Paper Group NANR 147
Detecting Grammatical Errors in the NTOU CGED System by Identifying Frequent Subsentences. Toward a Lightweight Solution for Less-resourced Languages: Creating a POS Tagger for Alsatian Using Voluntary Crowdsourcing. Word Sense Disambiguation Based on Word Similarity Calculation Using Word Vector Representation from a Knowledge-based Graph. Evaluat …
Detecting Grammatical Errors in the NTOU CGED System by Identifying Frequent Subsentences
| Title | Detecting Grammatical Errors in the NTOU CGED System by Identifying Frequent Subsentences |
| Authors | Chuan-Jie Lin, Shao-Heng Chen |
| Abstract | The main goal of Chinese grammatical error diagnosis task is to detect word er-rors in the sentences written by Chinese-learning students. Our previous system would generate error-corrected sentences as candidates and their sentence likeli-hood were measured based on a large scale Chinese n-gram dataset. This year we further tried to identify long frequent-ly-seen subsentences and label them as correct in order to avoid propose too many error candidates. Two new methods for suggesting missing and selection er-rors were also tested. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3730/ |
| https://www.aclweb.org/anthology/W18-3730 | |
| PWC | https://paperswithcode.com/paper/detecting-grammatical-errors-in-the-ntou-cged |
| Repo | |
| Framework | |
Toward a Lightweight Solution for Less-resourced Languages: Creating a POS Tagger for Alsatian Using Voluntary Crowdsourcing
| Title | Toward a Lightweight Solution for Less-resourced Languages: Creating a POS Tagger for Alsatian Using Voluntary Crowdsourcing |
| Authors | Alice Millour, Kar{"e}n Fort |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1071/ |
| https://www.aclweb.org/anthology/L18-1071 | |
| PWC | https://paperswithcode.com/paper/toward-a-lightweight-solution-for-less |
| Repo | |
| Framework | |
Word Sense Disambiguation Based on Word Similarity Calculation Using Word Vector Representation from a Knowledge-based Graph
| Title | Word Sense Disambiguation Based on Word Similarity Calculation Using Word Vector Representation from a Knowledge-based Graph |
| Authors | Dongsuk O, Sunjae Kwon, Kyungsun Kim, Youngjoong Ko |
| Abstract | Word sense disambiguation (WSD) is the task to determine the word sense according to its context. Many existing WSD studies have been using an external knowledge-based unsupervised approach because it has fewer word set constraints than supervised approaches requiring training data. In this paper, we propose a new WSD method to generate the context of an ambiguous word by using similarities between an ambiguous word and words in the input document. In addition, to leverage our WSD method, we further propose a new word similarity calculation method based on the semantic network structure of BabelNet. We evaluate the proposed methods on the SemEval-13 and SemEval-15 for English WSD dataset. Experimental results demonstrate that the proposed WSD method significantly improves the baseline WSD method. Furthermore, our WSD system outperforms the state-of-the-art WSD systems in the Semeval-13 dataset. Finally, it has higher performance than the state-of-the-art unsupervised knowledge-based WSD system in the average performance of both datasets. |
| Tasks | Information Retrieval, Machine Translation, Word Sense Disambiguation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1229/ |
| https://www.aclweb.org/anthology/C18-1229 | |
| PWC | https://paperswithcode.com/paper/word-sense-disambiguation-based-on-word |
| Repo | |
| Framework | |
Evaluating Automatic Speech Recognition in Translation
| Title | Evaluating Automatic Speech Recognition in Translation |
| Authors | Evelyne Tzoukermann, Corey Miller |
| Abstract | |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1922/ |
| https://www.aclweb.org/anthology/W18-1922 | |
| PWC | https://paperswithcode.com/paper/evaluating-automatic-speech-recognition-in |
| Repo | |
| Framework | |
Narrative Schema Stability in News Text
| Title | Narrative Schema Stability in News Text |
| Authors | Dan Simonson, Anthony Davis |
| Abstract | We investigate the stability of narrative schemas (Chambers and Jurafsky, 2009) automatically induced from a news corpus, representing recurring narratives in a corpus. If such techniques produce meaningful results, we should expect that small changes to the corpus will result in only small changes to the induced schemas. We describe experiments involving successive ablation of a corpus and cross-validation at each stage of ablation, on schemas generated by three different techniques over a general news corpus and topically-specific subcorpora. We also develop a method for evaluating the similarity between sets of narrative schemas, and thus the stability of the schema induction algorithms. This stability analysis affirms the heterogeneous/homogeneous document category hypothesis first presented in Simonson and Davis (2016), whose technique is problematically limited. Additionally, increased ablation leads to increasing stability, so the smaller the remaining corpus, the more stable schema generation appears to be. We surmise that as a corpus grows larger, novel and more varied narratives continue to appear and stability declines, though at some point this decline levels off as new additions to the corpus consist essentially of {``}more of the same.{''} | |
| Tasks | Topic Models |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1311/ |
| https://www.aclweb.org/anthology/C18-1311 | |
| PWC | https://paperswithcode.com/paper/narrative-schema-stability-in-news-text |
| Repo | |
| Framework | |
Proximal SCOPE for Distributed Sparse Learning
| Title | Proximal SCOPE for Distributed Sparse Learning |
| Authors | Shenyi Zhao, Gong-Duo Zhang, Ming-Wei Li, Wu-Jun Li |
