Paper Group NANR 70
Cross-Lingual Syntactically Informed Distributed Word Representations. Annotation of pain and anesthesia events for surgery-related processes and outcomes extraction. Communicating and Acting: Understanding Gesture in Simulation Semantics. Towards a Universal Sentiment Classifier in Multiple languages. CROWD-IN-THE-LOOP: A Hybrid Approach for Annot …
Cross-Lingual Syntactically Informed Distributed Word Representations
| Title | Cross-Lingual Syntactically Informed Distributed Word Representations |
| Authors | Ivan Vuli{'c} |
| Abstract | We develop a novel cross-lingual word representation model which injects syntactic information through dependency-based contexts into a shared cross-lingual word vector space. The model, termed CL-DepEmb, is based on the following assumptions: (1) dependency relations are largely language-independent, at least for related languages and prominent dependency links such as direct objects, as evidenced by the Universal Dependencies project; (2) word translation equivalents take similar grammatical roles in a sentence and are therefore substitutable within their syntactic contexts. Experiments with several language pairs on word similarity and bilingual lexicon induction, two fundamental semantic tasks emphasising semantic similarity, suggest the usefulness of the proposed syntactically informed cross-lingual word vector spaces. Improvements are observed in both tasks over standard cross-lingual {``}offline mapping{''} baselines trained using the same setup and an equal level of bilingual supervision. | |
| Tasks | Entity Linking, Information Retrieval, Semantic Similarity, Semantic Textual Similarity, Transfer Learning, Word Embeddings |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-2065/ |
| https://www.aclweb.org/anthology/E17-2065 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-syntactically-informed |
| Repo | |
| Framework | |
Annotation of pain and anesthesia events for surgery-related processes and outcomes extraction
| Title | Annotation of pain and anesthesia events for surgery-related processes and outcomes extraction |
| Authors | Wen-wai Yim, Dario Tedesco, Catherine Curtin, Hern, Tina ez-Boussard |
| Abstract | Pain and anesthesia information are crucial elements to identifying surgery-related processes and outcomes. However pain is not consistently recorded in the electronic medical record. Even when recorded, the rich complex granularity of the pain experience may be lost. Similarly, anesthesia information is recorded using local electronic collection systems; though the accuracy and completeness of the information is unknown. We propose an annotation schema to capture pain, pain management, and anesthesia event information. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2325/ |
| https://www.aclweb.org/anthology/W17-2325 | |
| PWC | https://paperswithcode.com/paper/annotation-of-pain-and-anesthesia-events-for |
| Repo | |
| Framework | |
Communicating and Acting: Understanding Gesture in Simulation Semantics
| Title | Communicating and Acting: Understanding Gesture in Simulation Semantics |
| Authors | Nikhil Krishnaswamy, Pradyumna Narayana, Isaac Wang, Kyeongmin Rim, Rahul Bangar, Dhruva Patil, Gururaj Mulay, Ross Beveridge, Jaime Ruiz, Bruce Draper, James Pustejovsky |
| Abstract | |
| Tasks | |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/W17-6919/ |
| https://www.aclweb.org/anthology/W17-6919 | |
| PWC | https://paperswithcode.com/paper/communicating-and-acting-understanding |
| Repo | |
| Framework | |
Towards a Universal Sentiment Classifier in Multiple languages
| Title | Towards a Universal Sentiment Classifier in Multiple languages |
| Authors | Kui Xu, Xiaojun Wan |
| Abstract | Existing sentiment classifiers usually work for only one specific language, and different classification models are used in different languages. In this paper we aim to build a universal sentiment classifier with a single classification model in multiple different languages. In order to achieve this goal, we propose to learn multilingual sentiment-aware word embeddings simultaneously based only on the labeled reviews in English and unlabeled parallel data available in a few language pairs. It is not required that the parallel data exist between English and any other language, because the sentiment information can be transferred into any language via pivot languages. We present the evaluation results of our universal sentiment classifier in five languages, and the results are very promising even when the parallel data between English and the target languages are not used. Furthermore, the universal single classifier is compared with a few cross-language sentiment classifiers relying on direct parallel data between the source and target languages, and the results show that the performance of our universal sentiment classifier is very promising compared to that of different cross-language classifiers in multiple target languages. |
| Tasks | Machine Translation, Sentiment Analysis, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1053/ |
| https://www.aclweb.org/anthology/D17-1053 | |
