Paper Group NANR 145
Supporting Content Design with an Eye Tracker: The Case of Weather-based Recommendations. Attending Sentences to detect Satirical Fake News. Proceedings of the Second Workshop on Subword/Character LEvel Models. NILC-SWORNEMO at the Surface Realization Shared Task: Exploring Syntax-Based Word Ordering using Neural Models. Fully Motion-Aware Network …
Supporting Content Design with an Eye Tracker: The Case of Weather-based Recommendations
| Title | Supporting Content Design with an Eye Tracker: The Case of Weather-based Recommendations |
| Authors | Alej Catala, ro, Jose M. Alonso, Alberto Bugarin |
| Abstract | |
| Tasks | Decision Making, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6708/ |
| https://www.aclweb.org/anthology/W18-6708 | |
| PWC | https://paperswithcode.com/paper/supporting-content-design-with-an-eye-tracker |
| Repo | |
| Framework | |
Attending Sentences to detect Satirical Fake News
| Title | Attending Sentences to detect Satirical Fake News |
| Authors | Sohan De Sarkar, Fan Yang, Arjun Mukherjee |
| Abstract | Satirical news detection is important in order to prevent the spread of misinformation over the Internet. Existing approaches to capture news satire use machine learning models such as SVM and hierarchical neural networks along with hand-engineered features, but do not explore sentence and document difference. This paper proposes a robust, hierarchical deep neural network approach for satire detection, which is capable of capturing satire both at the sentence level and at the document level. The architecture incorporates pluggable generic neural networks like CNN, GRU, and LSTM. Experimental results on real world news satire dataset show substantial performance gains demonstrating the effectiveness of our proposed approach. An inspection of the learned models reveals the existence of key sentences that control the presence of satire in news. |
| Tasks | Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1285/ |
| https://www.aclweb.org/anthology/C18-1285 | |
| PWC | https://paperswithcode.com/paper/attending-sentences-to-detect-satirical-fake |
| Repo | |
| Framework | |
Proceedings of the Second Workshop on Subword/Character LEvel Models
| Title | Proceedings of the Second Workshop on Subword/Character LEvel Models |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-1200/ |
| https://www.aclweb.org/anthology/W18-1200 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-second-workshop-on-4 |
| Repo | |
| Framework | |
NILC-SWORNEMO at the Surface Realization Shared Task: Exploring Syntax-Based Word Ordering using Neural Models
| Title | NILC-SWORNEMO at the Surface Realization Shared Task: Exploring Syntax-Based Word Ordering using Neural Models |
| Authors | Marco Antonio Sobrevilla Cabezudo, Thiago Pardo |
| Abstract | This paper describes the submission by the NILC Computational Linguistics research group of the University of S{~a}o Paulo/Brazil to the Track 1 of the Surface Realization Shared Task (SRST Track 1). We present a neural-based method that works at the syntactic level to order the words (which we refer by NILC-SWORNEMO, standing for {``}Syntax-based Word ORdering using NEural MOdels{''}). Additionally, we apply a bottom-up approach to build the sentence and, using language-specific lexicons, we produce the proper word form of each lemma in the sentence. The results obtained by our method outperformed the average of the results for English, Portuguese and Spanish in the track. | |
| Tasks | Language Modelling, Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3608/ |
| https://www.aclweb.org/anthology/W18-3608 | |
| PWC | https://paperswithcode.com/paper/nilc-swornemo-at-the-surface-realization |
| Repo | |
| Framework | |
Fully Motion-Aware Network for Video Object Detection
| Title | Fully Motion-Aware Network for Video Object Detection |
| Authors | Shiyao Wang, Yucong Zhou, Junjie Yan, Zhidong Deng |
| Abstract | Video objection detection is challenging in the presence of appearance deterioration in certain video frames. One of typical solutions is to enhance per-frame features through aggregating neighboring frames. But the features of objects are usually not spatially calibrated across frames due to motion from object and camera. In this paper, we propose an end-to-end model called fully motion-aware network (MANet), which jointly calibrates the features of objects on both pixel-level and instance-level in a unified framework. The pixel-level calibration is flexible in modeling detailed motion while the instance-level calibration captures more global motion cues in order to be robust to occlusion. To our best knowledge, MANet is the first work that can jointly train the two modules and dynamically combine them according to the motion patterns. It achieves leading performance on the large-scale ImageNet VID dataset. |
| Tasks | Calibration, Object Detection, Video Object Detection |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Shiyao_Wang_Fully_Motion-Aware_Network_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Shiyao_Wang_Fully_Motion-Aware_Network_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/fully-motion-aware-network-for-video-object |
