Paper Group NANR 137
E2E NLG Challenge Submission: Towards Controllable Generation of Diverse Natural Language. An Attribute Enhanced Domain Adaptive Model for Cold-Start Spam Review Detection. The Role of Syntax During Pronoun Resolution: Evidence from fMRI. Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP. Predictin …
E2E NLG Challenge Submission: Towards Controllable Generation of Diverse Natural Language
| Title | E2E NLG Challenge Submission: Towards Controllable Generation of Diverse Natural Language |
| Authors | Henry Elder, Sebastian Gehrmann, Alex O{'}Connor, er, Qun Liu |
| Abstract | In natural language generation (NLG), the task is to generate utterances from a more abstract input, such as structured data. An added challenge is to generate utterances that contain an accurate representation of the input, while reflecting the fluency and variety of human-generated text. In this paper, we report experiments with NLG models that can be used in task oriented dialogue systems. We explore the use of additional input to the model to encourage diversity and control of outputs. While our submission does not rank highly using automated metrics, qualitative investigation of generated utterances suggests the use of additional information in neural network NLG systems to be a promising research direction. |
| Tasks | Machine Translation, Task-Oriented Dialogue Systems, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6556/ |
| https://www.aclweb.org/anthology/W18-6556 | |
| PWC | https://paperswithcode.com/paper/e2e-nlg-challenge-submission-towards |
| Repo | |
| Framework | |
An Attribute Enhanced Domain Adaptive Model for Cold-Start Spam Review Detection
| Title | An Attribute Enhanced Domain Adaptive Model for Cold-Start Spam Review Detection |
| Authors | Zhenni You, Tieyun Qian, Bing Liu |
| Abstract | Spam detection has long been a research topic in both academic and industry due to its wide applications. Previous studies are mainly focused on extracting linguistic or behavior features to distinguish the spam and legitimate reviews. Such features are either ineffective or take long time to collect and thus are hard to be applied to cold-start spam review detection tasks. Recent advance leveraged the neural network to encode the textual and behavior features for the cold-start problem. However, the abundant attribute information are largely neglected by the existing framework. In this paper, we propose a novel deep learning architecture for incorporating entities and their inherent attributes from various domains into a unified framework. Specifically, our model not only encodes the entities of reviewer, item, and review, but also their attributes such as location, date, price ranges. Furthermore, we present a domain classifier to adapt the knowledge from one domain to the other. With the abundant attributes in existing entities and knowledge in other domains, we successfully solve the problem of data scarcity in the cold-start settings. Experimental results on two Yelp datasets prove that our proposed framework significantly outperforms the state-of-the-art methods. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1160/ |
| https://www.aclweb.org/anthology/C18-1160 | |
| PWC | https://paperswithcode.com/paper/an-attribute-enhanced-domain-adaptive-model |
| Repo | |
| Framework | |
The Role of Syntax During Pronoun Resolution: Evidence from fMRI
| Title | The Role of Syntax During Pronoun Resolution: Evidence from fMRI |
| Authors | Jixing Li, Murielle Fabre, Wen-Ming Luh, John Hale |
| Abstract | The current study examined the role of syntactic structure during pronoun resolution. We correlated complexity measures derived by the syntax-sensitive Hobbs algorithm and a neural network model for pronoun resolution with brain activity of participants listening to an audiobook during fMRI recording. Compared to the neural network model, the Hobbs algorithm is associated with larger clusters of brain activation in a network including the left Broca{'}s area. |
| Tasks | Coreference Resolution |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2808/ |
| https://www.aclweb.org/anthology/W18-2808 | |
| PWC | https://paperswithcode.com/paper/the-role-of-syntax-during-pronoun-resolution |
| Repo | |
| Framework | |
Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP
| Title | Proceedings of the Workshop on the Relevance of Linguistic Structure in Neural Architectures for NLP |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2900/ |
| https://www.aclweb.org/anthology/W18-2900 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-workshop-on-the-relevance |
| Repo | |
| Framework | |
Predicting Perceived Age: Both Language Ability and Appearance are Important
