Paper Group NANR 177
Language-Independent Prediction of Psycholinguistic Properties of Words. Utilizing Visual Forms of Japanese Characters for Neural Review Classification. A Multi-task Learning Approach to Adapting Bilingual Word Embeddings for Cross-lingual Named Entity Recognition. Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences. f …
Language-Independent Prediction of Psycholinguistic Properties of Words
| Title | Language-Independent Prediction of Psycholinguistic Properties of Words |
| Authors | Yo Ehara |
| Abstract | The psycholinguistic properties of words, namely, word familiarity, age of acquisition, concreteness, and imagery, have been reported to be effective for educational natural language-processing tasks. Previous studies on predicting the values of these properties rely on language-dependent features. This paper is the first to propose a practical language-independent method for predicting such values by using only a large raw corpus in a language. Through experiments, our method successfully predicted the values of these properties in two languages. The results for English were competitive with the reported accuracy achieved using features specific to English. |
| Tasks | Lexical Simplification |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2056/ |
| https://www.aclweb.org/anthology/I17-2056 | |
| PWC | https://paperswithcode.com/paper/language-independent-prediction-of |
| Repo | |
| Framework | |
Utilizing Visual Forms of Japanese Characters for Neural Review Classification
| Title | Utilizing Visual Forms of Japanese Characters for Neural Review Classification |
| Authors | Yota Toyama, Makoto Miwa, Yutaka Sasaki |
| Abstract | We propose a novel method that exploits visual information of ideograms and logograms in analyzing Japanese review documents. Our method first converts font images of Japanese characters into character embeddings using convolutional neural networks. It then constructs document embeddings from the character embeddings based on Hierarchical Attention Networks, which represent the documents based on attention mechanisms from a character level to a sentence level. The document embeddings are finally used to predict the labels of documents. Our method provides a way to exploit visual features of characters in languages with ideograms and logograms. In the experiments, our method achieved an accuracy comparable to a character embedding-based model while our method has much fewer parameters since it does not need to keep embeddings of thousands of characters. |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2064/ |
| https://www.aclweb.org/anthology/I17-2064 | |
| PWC | https://paperswithcode.com/paper/utilizing-visual-forms-of-japanese-characters |
| Repo | |
| Framework | |
A Multi-task Learning Approach to Adapting Bilingual Word Embeddings for Cross-lingual Named Entity Recognition
| Title | A Multi-task Learning Approach to Adapting Bilingual Word Embeddings for Cross-lingual Named Entity Recognition |
| Authors | Dingquan Wang, Nanyun Peng, Kevin Duh |
| Abstract | We show how to adapt bilingual word embeddings (BWE{'}s) to bootstrap a cross-lingual name-entity recognition (NER) system in a language with no labeled data. We assume a setting where we are given a comparable corpus with NER labels for the source language only; our goal is to build a NER model for the target language. The proposed multi-task model jointly trains bilingual word embeddings while optimizing a NER objective. This creates word embeddings that are both shared between languages and fine-tuned for the NER task. |
| Tasks | Cross-Lingual Transfer, Multi-Task Learning, Named Entity Recognition, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2065/ |
| https://www.aclweb.org/anthology/I17-2065 | |
| PWC | https://paperswithcode.com/paper/a-multi-task-learning-approach-to-adapting |
| Repo | |
| Framework | |
Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences
| Title | Extracting and Understanding Contrastive Opinion through Topic Relevant Sentences |
| Authors | Ebuka Ibeke, Chenghua Lin, Adam Wyner, Mohamad Hardyman Barawi |
