Paper Group NANR 30
Target-Bidirectional Neural Models for Machine Transliteration. Large Multi-lingual, Multi-level and Multi-genre Annotation Corpus. A ``Maximal Exclusion’’ Approach to Structural Uncertainty in Dynamic Syntax. Abstractive News Summarization based on Event Semantic Link Network. Consensus Maximization Fusion of Probabilistic Information Extractors. …
Target-Bidirectional Neural Models for Machine Transliteration
| Title | Target-Bidirectional Neural Models for Machine Transliteration |
| Authors | Andrew Finch, Lemao Liu, Xiaolin Wang, Eiichiro Sumita |
| Abstract | |
| Tasks | Machine Translation, Transliteration |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2711/ |
| https://www.aclweb.org/anthology/W16-2711 | |
| PWC | https://paperswithcode.com/paper/target-bidirectional-neural-models-for |
| Repo | |
| Framework | |
Large Multi-lingual, Multi-level and Multi-genre Annotation Corpus
| Title | Large Multi-lingual, Multi-level and Multi-genre Annotation Corpus |
| Authors | Xuansong Li, Martha Palmer, Nianwen Xue, Lance Ramshaw, Mohamed Maamouri, Ann Bies, Kathryn Conger, Stephen Grimes, Stephanie Strassel |
| Abstract | High accuracy for automated translation and information retrieval calls for linguistic annotations at various language levels. The plethora of informal internet content sparked the demand for porting state-of-art natural language processing (NLP) applications to new social media as well as diverse language adaptation. Effort launched by the BOLT (Broad Operational Language Translation) program at DARPA (Defense Advanced Research Projects Agency) successfully addressed the internet information with enhanced NLP systems. BOLT aims for automated translation and linguistic analysis for informal genres of text and speech in online and in-person communication. As a part of this program, the Linguistic Data Consortium (LDC) developed valuable linguistic resources in support of the training and evaluation of such new technologies. This paper focuses on methodologies, infrastructure, and procedure for developing linguistic annotation at various language levels, including Treebank (TB), word alignment (WA), PropBank (PB), and co-reference (CoRef). Inspired by the OntoNotes approach with adaptations to the tasks to reflect the goals and scope of the BOLT project, this effort has introduced more annotation types of informal and free-style genres in English, Chinese and Egyptian Arabic. The corpus produced is by far the largest multi-lingual, multi-level and multi-genre annotation corpus of informal text and speech. |
| Tasks | Information Retrieval, Word Alignment |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1145/ |
| https://www.aclweb.org/anthology/L16-1145 | |
| PWC | https://paperswithcode.com/paper/large-multi-lingual-multi-level-and-multi |
| Repo | |
| Framework | |
A ``Maximal Exclusion’’ Approach to Structural Uncertainty in Dynamic Syntax
| Title | A ``Maximal Exclusion’’ Approach to Structural Uncertainty in Dynamic Syntax | |
| Authors | Tohru Seraku |
| Abstract | |
| Tasks | |
| Published | 2016-10-01 |
| URL | https://www.aclweb.org/anthology/Y16-2001/ |
| https://www.aclweb.org/anthology/Y16-2001 | |
| PWC | https://paperswithcode.com/paper/a-amaximal-exclusiona-approach-to-structural |
| Repo | |
| Framework | |
Abstractive News Summarization based on Event Semantic Link Network
| Title | Abstractive News Summarization based on Event Semantic Link Network |
| Authors | Wei Li, Lei He, Hai Zhuge |
| Abstract | This paper studies the abstractive multi-document summarization for event-oriented news texts through event information extraction and abstract representation. Fine-grained event mentions and semantic relations between them are extracted to build a unified and connected event semantic link network, an abstract representation of source texts. A network reduction algorithm is proposed to summarize the most salient and coherent event information. New sentences with good linguistic quality are automatically generated and selected through sentences over-generation and greedy-selection processes. Experimental results on DUC 2006 and DUC 2007 datasets show that our system significantly outperforms the state-of-the-art extractive and abstractive baselines under both pyramid and ROUGE evaluation metrics. |
| Tasks | Abstractive Text Summarization, Document Summarization, Multi-Document Summarization |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1023/ |
| https://www.aclweb.org/anthology/C16-1023 | |
| PWC | https://paperswithcode.com/paper/abstractive-news-summarization-based-on-event |
| Repo | |
| Framework | |
Consensus Maximization Fusion of Probabilistic Information Extractors
| Title | Consensus Maximization Fusion of Probabilistic Information Extractors |
| Authors | Miguel Rodr{'\i}guez, Sean Goldberg, Daisy Zhe Wang |
| Abstract | |
| Tasks | Knowledge Base Population |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/N16-1144/ |
| https://www.aclweb.org/anthology/N16-1144 | |
| PWC | https://paperswithcode.com/paper/consensus-maximization-fusion-of |
| Repo | |
| Framework | |
A Multi-party Multi-modal Dataset for Focus of Visual Attention in Human-human and Human-robot Interaction
| Title | A Multi-party Multi-modal Dataset for Focus of Visual Attention in Human-human and Human-robot Interaction |
| Authors | Kalin Stefanov, Jonas Beskow |