| Title | Predicting Perceived Age: Both Language Ability and Appearance are Important |
| Authors | Sarah Plane, Ariel Marvasti, Tyler Egan, Casey Kennington |
| Abstract | When interacting with robots in a situated spoken dialogue setting, human dialogue partners tend to assign anthropomorphic and social characteristics to those robots. In this paper, we explore the age and educational level that human dialogue partners assign to three different robotic systems, including an un-embodied spoken dialogue system. We found that how a robot speaks is as important to human perceptions as the way the robot looks. Using the data from our experiment, we derived prosodic, emotional, and linguistic features from the participants to train and evaluate a classifier that predicts perceived intelligence, age, and education level. |
| Tasks | Language Acquisition |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-5014/ |
| https://www.aclweb.org/anthology/W18-5014 | |
| PWC | https://paperswithcode.com/paper/predicting-perceived-age-both-language |
| Repo | |
| Framework | |
A Pseudo Label based Dataless Naive Bayes Algorithm for Text Classification with Seed Words
| Title | A Pseudo Label based Dataless Naive Bayes Algorithm for Text Classification with Seed Words |
| Authors | Ximing Li, Bo Yang |
| Abstract | Traditional supervised text classifiers require a large number of manually labeled documents, which are often expensive to obtain. Recently, dataless text classification has attracted more attention, since it only requires very few seed words of categories that are much cheaper. In this paper, we develop a pseudo-label based dataless Naive Bayes (PL-DNB) classifier with seed words. We initialize pseudo-labels for each document using seed word occurrences, and employ the expectation maximization algorithm to train PL-DNB in a semi-supervised manner. The pseudo-labels are iteratively updated using a mixture of seed word occurrences and estimations of label posteriors. To avoid noisy pseudo-labels, we also consider the information of nearest neighboring documents in the pseudo-label update step, i.e., preserving local neighborhood structure of documents. We empirically show that PL-DNB outperforms traditional dataless text classification algorithms with seed words. Especially, PL-DNB performs well on the imbalanced dataset. |
| Tasks | Text Classification |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1162/ |
| https://www.aclweb.org/anthology/C18-1162 | |
| PWC | https://paperswithcode.com/paper/a-pseudo-label-based-dataless-naive-bayes |
| Repo | |
| Framework | |
PROMT Systems for WMT 2018 Shared Translation Task
| Title | PROMT Systems for WMT 2018 Shared Translation Task |
| Authors | Alex Molchanov, er |
| Abstract | This paper describes the PROMT submissions for the WMT 2018 Shared News Translation Task. This year we participated only in the English-Russian language pair. We built two primary neural networks-based systems: 1) a pure Marian-based neural system and 2) a hybrid system which incorporates OpenNMT-based neural post-editing component into our RBMT engine. We also submitted pure rule-based translation (RBMT) for contrast. We show competitive results with both primary submissions which significantly outperform the RBMT baseline. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6420/ |
| https://www.aclweb.org/anthology/W18-6420 | |
| PWC | https://paperswithcode.com/paper/promt-systems-for-wmt-2018-shared-translation |
| Repo | |
| Framework | |
Visual Question Answering Dataset for Bilingual Image Understanding: A Study of Cross-Lingual Transfer Using Attention Maps
| Title | Visual Question Answering Dataset for Bilingual Image Understanding: A Study of Cross-Lingual Transfer Using Attention Maps |
| Authors | Nobuyuki Shimizu, Na Rong, Takashi Miyazaki |
| Abstract | Visual question answering (VQA) is a challenging task that requires a computer system to understand both a question and an image. While there is much research on VQA in English, there is a lack of datasets for other languages, and English annotation is not directly applicable in those languages. To deal with this, we have created a Japanese VQA dataset by using crowdsourced annotation with images from the Visual Genome dataset. This is the first such dataset in Japanese. As another contribution, we propose a cross-lingual method for making use of English annotation to improve a Japanese VQA system. The proposed method is based on a popular VQA method that uses an attention mechanism. We use attention maps generated from English questions to help improve the Japanese VQA task. The proposed method experimentally performed better than simply using a monolingual corpus, which demonstrates the effectiveness of using attention maps to transfer cross-lingual information. |
