and Interpretation of English Puns. We participated in the first two subtasks, which are to detect and locate English puns respectively. For subtask 1, we presented a supervised system to determine whether or not a sentence contains a pun using similarity features calculated on sense vectors or cluster center vectors. For subtask 2, we established an unsupervised system to locate the pun by scoring each word in the sentence and we assumed that the word with the smallest score is the pun. |
| Tasks | Part-Of-Speech Tagging, Semantic Textual Similarity, Word Sense Disambiguation |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2078/ |
| https://www.aclweb.org/anthology/S17-2078 | |
| PWC | https://paperswithcode.com/paper/ecnu-at-semeval-2017-task-7-using-supervised |
| Repo | |
| Framework | |
Life-iNet: A Structured Network-Based Knowledge Exploration and Analytics System for Life Sciences
| Title | Life-iNet: A Structured Network-Based Knowledge Exploration and Analytics System for Life Sciences |
| Authors | Xiang Ren, Jiaming Shen, Meng Qu, Xuan Wang, Zeqiu Wu, Qi Zhu, Meng Jiang, Fangbo Tao, Saurabh Sinha, David Liem, Peipei Ping, Richard Weinshilboum, Jiawei Han |
| Abstract | |
| Tasks | Efficient Exploration |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4010/ |
| https://www.aclweb.org/anthology/P17-4010 | |
| PWC | https://paperswithcode.com/paper/life-inet-a-structured-network-based |
| Repo | |
| Framework | |
The Effect of Negative Sampling Strategy on Capturing Semantic Similarity in Document Embeddings
| Title | The Effect of Negative Sampling Strategy on Capturing Semantic Similarity in Document Embeddings |
| Authors | Marzieh Saeidi, Ritwik Kulkarni, Theodosia Togia, Michele Sama |
| Abstract | |
| Tasks | Answer Selection, Community Question Answering, Question Answering, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-7301/ |
| https://www.aclweb.org/anthology/W17-7301 | |
| PWC | https://paperswithcode.com/paper/the-effect-of-negative-sampling-strategy-on |
| Repo | |
| Framework | |
Semedico: A Comprehensive Semantic Search Engine for the Life Sciences
| Title | Semedico: A Comprehensive Semantic Search Engine for the Life Sciences |
| Authors | Erik Faessler, Udo Hahn |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-4016/ |
| https://www.aclweb.org/anthology/P17-4016 | |
| PWC | https://paperswithcode.com/paper/semedico-a-comprehensive-semantic-search |
| Repo | |
| Framework | |
Does syntax help discourse segmentation? Not so much
| Title | Does syntax help discourse segmentation? Not so much |
| Authors | Chlo{'e} Braud, Oph{'e}lie Lacroix, Anders S{\o}gaard |
| Abstract | Discourse segmentation is the first step in building discourse parsers. Most work on discourse segmentation does not scale to real-world discourse parsing across languages, for two reasons: (i) models rely on constituent trees, and (ii) experiments have relied on gold standard identification of sentence and token boundaries. We therefore investigate to what extent constituents can be replaced with universal dependencies, or left out completely, as well as how state-of-the-art segmenters fare in the absence of sentence boundaries. Our results show that dependency information is less useful than expected, but we provide a fully scalable, robust model that only relies on part-of-speech information, and show that it performs well across languages in the absence of any gold-standard annotation. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1258/ |
| https://www.aclweb.org/anthology/D17-1258 | |
| PWC | https://paperswithcode.com/paper/does-syntax-help-discourse-segmentation-not |
| Repo | |
| Framework | |
SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-Training on Indoor Segmentation?