| Abstract | This papers describes a data collection setup and a newly recorded dataset. The main purpose of this dataset is to explore patterns in the focus of visual attention of humans under three different conditions - two humans involved in task-based interaction with a robot; same two humans involved in task-based interaction where the robot is replaced by a third human, and a free three-party human interaction. The dataset contains two parts - 6 sessions with duration of approximately 3 hours and 9 sessions with duration of approximately 4.5 hours. Both parts of the dataset are rich in modalities and recorded data streams - they include the streams of three Kinect v2 devices (color, depth, infrared, body and face data), three high quality audio streams, three high resolution GoPro video streams, touch data for the task-based interactions and the system state of the robot. In addition, the second part of the dataset introduces the data streams from three Tobii Pro Glasses 2 eye trackers. The language of all interactions is English and all data streams are spatially and temporally aligned. |
| Tasks | |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1703/ |
| https://www.aclweb.org/anthology/L16-1703 | |
| PWC | https://paperswithcode.com/paper/a-multi-party-multi-modal-dataset-for-focus |
| Repo | |
| Framework | |
Perception of lexical tones by Swedish learners of Mandarin
| Title | Perception of lexical tones by Swedish learners of Mandarin |
| Authors | Man Gao |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-6505/ |
| https://www.aclweb.org/anthology/W16-6505 | |
| PWC | https://paperswithcode.com/paper/perception-of-lexical-tones-by-swedish |
| Repo | |
| Framework | |
A Discriminative Feature Learning Approach for Deep Face Recognition
| Title | A Discriminative Feature Learning Approach for Deep Face Recognition |
| Authors | Yandong Wen, Kaipeng Zhang, Zhifeng Li, Yu Qiao |
| Abstract | Convolutional neural networks (CNNs) have been widely used in computer vision community, significantly improving the state-ofthe-art. In most of the available CNNs, the softmax loss function is used as the supervision signal to train the deep model. In order to enhance the discriminative power of the deeply learned features, this paper proposes a new supervision signal, called center loss, for face recognition task. Specifically, the center loss simultaneously learns a center for deep features of each class and penalizes the distances between the deep features and their corresponding class centers. More importantly, we prove that the proposed center loss function is trainable and easy to optimize in the CNNs. With the joint supervision of softmax loss and center loss, we can train a robust CNNs to obtain the deep features with the two key learning objectives, inter-class dispension and intra-class compactness as much as possible, which are very essential to face recognition. It is encouraging to see that our CNNs (with such joint supervision) achieve the state-of-the-art accuracy on several important face recognition benchmarks, Labeled Faces in the Wild (LFW), YouTube Faces (YTF), and MegaFace Challenge. Especially, our new approach achieves the best results on MegaFace (the largest public domain face benchmark) under the protocol of small training set (contains under 500000 images and under 20000 persons), significantly improving the previous results and setting new state-of-the-art for both face recognition and face verification tasks. |
| Tasks | Face Recognition, Face Verification |
| Published | 2016-09-16 |
| URL | https://link.springer.com/chapter/10.1007/978-3-319-46478-7_31 |
| https://ydwen.github.io/papers/WenECCV16.pdf | |
| PWC | https://paperswithcode.com/paper/a-discriminative-feature-learning-approach |
| Repo | |
| Framework | |
Learning under uncertainty: a comparison between R-W and Bayesian approach
| Title | Learning under uncertainty: a comparison between R-W and Bayesian approach |
| Authors | He Huang, Martin Paulus |
| Abstract | Accurately differentiating between what are truly unpredictably random and systematic changes that occur at random can have profound effect on affect and cognition. To examine the underlying computational principles that guide different learning behavior in an uncertain environment, we compared an R-W model and a Bayesian approach in a visual search task with different volatility levels. Both R-W model and the Bayesian approach reflected an individual’s estimation of the environmental volatility, and there is a strong correlation between the learning rate in R-W model and the belief of stationarity in the Bayesian approach in different volatility conditions. In a low volatility condition, R-W model indicates that learning rate positively correlates with lose-shift rate, but not choice optimality (inverted U shape). The Bayesian approach indicates that the belief of environmental stationarity positively correlates with choice optimality, but not lose-shift rate (inverted U shape). In addition, we showed that comparing to Expert learners, individuals with high lose-shift rate (sub-optimal learners) had significantly higher learning rate estimated from R-W model and lower belief of stationarity from the Bayesian model. |
| Tasks | |
| Published | 2016-12-01 |
| URL | http://papers.nips.cc/paper/6409-learning-under-uncertainty-a-comparison-between-r-w-and-bayesian-approach |
| http://papers.nips.cc/paper/6409-learning-under-uncertainty-a-comparison-between-r-w-and-bayesian-approach.pdf | |
| PWC | https://paperswithcode.com/paper/learning-under-uncertainty-a-comparison |
| Repo | |
| Framework | |
Triaging Mental Health Forum Posts
| Title | Triaging Mental Health Forum Posts |
| Authors | Arman Cohan, Sydney Young, Nazli Goharian |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0316/ |