| PWC | https://paperswithcode.com/paper/towards-a-universal-sentiment-classifier-in |
| Repo | |
| Framework | |
CROWD-IN-THE-LOOP: A Hybrid Approach for Annotating Semantic Roles
| Title | CROWD-IN-THE-LOOP: A Hybrid Approach for Annotating Semantic Roles |
| Authors | Chenguang Wang, Alan Akbik, Laura Chiticariu, Yunyao Li, Fei Xia, Anbang Xu |
| Abstract | Crowdsourcing has proven to be an effective method for generating labeled data for a range of NLP tasks. However, multiple recent attempts of using crowdsourcing to generate gold-labeled training data for semantic role labeling (SRL) reported only modest results, indicating that SRL is perhaps too difficult a task to be effectively crowdsourced. In this paper, we postulate that while producing SRL annotation does require expert involvement in general, a large subset of SRL labeling tasks is in fact appropriate for the crowd. We present a novel workflow in which we employ a classifier to identify difficult annotation tasks and route each task either to experts or crowd workers according to their difficulties. Our experimental evaluation shows that the proposed approach reduces the workload for experts by over two-thirds, and thus significantly reduces the cost of producing SRL annotation at little loss in quality. |
| Tasks | Machine Translation, Question Answering, Semantic Role Labeling |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1205/ |
| https://www.aclweb.org/anthology/D17-1205 | |
| PWC | https://paperswithcode.com/paper/crowd-in-the-loop-a-hybrid-approach-for |
| Repo | |
| Framework | |
Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints
| Title | Semantic Specialization of Distributional Word Vector Spaces using Monolingual and Cross-Lingual Constraints |
| Authors | Nikola Mrk{\v{s}}i{'c}, Ivan Vuli{'c}, Diarmuid {'O} S{'e}aghdha, Ira Leviant, Roi Reichart, Milica Ga{\v{s}}i{'c}, Anna Korhonen, Steve Young |
| Abstract | We present Attract-Repel, an algorithm for improving the semantic quality of word vectors by injecting constraints extracted from lexical resources. Attract-Repel facilitates the use of constraints from mono- and cross-lingual resources, yielding semantically specialized cross-lingual vector spaces. Our evaluation shows that the method can make use of existing cross-lingual lexicons to construct high-quality vector spaces for a plethora of different languages, facilitating semantic transfer from high- to lower-resource ones. The effectiveness of our approach is demonstrated with state-of-the-art results on semantic similarity datasets in six languages. We next show that Attract-Repel-specialized vectors boost performance in the downstream task of dialogue state tracking (DST) across multiple languages. Finally, we show that cross-lingual vector spaces produced by our algorithm facilitate the training of multilingual DST models, which brings further performance improvements. |
| Tasks | Dialogue State Tracking, Representation Learning, Semantic Similarity, Semantic Textual Similarity |
| Published | 2017-01-01 |
| URL | https://www.aclweb.org/anthology/Q17-1022/ |
| https://www.aclweb.org/anthology/Q17-1022 | |
| PWC | https://paperswithcode.com/paper/semantic-specialization-of-distributional |
| Repo | |
| Framework | |
ADAPT at IJCNLP-2017 Task 4: A Multinomial Naive Bayes Classification Approach for Customer Feedback Analysis task
| Title | ADAPT at IJCNLP-2017 Task 4: A Multinomial Naive Bayes Classification Approach for Customer Feedback Analysis task |
| Authors | Pintu Lohar, Koel Dutta Chowdhury, Haithem Afli, Mohammed Hasanuzzaman, Andy Way |
| Abstract | In this age of the digital economy, promoting organisations attempt their best to engage the customers in the feedback provisioning process. With the assistance of customer insights, an organisation can develop a better product and provide a better service to its customer. In this paper, we analyse the real world samples of customer feedback from Microsoft Office customers in four languages, i.e., English, French, Spanish and Japanese and conclude a five-plus-one-classes categorisation (comment, request, bug, complaint, meaningless and undetermined) for meaning classification. The task is to {%}access multilingual corpora annotated by the proposed meaning categorization scheme and develop a system to determine what class(es) the customer feedback sentences should be annotated as in four languages. We propose following approaches to accomplish this task: (i) a multinomial naive bayes (MNB) approach for multi-label classification, (ii) MNB with one-vs-rest classifier approach, and (iii) the combination of the multilabel classification-based and the sentiment classification-based approach. Our best system produces F-scores of 0.67, 0.83, 0.72 and 0.7 for English, Spanish, French and Japanese, respectively. The results are competitive to the best ones for all languages and secure 3rd and 5th position for Japanese and French, respectively, among all submitted systems. |
| Tasks | Multi-Label Classification, Sentiment Analysis |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4027/ |