| Tasks | Cross-Lingual Transfer, Image Captioning, Question Answering, Visual Question Answering |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1163/ |
| https://www.aclweb.org/anthology/C18-1163 | |
| PWC | https://paperswithcode.com/paper/visual-question-answering-dataset-for |
| Repo | |
| Framework | |
Scalable Hyperparameter Transfer Learning
| Title | Scalable Hyperparameter Transfer Learning |
| Authors | Valerio Perrone, Rodolphe Jenatton, Matthias W. Seeger, Cedric Archambeau |
| Abstract | Bayesian optimization (BO) is a model-based approach for gradient-free black-box function optimization, such as hyperparameter optimization. Typically, BO relies on conventional Gaussian process (GP) regression, whose algorithmic complexity is cubic in the number of evaluations. As a result, GP-based BO cannot leverage large numbers of past function evaluations, for example, to warm-start related BO runs. We propose a multi-task adaptive Bayesian linear regression model for transfer learning in BO, whose complexity is linear in the function evaluations: one Bayesian linear regression model is associated to each black-box function optimization problem (or task), while transfer learning is achieved by coupling the models through a shared deep neural net. Experiments show that the neural net learns a representation suitable for warm-starting the black-box optimization problems and that BO runs can be accelerated when the target black-box function (e.g., validation loss) is learned together with other related signals (e.g., training loss). The proposed method was found to be at least one order of magnitude faster that methods recently published in the literature. |
| Tasks | Hyperparameter Optimization, Transfer Learning |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7917-scalable-hyperparameter-transfer-learning |
| http://papers.nips.cc/paper/7917-scalable-hyperparameter-transfer-learning.pdf | |
| PWC | https://paperswithcode.com/paper/scalable-hyperparameter-transfer-learning |
| Repo | |
| Framework | |
Policy and Value Transfer in Lifelong Reinforcement Learning
| Title | Policy and Value Transfer in Lifelong Reinforcement Learning |
| Authors | David Abel, Yuu Jinnai, Sophie Yue Guo, George Konidaris, Michael Littman |
| Abstract | We consider the problem of how best to use prior experience to bootstrap lifelong learning, where an agent faces a series of task instances drawn from some task distribution. First, we identify the initial policy that optimizes expected performance over the distribution of tasks for increasingly complex classes of policy and task distributions. We empirically demonstrate the relative performance of each policy class’ optimal element in a variety of simple task distributions. We then consider value-function initialization methods that preserve PAC guarantees while simultaneously minimizing the learning required in two learning algorithms, yielding MaxQInit, a practical new method for value-function-based transfer. We show that MaxQInit performs well in simple lifelong RL experiments. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2271 |
| http://proceedings.mlr.press/v80/abel18b/abel18b.pdf | |
| PWC | https://paperswithcode.com/paper/policy-and-value-transfer-in-lifelong |
| Repo | |
| Framework | |
MCDTB: A Macro-level Chinese Discourse TreeBank
| Title | MCDTB: A Macro-level Chinese Discourse TreeBank |
| Authors | Feng Jiang, Sheng Xu, Xiaomin Chu, Peifeng Li, Qiaoming Zhu, Guodong Zhou |
| Abstract | In view of the differences between the annotations of micro and macro discourse rela-tionships, this paper describes the relevant experiments on the construction of the Macro Chinese Discourse Treebank (MCDTB), a higher-level Chinese discourse corpus. Fol-lowing RST (Rhetorical Structure Theory), we annotate the macro discourse information, including discourse structure, nuclearity and relationship, and the additional discourse information, including topic sentences, lead and abstract, to make the macro discourse annotation more objective and accurate. Finally, we annotated 720 articles with a Kappa value greater than 0.6. Preliminary experiments on this corpus verify the computability of MCDTB. |
| Tasks | Reading Comprehension |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1296/ |
| https://www.aclweb.org/anthology/C18-1296 | |
| PWC | https://paperswithcode.com/paper/mcdtb-a-macro-level-chinese-discourse |
| Repo | |
| Framework | |
Template-based multilingual football reports generation using Wikidata as a knowledge base
| Title | Template-based multilingual football reports generation using Wikidata as a knowledge base |