| https://www.aclweb.org/anthology/W16-0316 | |
| PWC | https://paperswithcode.com/paper/triaging-mental-health-forum-posts |
| Repo | |
| Framework | |
Different Contexts Lead to Different Word Embeddings
| Title | Different Contexts Lead to Different Word Embeddings |
| Authors | Wenpeng Hu, Jiajun Zhang, Nan Zheng |
| Abstract | Recent work for learning word representations has applied successfully to many NLP applications, such as sentiment analysis and question answering. However, most of these models assume a single vector per word type without considering polysemy and homonymy. In this paper, we present an extension to the CBOW model which not only improves the quality of embeddings but also makes embeddings suitable for polysemy. It differs from most of the related work in that it learns one semantic center embedding and one context bias instead of training multiple embeddings per word type. Different context leads to different bias which is defined as the weighted average embeddings of local context. Experimental results on similarity task and analogy task show that the word representations learned by the proposed method outperform the competitive baselines. |
| Tasks | Information Retrieval, Learning Word Embeddings, Question Answering, Sentiment Analysis, Word Embeddings |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1073/ |
| https://www.aclweb.org/anthology/C16-1073 | |
| PWC | https://paperswithcode.com/paper/different-contexts-lead-to-different-word |
| Repo | |
| Framework | |
Cosmopolitan Mumbai, Orthodox Delhi, Techcity Bangalore:Understanding City Specific Societal Sentiment
| Title | Cosmopolitan Mumbai, Orthodox Delhi, Techcity Bangalore:Understanding City Specific Societal Sentiment |
| Authors | Aishwarya N Reganti, Tushar Maheshwari, Upendra Kumar, Amitava Das |
| Abstract | |
| Tasks | Emotion Recognition |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-6322/ |
| https://www.aclweb.org/anthology/W16-6322 | |
| PWC | https://paperswithcode.com/paper/cosmopolitan-mumbai-orthodox-delhi-techcity |
| Repo | |
| Framework | |
Analyzing Gender Bias in Student Evaluations
| Title | Analyzing Gender Bias in Student Evaluations |
| Authors | Andamlak Terkik, Emily Prud{'}hommeaux, Cecilia Ovesdotter Alm, Christopher Homan, Scott Franklin |
| Abstract | University students in the United States are routinely asked to provide feedback on the quality of the instruction they have received. Such feedback is widely used by university administrators to evaluate teaching ability, despite growing evidence that students assign lower numerical scores to women and people of color, regardless of the actual quality of instruction. In this paper, we analyze students{'} written comments on faculty evaluation forms spanning eight years and five STEM disciplines in order to determine whether open-ended comments reflect these same biases. First, we apply sentiment analysis techniques to the corpus of comments to determine the overall affect of each comment. We then use this information, in combination with other features, to explore whether there is bias in how students describe their instructors. We show that while the gender of the evaluated instructor does not seem to affect students{'} expressed level of overall satisfaction with their instruction, it does strongly influence the language that they use to describe their instructors and their experience in class. |
| Tasks | Sentiment Analysis |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/C16-1083/ |
| https://www.aclweb.org/anthology/C16-1083 | |
| PWC | https://paperswithcode.com/paper/analyzing-gender-bias-in-student-evaluations |
| Repo | |
| Framework | |
Natural Language Model Re-usability for Scaling to Different Domains
| Title | Natural Language Model Re-usability for Scaling to Different Domains |
| Authors | Young-Bum Kim, Alex Rochette, re, Ruhi Sarikaya |
| Abstract | |
| Tasks | Language Modelling |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/D16-1222/ |
| https://www.aclweb.org/anthology/D16-1222 | |
| PWC | https://paperswithcode.com/paper/natural-language-model-re-usability-for |
| Repo | |
| Framework | |
Automatic Grammatical Error Detection for Chinese based on Conditional Random Field
| Title | Automatic Grammatical Error Detection for Chinese based on Conditional Random Field |
| Authors | Yajun Liu, Yingjie Han, Liyan Zhuo, Hongying Zan |
| Abstract | In the process of learning and using Chinese, foreigners may have grammatical errors due to negative migration of their native languages. Currently, the computer-oriented automatic detection method of grammatical errors is not mature enough. Based on the evaluating task {—} CGED2016, we select and analyze the classification model and design feature extraction method to obtain grammatical errors including Mission(M), Disorder(W), Selection (S) and Redundant (R) automatically. The experiment results based on the dynamic corpus of HSK show that the Chinese grammatical error automatic detection method, which uses CRF as classification model and n-gram as feature extraction method. It is simple and efficient which play a positive effect on the research of Chinese grammatical error automatic detection and also a supporting and guiding role in the teaching of Chinese as a foreign language. |
| Tasks | Grammatical Error Detection, Part-Of-Speech Tagging |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4908/ |
| https://www.aclweb.org/anthology/W16-4908 | |
| PWC | https://paperswithcode.com/paper/automatic-grammatical-error-detection-for |
| Repo | |
| Framework | |