| Abstract | Distributed sparse learning with a cluster of multiple machines has attracted much attention in machine learning, especially for large-scale applications with high-dimensional data. One popular way to implement sparse learning is to use L1 regularization. In this paper, we propose a novel method, called proximal SCOPE (pSCOPE), for distributed sparse learning with L1 regularization. pSCOPE is based on a cooperative autonomous local learning (CALL) framework. In the CALL framework of pSCOPE, we find that the data partition affects the convergence of the learning procedure, and subsequently we define a metric to measure the goodness of a data partition. Based on the defined metric, we theoretically prove that pSCOPE is convergent with a linear convergence rate if the data partition is good enough. We also prove that better data partition implies faster convergence rate. Furthermore, pSCOPE is also communication efficient. Experimental results on real data sets show that pSCOPE can outperform other state-of-the-art distributed methods for sparse learning. |
| Tasks | Sparse Learning |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7890-proximal-scope-for-distributed-sparse-learning |
| http://papers.nips.cc/paper/7890-proximal-scope-for-distributed-sparse-learning.pdf | |
| PWC | https://paperswithcode.com/paper/proximal-scope-for-distributed-sparse-1 |
| Repo | |
| Framework | |
An Initial Test Collection for Ranked Retrieval of SMS Conversations
| Title | An Initial Test Collection for Ranked Retrieval of SMS Conversations |
| Authors | Rashmi Sankepally, Douglas W. Oard |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1328/ |
| https://www.aclweb.org/anthology/L18-1328 | |
| PWC | https://paperswithcode.com/paper/an-initial-test-collection-for-ranked |
| Repo | |
| Framework | |
Neural Dialogue Context Online End-of-Turn Detection
| Title | Neural Dialogue Context Online End-of-Turn Detection |
| Authors | Ryo Masumura, Tomohiro Tanaka, Atsushi Ando, Ryo Ishii, Ryuichiro Higashinaka, Yushi Aono |
| Abstract | This paper proposes a fully neural network based dialogue-context online end-of-turn detection method that can utilize long-range interactive information extracted from both speaker{'}s utterances and collocutor{'}s utterances. The proposed method combines multiple time-asynchronous long short-term memory recurrent neural networks, which can capture speaker{'}s and collocutor{'}s multiple sequential features, and their interactions. On the assumption of applying the proposed method to spoken dialogue systems, we introduce speaker{'}s acoustic sequential features and collocutor{'}s linguistic sequential features, each of which can be extracted in an online manner. Our evaluation confirms the effectiveness of taking dialogue context formed by the speaker{'}s utterances and collocutor{'}s utterances into consideration. |
| Tasks | Action Detection, Spoken Dialogue Systems |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5024/ |
| https://www.aclweb.org/anthology/W18-5024 | |
| PWC | https://paperswithcode.com/paper/neural-dialogue-context-online-end-of-turn |
| Repo | |
| Framework | |
Interpolating Convolutional Neural Networks Using Batch Normalization
| Title | Interpolating Convolutional Neural Networks Using Batch Normalization |
| Authors | Gratianus Wesley Putra Data, Kirjon Ngu, David William Murray, Victor Adrian Prisacariu |
| Abstract | Perceiving a visual concept as a mixture of learned ones is natural for humans, aiding them to grasp new concepts and strengthening old ones. For all their power and recent success, deep convolutional networks do not have this ability. Inspired by recent work on universal representations for neural networks, we propose a simple emulation of this mechanism by purposing batch normalization layers to discriminate visual classes, and formulating a way to combine them to solve new tasks. We show that this can be applied for 2-way few-shot learning where we obtain between 4% and 17% better accuracy compared to straightforward full fine-tuning, and demonstrate that it can also be extended to the orthogonal application of style transfer. |
| Tasks | Few-Shot Learning, Style Transfer |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Gratianus_Wesley_Putra_Data_Interpolating_Convolutional_Neural_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Gratianus_Wesley_Putra_Data_Interpolating_Convolutional_Neural_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/interpolating-convolutional-neural-networks |
| Repo | |
| Framework | |
Learning from discriminative feature feedback
| Title | Learning from discriminative feature feedback |
| Authors | Sanjoy Dasgupta, Akansha Dey, Nicholas Roberts, Sivan Sabato |
| Abstract | We consider the problem of learning a multi-class classifier from labels as well as simple explanations that we call “discriminative features”. We show that such explanations can be provided whenever the target concept is a decision tree, or more generally belongs to a particular subclass of DNF formulas. We present an efficient online algorithm for learning from such feedback and we give tight bounds on the number of mistakes made during the learning process. These bounds depend only on the size of the target concept and not on the overall number of available features, which could be infinite. We also demonstrate the learning procedure experimentally. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7651-learning-from-discriminative-feature-feedback |
| http://papers.nips.cc/paper/7651-learning-from-discriminative-feature-feedback.pdf | |
| PWC | https://paperswithcode.com/paper/learning-from-discriminative-feature-feedback |
| Repo | |
| Framework | |
One-Shot Action Localization by Learning Sequence Matching Network
