Paper Group NANR 20
All-In-1 at IJCNLP-2017 Task 4: Short Text Classification with One Model for All Languages. Multivariate Gaussian Document Representation from Word Embeddings for Text Categorization. Face Normals “In-The-Wild” Using Fully Convolutional Networks. Inducing Embeddings for Rare and Unseen Words by Leveraging Lexical Resources. Sentiment Intensity Rank …
All-In-1 at IJCNLP-2017 Task 4: Short Text Classification with One Model for All Languages
| Title | All-In-1 at IJCNLP-2017 Task 4: Short Text Classification with One Model for All Languages |
| Authors | Barbara Plank |
| Abstract | We present All-In-1, a simple model for multilingual text classification that does not require any parallel data. It is based on a traditional Support Vector Machine classifier exploiting multilingual word embeddings and character n-grams. Our model is simple, easily extendable yet very effective, overall ranking 1st (out of 12 teams) in the IJCNLP 2017 shared task on customer feedback analysis in four languages: English, French, Japanese and Spanish. |
| Tasks | Multilingual text classification, Multilingual Word Embeddings, Text Classification, Tokenization, Word Embeddings |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4024/ |
| https://www.aclweb.org/anthology/I17-4024 | |
| PWC | https://paperswithcode.com/paper/all-in-1-at-ijcnlp-2017-task-4-short-text |
| Repo | |
| Framework | |
Multivariate Gaussian Document Representation from Word Embeddings for Text Categorization
| Title | Multivariate Gaussian Document Representation from Word Embeddings for Text Categorization |
| Authors | Giannis Nikolentzos, Polykarpos Meladianos, Fran{\c{c}}ois Rousseau, Yannis Stavrakas, Michalis Vazirgiannis |
| Abstract | Recently, there has been a lot of activity in learning distributed representations of words in vector spaces. Although there are models capable of learning high-quality distributed representations of words, how to generate vector representations of the same quality for phrases or documents still remains a challenge. In this paper, we propose to model each document as a multivariate Gaussian distribution based on the distributed representations of its words. We then measure the similarity between two documents based on the similarity of their distributions. Experiments on eight standard text categorization datasets demonstrate the effectiveness of the proposed approach in comparison with state-of-the-art methods. |
| Tasks | Text Categorization, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2072/ |
| https://www.aclweb.org/anthology/E17-2072 | |
| PWC | https://paperswithcode.com/paper/multivariate-gaussian-document-representation |
| Repo | |
| Framework | |
Face Normals “In-The-Wild” Using Fully Convolutional Networks
| Title | Face Normals “In-The-Wild” Using Fully Convolutional Networks |
| Authors | George Trigeorgis, Patrick Snape, Iasonas Kokkinos, Stefanos Zafeiriou |
| Abstract | In this work we pursue a data-driven approach to the problem of estimating surface normals from a single intensity image, focusing in particular on human faces. We introduce new methods to exploit the currently available facial databases for dataset construction and tailor a deep convolutional neural network to the task of estimating facial surface normals `in-the-wild’. We train a fully convolutional network that can accurately recover facial normals from images including a challenging variety of expressions and facial poses. We compare against state-of-the-art face Shape-from-Shading and 3D reconstruction techniques and show that the proposed network can recover substantially more accurate and realistic normals. Furthermore, in contrast to other existing face-specific surface recovery methods, we do not require the solving of an explicit alignment step due to the fully convolutional nature of our network. | |
| Tasks | 3D Reconstruction |
| Published | 2017-07-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2017/html/Trigeorgis_Face_Normals_In-The-Wild_CVPR_2017_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2017/papers/Trigeorgis_Face_Normals_In-The-Wild_CVPR_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/face-normals-in-the-wild-using-fully |
| Repo | |
| Framework | |
Inducing Embeddings for Rare and Unseen Words by Leveraging Lexical Resources
| Title | Inducing Embeddings for Rare and Unseen Words by Leveraging Lexical Resources |
| Authors | Mohammad Taher Pilehvar, Nigel Collier |