| Abstract | Contrastive opinion mining is essential in identifying, extracting and organising opinions from user generated texts. Most existing studies separate input data into respective collections. In addition, the relationships between the topics extracted and the sentences in the corpus which express the topics are opaque, hindering our understanding of the opinions expressed in the corpus. We propose a novel unified latent variable model (contraLDA) which addresses the above matters. Experimental results show the effectiveness of our model in mining contrasted opinions, outperforming our baselines. |
| Tasks | Opinion Mining |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2067/ |
| https://www.aclweb.org/anthology/I17-2067 | |
| PWC | https://paperswithcode.com/paper/extracting-and-understanding-contrastive |
| Repo | |
| Framework | |
funSentiment at SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs Using Word Vectors Built from StockTwits and Twitter
| Title | funSentiment at SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs Using Word Vectors Built from StockTwits and Twitter |
| Authors | Quanzhi Li, Sameena Shah, Armineh Nourbakhsh, Rui Fang, Xiaomo Liu |
| Abstract | This paper describes the approach we used for SemEval-2017 Task 5: Fine-Grained Sentiment Analysis on Financial Microblogs. We use three types of word embeddings in our algorithm: word embeddings learned from 200 million tweets, sentiment-specific word embeddings learned from 10 million tweets using distance supervision, and word embeddings learned from 20 million StockTwits messages. In our approach, we also take the left and right context of the target company into consideration when generating polarity prediction features. All the features generated from different word embeddings and contexts are integrated together to train our algorithm |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2145/ |
| https://www.aclweb.org/anthology/S17-2145 | |
| PWC | https://paperswithcode.com/paper/funsentiment-at-semeval-2017-task-5-fine |
| Repo | |
| Framework | |
Local Bayesian Optimization of Motor Skills
| Title | Local Bayesian Optimization of Motor Skills |
| Authors | Riad Akrour, Dmitry Sorokin, Jan Peters, Gerhard Neumann |
| Abstract | Bayesian optimization is renowned for its sample efficiency but its application to higher dimensional tasks is impeded by its focus on global optimization. To scale to higher dimensional problems, we leverage the sample efficiency of Bayesian optimization in a local context. The optimization of the acquisition function is restricted to the vicinity of a Gaussian search distribution which is moved towards high value areas of the objective. The proposed information-theoretic update of the search distribution results in a Bayesian interpretation of local stochastic search: the search distribution encodes prior knowledge on the optimum’s location and is weighted at each iteration by the likelihood of this location’s optimality. We demonstrate the effectiveness of our algorithm on several benchmark objective functions as well as a continuous robotic task in which an informative prior is obtained by imitation learning. |
| Tasks | Imitation Learning |
| Published | 2017-08-01 |
| URL | https://icml.cc/Conferences/2017/Schedule?showEvent=748 |
| http://proceedings.mlr.press/v70/akrour17a/akrour17a.pdf | |
| PWC | https://paperswithcode.com/paper/local-bayesian-optimization-of-motor-skills |
| Repo | |
| Framework | |
Generating Stylistically Consistent Dialog Responses with Transfer Learning
| Title | Generating Stylistically Consistent Dialog Responses with Transfer Learning |
| Authors | Reina Akama, Kazuaki Inada, Naoya Inoue, Sosuke Kobayashi, Kentaro Inui |
| Abstract | We propose a novel, data-driven, and stylistically consistent dialog response generation system. To create a user-friendly system, it is crucial to make generated responses not only appropriate but also stylistically consistent. For leaning both the properties effectively, our proposed framework has two training stages inspired by transfer learning. First, we train the model to generate appropriate responses, and then we ensure that the responses have a specific style. Experimental results demonstrate that the proposed method produces stylistically consistent responses while maintaining the appropriateness of the responses learned in a general domain. |
| Tasks | Transfer Learning |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2069/ |
| https://www.aclweb.org/anthology/I17-2069 | |