| https://www.aclweb.org/anthology/I17-4027 | |
| PWC | https://paperswithcode.com/paper/adapt-at-ijcnlp-2017-task-4-a-multinomial |
| Repo | |
| Framework | |
Protein Word Detection using Text Segmentation Techniques
| Title | Protein Word Detection using Text Segmentation Techniques |
| Authors | Devi Ganesan, Ashish V. Tendulkar, Sutanu Chakraborti |
| Abstract | Literature in Molecular Biology is abundant with linguistic metaphors. There have been works in the past that attempt to draw parallels between linguistics and biology, driven by the fundamental premise that proteins have a language of their own. Since word detection is crucial to the decipherment of any unknown language, we attempt to establish a problem mapping from natural language text to protein sequences at the level of words. Towards this end, we explore the use of an unsupervised text segmentation algorithm to the task of extracting {``}biological words{''} from protein sequences. In particular, we demonstrate the effectiveness of using domain knowledge to complement data driven approaches in the text segmentation task, as well as in its biological counterpart. We also propose a novel extrinsic evaluation measure for protein words through protein family classification. | |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2330/ |
| https://www.aclweb.org/anthology/W17-2330 | |
| PWC | https://paperswithcode.com/paper/protein-word-detection-using-text |
| Repo | |
| Framework | |
A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery
| Title | A Unified Variance Reduction-Based Framework for Nonconvex Low-Rank Matrix Recovery |
| Authors | Lingxiao Wang, Xiao Zhang, Quanquan Gu |
| Abstract | We propose a generic framework based on a new stochastic variance-reduced gradient descent algorithm for accelerating nonconvex low-rank matrix recovery. Starting from an appropriate initial estimator, our proposed algorithm performs projected gradient descent based on a novel semi-stochastic gradient specifically designed for low-rank matrix recovery. Based upon the mild restricted strong convexity and smoothness conditions, we derive a projected notion of the restricted Lipschitz continuous gradient property, and prove that our algorithm enjoys linear convergence rate to the unknown low-rank matrix with an improved computational complexity. Moreover, our algorithm can be employed to both noiseless and noisy observations, where the (near) optimal sample complexity and statistical rate can be attained respectively. We further illustrate the superiority of our generic framework through several specific examples, both theoretically and experimentally. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=624 |
| http://proceedings.mlr.press/v70/wang17n/wang17n.pdf | |
| PWC | https://paperswithcode.com/paper/a-unified-variance-reduction-based-framework |
| Repo | |
| Framework | |
Approximate Newton Methods and Their Local Convergence
| Title | Approximate Newton Methods and Their Local Convergence |
| Authors | Haishan Ye, Luo Luo, Zhihua Zhang |
| Abstract | Many machine learning models are reformulated as optimization problems. Thus, it is important to solve a large-scale optimization problem in big data applications. Recently, subsampled Newton methods have emerged to attract much attention for optimization due to their efficiency at each iteration, rectified a weakness in the ordinary Newton method of suffering a high cost in each iteration while commanding a high convergence rate. Other efficient stochastic second order methods are also proposed. However, the convergence properties of these methods are still not well understood. There are also several important gaps between the current convergence theory and performance in real applications. In this paper, we aim to fill these gaps. We propose a unifying framework to analyze local convergence properties of second order methods. Based on this framework, our theoretical analysis matches the performance in real applications. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=715 |
| http://proceedings.mlr.press/v70/ye17a/ye17a.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-newton-methods-and-their-local |
| Repo | |
| Framework | |
Predicting News Values from Headline Text and Emotions
| Title | Predicting News Values from Headline Text and Emotions |
| Authors | Maria Pia di Buono, Jan {\v{S}}najder, Bojana Dalbelo Ba{\v{s}}i{'c}, Goran Glava{\v{s}}, Martin Tutek, Natasa Milic-Frayling |
| Abstract | We present a preliminary study on predicting news values from headline text and emotions. We perform a multivariate analysis on a dataset manually annotated with news values and emotions, discovering interesting correlations among them. We then train two competitive machine learning models {–} an SVM and a CNN {–} to predict news values from headline text and emotions as features. We find that, while both models yield a satisfactory performance, some news values are more difficult to detect than others, while some profit more from including emotion information. |
| Tasks | Recommendation Systems |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4201/ |