| Abstract | We put forward an approach that exploits the knowledge encoded in lexical resources in order to induce representations for words that were not encountered frequently during training. Our approach provides an advantage over the past work in that it enables vocabulary expansion not only for morphological variations, but also for infrequent domain specific terms. We performed evaluations in different settings, showing that the technique can provide consistent improvements on multiple benchmarks across domains. |
| Tasks | Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2062/ |
| https://www.aclweb.org/anthology/E17-2062 | |
| PWC | https://paperswithcode.com/paper/inducing-embeddings-for-rare-and-unseen-words |
| Repo | |
| Framework | |
Sentiment Intensity Ranking among Adjectives Using Sentiment Bearing Word Embeddings
| Title | Sentiment Intensity Ranking among Adjectives Using Sentiment Bearing Word Embeddings |
| Authors | Raksha Sharma, Arpan Somani, Lakshya Kumar, Pushpak Bhattacharyya |
| Abstract | Identification of intensity ordering among polar (positive or negative) words which have the same semantics can lead to a fine-grained sentiment analysis. For example, {}master{'}, {}seasoned{'} and {`}familiar{'} point to different intensity levels, though they all convey the same meaning (semantics), i.e., expertise: having a good knowledge of. In this paper, we propose a semi-supervised technique that uses sentiment bearing word embeddings to produce a continuous ranking among adjectives that share common semantics. Our system demonstrates a strong Spearman{'}s rank correlation of 0.83 with the gold standard ranking. We show that sentiment bearing word embeddings facilitate a more accurate intensity ranking system than other standard word embeddings (word2vec and GloVe). Word2vec is the state-of-the-art for intensity ordering task. | |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1058/ |
| https://www.aclweb.org/anthology/D17-1058 | |
| PWC | https://paperswithcode.com/paper/sentiment-intensity-ranking-among-adjectives |
| Repo | |
| Framework | |
Are You Asking the Right Questions? Teaching Machines to Ask Clarification Questions
| Title | Are You Asking the Right Questions? Teaching Machines to Ask Clarification Questions |
| Authors | Sudha Rao |
| Abstract | |
| Tasks | |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-3006/ |
| https://www.aclweb.org/anthology/P17-3006 | |
| PWC | https://paperswithcode.com/paper/are-you-asking-the-right-questions-teaching |
| Repo | |
| Framework | |
Using Context Information for Dialog Act Classification in DNN Framework
| Title | Using Context Information for Dialog Act Classification in DNN Framework |
| Authors | Yang Liu, Kun Han, Zhao Tan, Yun Lei |
| Abstract | Previous work on dialog act (DA) classification has investigated different methods, such as hidden Markov models, maximum entropy, conditional random fields, graphical models, and support vector machines. A few recent studies explored using deep learning neural networks for DA classification, however, it is not clear yet what is the best method for using dialog context or DA sequential information, and how much gain it brings. This paper proposes several ways of using context information for DA classification, all in the deep learning framework. The baseline system classifies each utterance using the convolutional neural networks (CNN). Our proposed methods include using hierarchical models (recurrent neural networks (RNN) or CNN) for DA sequence tagging where the bottom layer takes the sentence CNN representation as input, concatenating predictions from the previous utterances with the CNN vector for classification, and performing sequence decoding based on the predictions from the sentence CNN model. We conduct thorough experiments and comparisons on the Switchboard corpus, demonstrate that incorporating context information significantly improves DA classification, and show that we achieve new state-of-the-art performance for this task. |
| Tasks | Dialog Act Classification, Sentence Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1231/ |
| https://www.aclweb.org/anthology/D17-1231 | |
| PWC | https://paperswithcode.com/paper/using-context-information-for-dialog-act |
| Repo | |
| Framework | |
Ngram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics
| Title | Ngram2vec: Learning Improved Word Representations from Ngram Co-occurrence Statistics |