| PWC | https://paperswithcode.com/paper/generating-stylistically-consistent-dialog |
| Repo | |
| Framework | |
Domain Adaptation for Relation Extraction with Domain Adversarial Neural Network
| Title | Domain Adaptation for Relation Extraction with Domain Adversarial Neural Network |
| Authors | Lisheng Fu, Thien Huu Nguyen, Bonan Min, Ralph Grishman |
| Abstract | Relations are expressed in many domains such as newswire, weblogs and phone conversations. Trained on a source domain, a relation extractor{'}s performance degrades when applied to target domains other than the source. A common yet labor-intensive method for domain adaptation is to construct a target-domain-specific labeled dataset for adapting the extractor. In response, we present an unsupervised domain adaptation method which only requires labels from the source domain. Our method is a joint model consisting of a CNN-based relation classifier and a domain-adversarial classifier. The two components are optimized jointly to learn a domain-independent representation for prediction on the target domain. Our model outperforms the state-of-the-art on all three test domains of ACE 2005. |
| Tasks | Domain Adaptation, Relation Extraction, Unsupervised Domain Adaptation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2072/ |
| https://www.aclweb.org/anthology/I17-2072 | |
| PWC | https://paperswithcode.com/paper/domain-adaptation-for-relation-extraction |
| Repo | |
| Framework | |
Proofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction
| Title | Proofread Sentence Generation as Multi-Task Learning with Editing Operation Prediction |
| Authors | Yuta Hitomi, Hideaki Tamori, Naoaki Okazaki, Kentaro Inui |
| Abstract | This paper explores the idea of robot editors, automated proofreaders that enable journalists to improve the quality of their articles. We propose a novel neural model of multi-task learning that both generates proofread sentences and predicts the editing operations required to rewrite the source sentences and create the proofread ones. The model is trained using logs of the revisions made professional editors revising draft newspaper articles written by journalists. Experiments demonstrate the effectiveness of our multi-task learning approach and the potential value of using revision logs for this task. |
| Tasks | Grammatical Error Correction, Multi-Task Learning |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2074/ |
| https://www.aclweb.org/anthology/I17-2074 | |
| PWC | https://paperswithcode.com/paper/proofread-sentence-generation-as-multi-task |
| Repo | |
| Framework | |
Proceedings of the IJCNLP 2017, System Demonstrations
| Title | Proceedings of the IJCNLP 2017, System Demonstrations |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3000/ |
| https://www.aclweb.org/anthology/I17-3000 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-ijcnlp-2017-system |
| Repo | |
| Framework | |
CADET: Computer Assisted Discovery Extraction and Translation
| Title | CADET: Computer Assisted Discovery Extraction and Translation |
| Authors | Benjamin Van Durme, Tom Lippincott, Kevin Duh, Deana Burchfield, Adam Poliak, Cash Costello, Tim Finin, Scott Miller, James Mayfield, Philipp Koehn, Craig Harman, Dawn Lawrie, Ch May, ler, Max Thomas, Annabelle Carrell, Julianne Chaloux, Tongfei Chen, Alex Comerford, Mark Dredze, Benjamin Glass, Shudong Hao, Patrick Martin, Pushpendre Rastogi, Rashmi Sankepally, Travis Wolfe, Ying-Ying Tran, Ted Zhang |
| Abstract | Computer Assisted Discovery Extraction and Translation (CADET) is a workbench for helping knowledge workers find, label, and translate documents of interest. It combines a multitude of analytics together with a flexible environment for customizing the workflow for different users. This open-source framework allows for easy development of new research prototypes using a micro-service architecture based atop Docker and Apache Thrift. |
| Tasks | Active Learning, Machine Translation |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3002/ |
| https://www.aclweb.org/anthology/I17-3002 | |
| PWC | https://paperswithcode.com/paper/cadet-computer-assisted-discovery-extraction |
| Repo | |
| Framework | |
A Telecom-Domain Online Customer Service Assistant Based on Question Answering with Word Embedding and Intent Classification