| Repo | |
| Framework | |
Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference
| Title | Proceedings of the First Workshop on Computational Models of Reference, Anaphora and Coreference |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0700/ |
| https://www.aclweb.org/anthology/W18-0700 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-4 |
| Repo | |
| Framework | |
Syntactic and Lexical Approaches to Reading Comprehension
| Title | Syntactic and Lexical Approaches to Reading Comprehension |
| Authors | Henry Lin |
| Abstract | Among the challenges of teaching reading comprehension in K {–} 12 are identifying the portions of a text that are difficult for a student, comprehending major critical ideas, and understanding context-dependent polysemous words. We present a simple, unsupervised but robust and accurate syntactic method for achieving the first objective and a modified hierarchical lexical method for the second objective. Focusing on pinpointing troublesome sentences instead of the overall readability and on concepts central to a reading, we believe these methods will greatly facilitate efforts to help students improve reading skills |
| Tasks | Reading Comprehension |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3702/ |
| https://www.aclweb.org/anthology/W18-3702 | |
| PWC | https://paperswithcode.com/paper/syntactic-and-lexical-approaches-to-reading |
| Repo | |
| Framework | |
Mask-Guided Contrastive Attention Model for Person Re-Identification
| Title | Mask-Guided Contrastive Attention Model for Person Re-Identification |
| Authors | Chunfeng Song, Yan Huang, Wanli Ouyang, Liang Wang |
| Abstract | Person Re-identification (ReID) is an important yet challenging task in computer vision. Due to the diverse background clutters, variations on viewpoints and body poses, it is far from solved. How to extract discriminative and robust features invariant to background clutters is the core problem. In this paper, we first introduce the binary segmentation masks to construct synthetic RGB-Mask pairs as inputs, then we design a mask-guided contrastive attention model (MGCAM) to learn features separately from the body and background regions. Moreover, we propose a novel region-level triplet loss to restrain the features learnt from different regions, i.e., pulling the features from the full image and body region close, whereas pushing the features from backgrounds away. We may be the first one to successfully introduce the binary mask into person ReID task and the first one to propose region-level contrastive learning. We evaluate the proposed method on three public datasets, including MARS, Market-1501 and CUHK03. Extensive experimental results show that the proposed method is effective and achieves the state-of-the-art results. Mask and code will be released upon request. |
| Tasks | Person Re-Identification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Song_Mask-Guided_Contrastive_Attention_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Song_Mask-Guided_Contrastive_Attention_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mask-guided-contrastive-attention-model-for |
| Repo | |
| Framework | |
Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization
| Title | Retrieve, Rerank and Rewrite: Soft Template Based Neural Summarization |
| Authors | Ziqiang Cao, Wenjie Li, Sujian Li, Furu Wei |
| Abstract | Most previous seq2seq summarization systems purely depend on the source text to generate summaries, which tends to work unstably. Inspired by the traditional template-based summarization approaches, this paper proposes to use existing summaries as soft templates to guide the seq2seq model. To this end, we use a popular IR platform to Retrieve proper summaries as candidate templates. Then, we extend the seq2seq framework to jointly conduct template Reranking and template-aware summary generation (Rewriting). Experiments show that, in terms of informativeness, our model significantly outperforms the state-of-the-art methods, and even soft templates themselves demonstrate high competitiveness. In addition, the import of high-quality external summaries improves the stability and readability of generated summaries. |
| Tasks | Abstractive Sentence Summarization, Abstractive Text Summarization |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-1015/ |
| https://www.aclweb.org/anthology/P18-1015 | |
| PWC | https://paperswithcode.com/paper/retrieve-rerank-and-rewrite-soft-template |
| Repo | |
| Framework | |
Multi-task learning for historical text normalization: Size matters
| Title | Multi-task learning for historical text normalization: Size matters |
| Authors | Marcel Bollmann, Anders S{\o}gaard, Joachim Bingel |
| Abstract | Historical text normalization suffers from small datasets that exhibit high variance, and previous work has shown that multi-task learning can be used to leverage data from related problems in order to obtain more robust models. Previous work has been limited to datasets from a specific language and a specific historical period, and it is not clear whether results generalize. It therefore remains an open problem, when historical text normalization benefits from multi-task learning. We explore the benefits of multi-task learning across 10 different datasets, representing different languages and periods. Our main finding{—}contrary to what has been observed for other NLP tasks{—}is that multi-task learning mainly works when target task data is very scarce. |