| Title | SceneNet RGB-D: Can 5M Synthetic Images Beat Generic ImageNet Pre-Training on Indoor Segmentation? |
| Authors | John McCormac, Ankur Handa, Stefan Leutenegger, Andrew J. Davison |
| Abstract | We introduce SceneNet RGB-D, a dataset providing pixel-perfect ground truth for scene understanding problems such as semantic segmentation, instance segmentation, and object detection. It also provides perfect camera poses and depth data, allowing investigation into geometric computer vision problems such as optical flow, camera pose estimation, and 3D scene labelling tasks. Random sampling permits virtually unlimited scene configurations, and here we provide 5M rendered RGB-D images from 16K randomly generated 3D trajectories in synthetic layouts, with random but physically simulated object configurations. We compare the semantic segmentation performance of network weights produced from pre-training on RGB images from our dataset against generic VGG-16 ImageNet weights. After fine-tuning on the SUN RGB-D and NYUv2 real-world datasets we find in both cases that the synthetically pre-trained network outperforms the VGG-16 weights. When synthetic pre-training includes a depth channel (something ImageNet cannot natively provide) the performance is greater still. This suggests that large-scale high-quality synthetic RGB datasets with task-specific labels can be more useful for pre-training than real-world generic pre-training such as ImageNet. We host the dataset at http://robotvault.bitbucket.io/scenenet-rgbd.html |
| Tasks | Instance Segmentation, Object Detection, Optical Flow Estimation, Pose Estimation, Scene Understanding, Semantic Segmentation |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/McCormac_SceneNet_RGB-D_Can_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/McCormac_SceneNet_RGB-D_Can_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/scenenet-rgb-d-can-5m-synthetic-images-beat |
| Repo | |
| Framework | |
Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Sparse Coding
| Title | Efficient Optimization for Linear Dynamical Systems with Applications to Clustering and Sparse Coding |
| Authors | Wenbing Huang, Mehrtash Harandi, Tong Zhang, Lijie Fan, Fuchun Sun, Junzhou Huang |
| Abstract | Linear Dynamical Systems (LDSs) are fundamental tools for modeling spatio-temporal data in various disciplines. Though rich in modeling, analyzing LDSs is not free of difficulty, mainly because LDSs do not comply with Euclidean geometry and hence conventional learning techniques can not be applied directly. In this paper, we propose an efficient projected gradient descent method to minimize a general form of a loss function and demonstrate how clustering and sparse coding with LDSs can be solved by the proposed method efficiently. To this end, we first derive a novel canonical form for representing the parameters of an LDS, and then show how gradient-descent updates through the projection on the space of LDSs can be achieved dexterously. In contrast to previous studies, our solution avoids any approximation in LDS modeling or during the optimization process. Extensive experiments reveal the superior performance of the proposed method in terms of the convergence and classification accuracy over state-of-the-art techniques. |
| Tasks | |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6936-efficient-optimization-for-linear-dynamical-systems-with-applications-to-clustering-and-sparse-coding |
| http://papers.nips.cc/paper/6936-efficient-optimization-for-linear-dynamical-systems-with-applications-to-clustering-and-sparse-coding.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-optimization-for-linear-dynamical |
| Repo | |
| Framework | |
Understanding and Predicting Empathic Behavior in Counseling Therapy
| Title | Understanding and Predicting Empathic Behavior in Counseling Therapy |
| Authors | Ver{'o}nica P{'e}rez-Rosas, Rada Mihalcea, Kenneth Resnicow, Satinder Singh, Lawrence An |
| Abstract | Counselor empathy is associated with better outcomes in psychology and behavioral counseling. In this paper, we explore several aspects pertaining to counseling interaction dynamics and their relation to counselor empathy during motivational interviewing encounters. Particularly, we analyze aspects such as participants{'} engagement, participants{'} verbal and nonverbal accommodation, as well as topics being discussed during the conversation, with the final goal of identifying linguistic and acoustic markers of counselor empathy. We also show how we can use these findings alongside other raw linguistic and acoustic features to build accurate counselor empathy classifiers with accuracies of up to 80{%}. |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1131/ |
| https://www.aclweb.org/anthology/P17-1131 | |
| PWC | https://paperswithcode.com/paper/understanding-and-predicting-empathic |
| Repo | |
| Framework | |
Oracle Summaries of Compressive Summarization
| Title | Oracle Summaries of Compressive Summarization |
| Authors | Tsutomu Hirao, Masaaki Nishino, Masaaki Nagata |
| Abstract | This paper derives an Integer Linear Programming (ILP) formulation to obtain an oracle summary of the compressive summarization paradigm in terms of ROUGE. The oracle summary is essential to reveal the upper bound performance of the paradigm. Experimental results on the DUC dataset showed that ROUGE scores of compressive oracles are significantly higher than those of extractive oracles and state-of-the-art summarization systems. These results reveal that compressive summarization is a promising paradigm and encourage us to continue with the research to produce informative summaries. |
| Tasks | Sentence Compression |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-2043/ |
| https://www.aclweb.org/anthology/P17-2043 | |
| PWC | https://paperswithcode.com/paper/oracle-summaries-of-compressive-summarization |
| Repo | |
| Framework | |