| Title | A Telecom-Domain Online Customer Service Assistant Based on Question Answering with Word Embedding and Intent Classification |
| Authors | Jui-Yang Wang, Min-Feng Kuo, Jen-Chieh Han, Chao-Chuang Shih, Chun-Hsun Chen, Po-Ching Lee, Richard Tzong-Han Tsai |
| Abstract | In the paper, we propose an information retrieval based (IR-based) Question Answering (QA) system to assist online customer service staffs respond users in the telecom domain. When user asks a question, the system retrieves a set of relevant answers and ranks them. Moreover, our system uses a novel reranker to enhance the ranking result of information retrieval.It employs the word2vec model to represent the sentences as vectors. It also uses a sub-category feature, predicted by the k-nearest neighbor algorithm. Finally, the system returns the top five candidate answers, making online staffs find answers much more efficiently. |
| Tasks | Information Retrieval, Intent Classification, Question Answering |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3005/ |
| https://www.aclweb.org/anthology/I17-3005 | |
| PWC | https://paperswithcode.com/paper/a-telecom-domain-online-customer-service |
| Repo | |
| Framework | |
Double Trouble: The Problem of Construal in Semantic Annotation of Adpositions
| Title | Double Trouble: The Problem of Construal in Semantic Annotation of Adpositions |
| Authors | Jena D. Hwang, Archna Bhatia, Na-Rae Han, Tim O{'}Gorman, Vivek Srikumar, Nathan Schneider |
| Abstract | We consider the semantics of prepositions, revisiting a broad-coverage annotation scheme used for annotating all 4,250 preposition tokens in a 55,000 word corpus of English. Attempts to apply the scheme to adpositions and case markers in other languages, as well as some problematic cases in English, have led us to reconsider the assumption that an adposition{'}s lexical contribution is equivalent to the role/relation that it mediates. Our proposal is to embrace the potential for construal in adposition use, expressing such phenomena directly at the token level to manage complexity and avoid sense proliferation. We suggest a framework to represent both the scene role and the adposition{'}s lexical function so they can be annotated at scale{—}supporting automatic, statistical processing of domain-general language{—}and discuss how this representation would allow for a simpler inventory of labels. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-1022/ |
| https://www.aclweb.org/anthology/S17-1022 | |
| PWC | https://paperswithcode.com/paper/double-trouble-the-problem-of-construal-in |
| Repo | |
| Framework | |
XMU Neural Machine Translation Online Service
| Title | XMU Neural Machine Translation Online Service |
| Authors | Boli Wang, Zhixing Tan, Jinming Hu, Yidong Chen, Xiaodong Shi |
| Abstract | We demonstrate a neural machine translation web service. Our NMT service provides web-based translation interfaces for a variety of language pairs. We describe the architecture of NMT runtime pipeline and the training details of NMT models. We also show several applications of our online translation interfaces. |
| Tasks | Machine Translation, Tokenization |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-3008/ |
| https://www.aclweb.org/anthology/I17-3008 | |
| PWC | https://paperswithcode.com/paper/xmu-neural-machine-translation-online-service |
| Repo | |
| Framework | |
Why ADAGRAD Fails for Online Topic Modeling
| Title | Why ADAGRAD Fails for Online Topic Modeling |
| Authors | You Lu, Jeffrey Lund, Jordan Boyd-Graber |
| Abstract | Online topic modeling, i.e., topic modeling with stochastic variational inference, is a powerful and efficient technique for analyzing large datasets, and ADAGRAD is a widely-used technique for tuning learning rates during online gradient optimization. However, these two techniques do not work well together. We show that this is because ADAGRAD uses accumulation of previous gradients as the learning rates{'} denominators. For online topic modeling, the magnitude of gradients is very large. It causes learning rates to shrink very quickly, so the parameters cannot fully converge until the training ends |
| Tasks | Topic Models |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1046/ |
| https://www.aclweb.org/anthology/D17-1046 | |
| PWC | https://paperswithcode.com/paper/why-adagrad-fails-for-online-topic-modeling |
| Repo | |
| Framework | |