| Title | One-Shot Action Localization by Learning Sequence Matching Network |
| Authors | Hongtao Yang, Xuming He, Fatih Porikli |
| Abstract | Learning based temporal action localization methods require vast amounts of training data. However, such large-scale video datasets, which are expected to capture the dynamics of every action category, are not only very expensive to acquire but are also not practical simply because there exists an uncountable number of action classes. This poses a critical restriction to the current methods when the training samples are few and rare (e.g. when the target action classes are not present in the current publicly available datasets). To address this challenge, we conceptualize a new example-based action detection problem where only a few examples are provided, and the goal is to find the occurrences of these examples in an untrimmed video sequence. Towards this objective, we introduce a novel one-shot action localization method that alleviates the need for large amounts of training samples. Our solution adopts the one-shot learning technique of Matching Network and utilizes correlations to mine and localize actions of previously unseen classes. We evaluate our one-shot action localization method on the THUMOS14 and ActivityNet datasets, of which we modified the configuration to fit our one-shot problem setup. |
| Tasks | Action Detection, Action Localization, One-Shot Learning, Temporal Action Localization |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Yang_One-Shot_Action_Localization_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Yang_One-Shot_Action_Localization_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/one-shot-action-localization-by-learning |
| Repo | |
| Framework | |
Discovering the Language of Wine Reviews: A Text Mining Account
| Title | Discovering the Language of Wine Reviews: A Text Mining Account |
| Authors | Els Lefever, Iris Hendrickx, Ilja Croijmans, Antal van den Bosch, Asifa Majid |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1521/ |
| https://www.aclweb.org/anthology/L18-1521 | |
| PWC | https://paperswithcode.com/paper/discovering-the-language-of-wine-reviews-a |
| Repo | |
| Framework | |
Don’t Annotate, but Validate: a Data-to-Text Method for Capturing Event Data
| Title | Don’t Annotate, but Validate: a Data-to-Text Method for Capturing Event Data |
| Authors | Piek Vossen, Filip Ilievski, Marten Postma, Roxane Segers |
| Abstract | |
| Tasks | Semantic Parsing |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1480/ |
| https://www.aclweb.org/anthology/L18-1480 | |
| PWC | https://paperswithcode.com/paper/dont-annotate-but-validate-a-data-to-text |
| Repo | |
| Framework | |
Joint Learning from Labeled and Unlabeled Data for Information Retrieval
| Title | Joint Learning from Labeled and Unlabeled Data for Information Retrieval |
| Authors | Bo Li, Ping Cheng, Le Jia |
| Abstract | Recently, a significant number of studies have focused on neural information retrieval (IR) models. One category of works use unlabeled data to train general word embeddings based on term proximity, which can be integrated into traditional IR models. The other category employs labeled data (e.g. click-through data) to train end-to-end neural IR models consisting of layers for target-specific representation learning. The latter idea accounts better for the IR task and is favored by recent research works, which is the one we will follow in this paper. We hypothesize that general semantics learned from unlabeled data can complement task-specific representation learned from labeled data of limited quality, and that a combination of the two is favorable. To this end, we propose a learning framework which can benefit from both labeled and more abundant unlabeled data for representation learning in the context of IR. Through a joint learning fashion in a single neural framework, the learned representation is optimized to minimize both the supervised loss on query-document matching and the unsupervised loss on text reconstruction. Standard retrieval experiments on TREC collections indicate that the joint learning methodology leads to significant better performance of retrieval over several strong baselines for IR. |
| Tasks | Information Retrieval, Representation Learning, Speech Recognition, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1025/ |
| https://www.aclweb.org/anthology/C18-1025 | |
| PWC | https://paperswithcode.com/paper/joint-learning-from-labeled-and-unlabeled |
| Repo | |
| Framework | |
Learning Domain Representation for Multi-Domain Sentiment Classification
| Title | Learning Domain Representation for Multi-Domain Sentiment Classification |
| Authors | Qi Liu, Yue Zhang, Jiangming Liu |
| Abstract | Training data for sentiment analysis are abundant in multiple domains, yet scarce for other domains. It is useful to leveraging data available for all existing domains to enhance performance on different domains. We investigate this problem by learning domain-specific representations of input sentences using neural network. In particular, a descriptor vector is learned for representing each domain, which is used to map adversarially trained domain-general Bi-LSTM input representations into domain-specific representations. Based on this model, we further expand the input representation with exemplary domain knowledge, collected by attending over a memory network of domain training data. Results show that our model outperforms existing methods on multi-domain sentiment analysis significantly, giving the best accuracies on two different benchmarks. |
| Tasks | Multi-Task Learning, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1050/ |
| https://www.aclweb.org/anthology/N18-1050 | |
| PWC | https://paperswithcode.com/paper/learning-domain-representation-for-multi |
| Repo | |
| Framework | |