| Authors | Lorenzo Gatti, Chris van der Lee, Mari{"e}t Theune |
| Abstract | This paper presents a new version of a football reports generation system called PASS. The original version generated Dutch text and relied on a limited hand-crafted knowledge base. We describe how, in a short amount of time, we extended PASS to produce English texts, exploiting machine translation and Wikidata as a large-scale source of multilingual knowledge. |
| Tasks | Machine Translation, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6523/ |
| https://www.aclweb.org/anthology/W18-6523 | |
| PWC | https://paperswithcode.com/paper/template-based-multilingual-football-reports |
| Repo | |
| Framework | |
NICT Self-Training Approach to Neural Machine Translation at NMT-2018
| Title | NICT Self-Training Approach to Neural Machine Translation at NMT-2018 |
| Authors | Kenji Imamura, Eiichiro Sumita |
| Abstract | This paper describes the NICT neural machine translation system submitted at the NMT-2018 shared task. A characteristic of our approach is the introduction of self-training. Since our self-training does not change the model structure, it does not influence the efficiency of translation, such as the translation speed. The experimental results showed that the translation quality improved not only in the sequence-to-sequence (seq-to-seq) models but also in the transformer models. |
| Tasks | Machine Translation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2713/ |
| https://www.aclweb.org/anthology/W18-2713 | |
| PWC | https://paperswithcode.com/paper/nict-self-training-approach-to-neural-machine |
| Repo | |
| Framework | |
Automatic Glossing in a Low-Resource Setting for Language Documentation
| Title | Automatic Glossing in a Low-Resource Setting for Language Documentation |
| Authors | Sarah Moeller, Mans Hulden |
| Abstract | Morphological analysis of morphologically rich and low-resource languages is important to both descriptive linguistics and natural language processing. Field documentary efforts usually procure analyzed data in cooperation with native speakers who are capable of providing some level of linguistic information. Manually annotating such data is very expensive and the traditional process is arguably too slow in the face of language endangerment and loss. We report on a case study of learning to automatically gloss a Nakh-Daghestanian language, Lezgi, from a very small amount of seed data. We compare a conditional random field based sequence labeler and a neural encoder-decoder model and show that a nearly 0.9 F1-score on labeled accuracy of morphemes can be achieved with 3,000 words of transcribed oral text. Errors are mostly limited to morphemes with high allomorphy. These results are potentially useful for developing rapid annotation and fieldwork tools to support documentation of morphologically rich, endangered languages. |
| Tasks | Morphological Analysis |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4809/ |
| https://www.aclweb.org/anthology/W18-4809 | |
| PWC | https://paperswithcode.com/paper/automatic-glossing-in-a-low-resource-setting |
| Repo | |
| Framework | |
Multi-glance Reading Model for Text Understanding
| Title | Multi-glance Reading Model for Text Understanding |
| Authors | Pengcheng Zhu, Yujiu Yang, Wenqiang Gao, Yi Liu |
| Abstract | In recent years, a variety of recurrent neural networks have been proposed, e.g LSTM. However, existing models only read the text once, it cannot describe the situation of repeated reading in reading comprehension. In fact, when reading or analyzing a text, we may read the text several times rather than once if we couldn{'}t well understand it. So, how to model this kind of the reading behavior? To address the issue, we propose a multi-glance mechanism (MGM) for modeling the habit of reading behavior. In the proposed framework, the actual reading process can be fully simulated, and then the obtained information can be consistent with the task. Based on the multi-glance mechanism, we design two types of recurrent neural network models for repeated reading: Glance Cell Model (GCM) and Glance Gate Model (GGM). Visualization analysis of the GCM and the GGM demonstrates the effectiveness of multi-glance mechanisms. Experiments results on the large-scale datasets show that the proposed methods can achieve better performance. |
| Tasks | Document Classification, Machine Translation, Reading Comprehension, Sentiment Analysis |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-2804/ |
| https://www.aclweb.org/anthology/W18-2804 | |
| PWC | https://paperswithcode.com/paper/multi-glance-reading-model-for-text |
| Repo | |
| Framework | |