| Authors | Zhe Zhao, Tao Liu, Shen Li, Bofang Li, Xiaoyong Du |
| Abstract | The existing word representation methods mostly limit their information source to word co-occurrence statistics. In this paper, we introduce ngrams into four representation methods: SGNS, GloVe, PPMI matrix, and its SVD factorization. Comprehensive experiments are conducted on word analogy and similarity tasks. The results show that improved word representations are learned from ngram co-occurrence statistics. We also demonstrate that the trained ngram representations are useful in many aspects such as finding antonyms and collocations. Besides, a novel approach of building co-occurrence matrix is proposed to alleviate the hardware burdens brought by ngrams. |
| Tasks | Language Modelling, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1023/ |
| https://www.aclweb.org/anthology/D17-1023 | |
| PWC | https://paperswithcode.com/paper/ngram2vec-learning-improved-word |
| Repo | |
| Framework | |
A Multimodal Dialogue System for Medical Decision Support inside Virtual Reality
| Title | A Multimodal Dialogue System for Medical Decision Support inside Virtual Reality |
| Authors | Alex Prange, er, Margarita Chikobava, Peter Poller, Michael Barz, Daniel Sonntag |
| Abstract | We present a multimodal dialogue system that allows doctors to interact with a medical decision support system in virtual reality (VR). We integrate an interactive visualization of patient records and radiology image data, as well as therapy predictions. Therapy predictions are computed in real-time using a deep learning model. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-5504/ |
| https://www.aclweb.org/anthology/W17-5504 | |
| PWC | https://paperswithcode.com/paper/a-multimodal-dialogue-system-for-medical |
| Repo | |
| Framework | |
Automatically Labeled Data Generation for Large Scale Event Extraction
| Title | Automatically Labeled Data Generation for Large Scale Event Extraction |
| Authors | Yubo Chen, Shulin Liu, Xiang Zhang, Kang Liu, Jun Zhao |
| Abstract | Modern models of event extraction for tasks like ACE are based on supervised learning of events from small hand-labeled data. However, hand-labeled training data is expensive to produce, in low coverage of event types, and limited in size, which makes supervised methods hard to extract large scale of events for knowledge base population. To solve the data labeling problem, we propose to automatically label training data for event extraction via world knowledge and linguistic knowledge, which can detect key arguments and trigger words for each event type and employ them to label events in texts automatically. The experimental results show that the quality of our large scale automatically labeled data is competitive with elaborately human-labeled data. And our automatically labeled data can incorporate with human-labeled data, then improve the performance of models learned from these data. |
| Tasks | Knowledge Base Population, Relation Extraction |
| Published | 2017-07-01 |
| URL | https://www.aclweb.org/anthology/P17-1038/ |
| https://www.aclweb.org/anthology/P17-1038 | |
| PWC | https://paperswithcode.com/paper/automatically-labeled-data-generation-for |
| Repo | |
| Framework | |
Improving Claim Stance Classification with Lexical Knowledge Expansion and Context Utilization
| Title | Improving Claim Stance Classification with Lexical Knowledge Expansion and Context Utilization |
| Authors | Roy Bar-Haim, Lilach Edelstein, Charles Jochim, Noam Slonim |
| Abstract | Stance classification is a core component in on-demand argument construction pipelines. Previous work on claim stance classification relied on background knowledge such as manually-composed sentiment lexicons. We show that both accuracy and coverage can be significantly improved through automatic expansion of the initial lexicon. We also developed a set of contextual features that further improves the state-of-the-art for this task. |
| Tasks | Argument Mining, Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5104/ |
| https://www.aclweb.org/anthology/W17-5104 | |
| PWC | https://paperswithcode.com/paper/improving-claim-stance-classification-with |
| Repo | |
| Framework | |
Decoupling Encoder and Decoder Networks for Abstractive Document Summarization
| Title | Decoupling Encoder and Decoder Networks for Abstractive Document Summarization |
| Authors | Ying Xu, Jey Han Lau, Timothy Baldwin, Trevor Cohn |