| https://www.aclweb.org/anthology/W17-4201 | |
| PWC | https://paperswithcode.com/paper/predicting-news-values-from-headline-text-and |
| Repo | |
| Framework | |
Stance Classification of Context-Dependent Claims
| Title | Stance Classification of Context-Dependent Claims |
| Authors | Roy Bar-Haim, Indrajit Bhattacharya, Francesco Dinuzzo, Amrita Saha, Noam Slonim |
| Abstract | Recent work has addressed the problem of detecting relevant claims for a given controversial topic. We introduce the complementary task of Claim Stance Classification, along with the first benchmark dataset for this task. We decompose this problem into: (a) open-domain target identification for topic and claim (b) sentiment classification for each target, and (c) open-domain contrast detection between the topic and the claim targets. Manual annotation of the dataset confirms the applicability and validity of our model. We describe an implementation of our model, focusing on a novel algorithm for contrast detection. Our approach achieves promising results, and is shown to outperform several baselines, which represent the common practice of applying a single, monolithic classifier for stance classification. |
| Tasks | Sentiment Analysis |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/E17-1024/ |
| https://www.aclweb.org/anthology/E17-1024 | |
| PWC | https://paperswithcode.com/paper/stance-classification-of-context-dependent |
| Repo | |
| Framework | |
Inforex — a collaborative system for text corpora annotation and analysis
| Title | Inforex — a collaborative system for text corpora annotation and analysis |
| Authors | Micha{\l} Marci{'n}czuk, Marcin Oleksy, Jan Koco{'n} |
| Abstract | We report a first major upgrade of Inforex {—} a web-based system for qualitative and collaborative text corpora annotation and analysis. Inforex is a part of Polish CLARIN infrastructure. It is integrated with a digital repository for storing and publishing language resources and allows to visualize, browse and annotate text corpora stored in the repository. As a result of a series of workshops for researches from humanities and social sciences fields we improved the graphical interface to make the system more friendly and readable for non-experienced users. We also implemented a new functionality for gold standard annotation which includes private annotations and annotation agreement by a super-annotator. |
| Tasks | Named Entity Recognition, Word Sense Disambiguation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1063/ |
| https://doi.org/10.26615/978-954-452-049-6_063 | |
| PWC | https://paperswithcode.com/paper/inforex-a-a-collaborative-system-for-text |
| Repo | |
| Framework | |
IJCNLP-2017 Task 3: Review Opinion Diversification (RevOpiD-2017)
| Title | IJCNLP-2017 Task 3: Review Opinion Diversification (RevOpiD-2017) |
| Authors | Anil Kumar Singh, Avijit Thawani, Mayank Panchal, Anubhav Gupta, Julian McAuley |
| Abstract | Unlike Entity Disambiguation in web search results, Opinion Disambiguation is a relatively unexplored topic. RevOpiD shared task at IJCNLP-2107 aimed to attract attention towards this research problem. In this paper, we summarize the first run of this task and introduce a new dataset that we have annotated for the purpose of evaluating Opinion Mining, Summarization and Disambiguation methods. |
| Tasks | Document Ranking, Document Summarization, Entity Disambiguation, Information Retrieval, Opinion Mining |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/I17-4003/ |
| https://www.aclweb.org/anthology/I17-4003 | |
| PWC | https://paperswithcode.com/paper/ijcnlp-2017-task-3-review-opinion |
| Repo | |
| Framework | |
Neural Response Generation via GAN with an Approximate Embedding Layer
| Title | Neural Response Generation via GAN with an Approximate Embedding Layer |
| Authors | Zhen Xu, Bingquan Liu, Baoxun Wang, Chengjie Sun, Xiaolong Wang, Zhuoran Wang, Chao Qi |
| Abstract | This paper presents a Generative Adversarial Network (GAN) to model single-turn short-text conversations, which trains a sequence-to-sequence (Seq2Seq) network for response generation simultaneously with a discriminative classifier that measures the differences between human-produced responses and machine-generated ones. In addition, the proposed method introduces an approximate embedding layer to solve the non-differentiable problem caused by the sampling-based output decoding procedure in the Seq2Seq generative model. The GAN setup provides an effective way to avoid noninformative responses (a.k.a {``}safe responses{''}), which are frequently observed in traditional neural response generators. The experimental results show that the proposed approach significantly outperforms existing neural response generation models in diversity metrics, with slight increases in relevance scores as well, when evaluated on both a Mandarin corpus and an English corpus. | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1065/ |
| https://www.aclweb.org/anthology/D17-1065 | |
| PWC | https://paperswithcode.com/paper/neural-response-generation-via-gan-with-an |
| Repo | |
| Framework | |