| Abstract | Abstractive document summarization seeks to automatically generate a summary for a document, based on some abstract {``}understanding{''} of the original document. State-of-the-art techniques traditionally use attentive encoder{–}decoder architectures. However, due to the large number of parameters in these models, they require large training datasets and long training times. In this paper, we propose decoupling the encoder and decoder networks, and training them separately. We encode documents using an unsupervised document encoder, and then feed the document vector to a recurrent neural network decoder. With this decoupled architecture, we decrease the number of parameters in the decoder substantially, and shorten its training time. Experiments show that the decoupled model achieves comparable performance with state-of-the-art models for in-domain documents, but less well for out-of-domain documents. | |
| Tasks | Abstractive Text Summarization, Document Summarization |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1002/ |
| https://www.aclweb.org/anthology/W17-1002 | |
| PWC | https://paperswithcode.com/paper/decoupling-encoder-and-decoder-networks-for |
| Repo | |
| Framework | |
Utilizing Automatic Predicate-Argument Analysis for Concept Map Mining
| Title | Utilizing Automatic Predicate-Argument Analysis for Concept Map Mining |
| Authors | Tobias Falke, Iryna Gurevych |
| Abstract | |
| Tasks | Document Summarization, Multi-Document Summarization |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6909/ |
| https://www.aclweb.org/anthology/W17-6909 | |
| PWC | https://paperswithcode.com/paper/utilizing-automatic-predicate-argument |
| Repo | |
| Framework | |
Towards Problem Solving Agents that Communicate and Learn
| Title | Towards Problem Solving Agents that Communicate and Learn |
| Authors | Anjali Narayan-Chen, Colin Graber, Mayukh Das, Md Rakibul Islam, Soham Dan, Sriraam Natarajan, Janardhan Rao Doppa, Julia Hockenmaier, Martha Palmer, Dan Roth |
| Abstract | Agents that communicate back and forth with humans to help them execute non-linguistic tasks are a long sought goal of AI. These agents need to translate between utterances and actionable meaning representations that can be interpreted by task-specific problem solvers in a context-dependent manner. They should also be able to learn such actionable interpretations for new predicates on the fly. We define an agent architecture for this scenario and present a series of experiments in the Blocks World domain that illustrate how our architecture supports language learning and problem solving in this domain. |
| Tasks | Semantic Parsing |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2812/ |
| https://www.aclweb.org/anthology/W17-2812 | |
| PWC | https://paperswithcode.com/paper/towards-problem-solving-agents-that |
| Repo | |
| Framework | |
Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data
| Title | Toward Efficient and Accurate Covariance Matrix Estimation on Compressed Data |
| Authors | Xixian Chen, Michael R. Lyu, Irwin King |
| Abstract | Estimating covariance matrices is a fundamental technique in various domains, most notably in machine learning and signal processing. To tackle the challenges of extensive communication costs, large storage capacity requirements, and high processing time complexity when handling massive high-dimensional and distributed data, we propose an efficient and accurate covariance matrix estimation method via data compression. In contrast to previous data-oblivious compression schemes, we leverage a data-aware weighted sampling method to construct low-dimensional data for such estimation. We rigorously prove that our proposed estimator is unbiased and requires smaller data to achieve the same accuracy with specially designed sampling distributions. Besides, we depict that the computational procedures in our algorithm are efficient. All achievements imply an improved tradeoff between the estimation accuracy and computational costs. Finally, the extensive experiments on synthetic and real-world datasets validate the superior property of our method and illustrate that it significantly outperforms the state-of-the-art algorithms. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=473 |
| http://proceedings.mlr.press/v70/chen17g/chen17g.pdf | |
| PWC | https://paperswithcode.com/paper/toward-efficient-and-accurate-covariance |
| Repo | |
| Framework | |