| Tasks | Grammatical Error Correction, Multi-Task Learning, Text Generation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3403/ |
| https://www.aclweb.org/anthology/W18-3403 | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-for-historical-text |
| Repo | |
| Framework | |
Every Object Tells a Story
| Title | Every Object Tells a Story |
| Authors | James Pustejovsky, Nikhil Krishnaswamy |
| Abstract | Most work within the computational event modeling community has tended to focus on the interpretation and ordering of events that are associated with verbs and event nominals in linguistic expressions. What is often overlooked in the construction of a global interpretation of a narrative is the role contributed by the objects participating in these structures, and the latent events and activities conventionally associated with them. Recently, the analysis of visual images has also enriched the scope of how events can be identified, by anchoring both linguistic expressions and ontological labels to segments, subregions, and properties of images. By semantically grounding event descriptions in their visualization, the importance of object-based attributes becomes more apparent. In this position paper, we look at the narrative structure of objects: that is, how objects reference events through their intrinsic attributes, such as affordances, purposes, and functions. We argue that, not only do objects encode conventionalized events, but that when they are composed within specific habitats, the ensemble can be viewed as modeling coherent event sequences, thereby enriching the global interpretation of the evolving narrative being constructed. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4301/ |
| https://www.aclweb.org/anthology/W18-4301 | |
| PWC | https://paperswithcode.com/paper/every-object-tells-a-story |
| Repo | |
| Framework | |
A Corpus of Non-Native Written English Annotated for Metaphor
| Title | A Corpus of Non-Native Written English Annotated for Metaphor |
| Authors | Beata Beigman Klebanov, Chee Wee (Ben) Leong, Michael Flor |
| Abstract | We present a corpus of 240 argumentative essays written by non-native speakers of English annotated for metaphor. The corpus is made publicly available. We provide benchmark performance of state-of-the-art systems on this new corpus, and explore the relationship between writing proficiency and metaphor use. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-2014/ |
| https://www.aclweb.org/anthology/N18-2014 | |
| PWC | https://paperswithcode.com/paper/a-corpus-of-non-native-written-english |
| Repo | |
| Framework | |
The Linguistic Category Model in Polish (LCM-PL)
| Title | The Linguistic Category Model in Polish (LCM-PL) |
| Authors | Aleks Wawer, er, Justyna Sarzy{'n}ska |
| Abstract | |
| Tasks | |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1696/ |
| https://www.aclweb.org/anthology/L18-1696 | |
| PWC | https://paperswithcode.com/paper/the-linguistic-category-model-in-polish-lcm |
| Repo | |
| Framework | |
Tencent Neural Machine Translation Systems for WMT18
| Title | Tencent Neural Machine Translation Systems for WMT18 |
| Authors | Mingxuan Wang, Li Gong, Wenhuan Zhu, Jun Xie, Chao Bian |
| Abstract | We participated in the WMT 2018 shared news translation task on English↔Chinese language pair. Our systems are based on attentional sequence-to-sequence models with some form of recursion and self-attention. Some data augmentation methods are also introduced to improve the translation performance. The best translation result is obtained with ensemble and reranking techniques. Our Chinese→English system achieved the highest cased BLEU score among all 16 submitted systems, and our English→Chinese system ranked the third out of 18 submitted systems. |
| Tasks | Data Augmentation, Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6429/ |
| https://www.aclweb.org/anthology/W18-6429 | |
| PWC | https://paperswithcode.com/paper/tencent-neural-machine-translation-systems |
| Repo | |
| Framework | |
A Tutorial Markov Analysis of Effective Human Tutorial Sessions
| Title | A Tutorial Markov Analysis of Effective Human Tutorial Sessions |
| Authors | Nabin Maharjan, Vasile Rus |
| Abstract | This paper investigates what differentiates effective tutorial sessions from less effective sessions. Towards this end, we characterize and explore human tutors{'} actions in tutorial dialogue sessions by mapping the tutor-tutee interactions, which are streams of dialogue utterances, into streams of actions, based on the language-as-action theory. Next, we use human expert judgment measures, evidence of learning (EL) and evidence of soundness (ES), to identify effective and ineffective sessions. We perform sub-sequence pattern mining to identify sub-sequences of dialogue modes that discriminate good sessions from bad sessions. We finally use the results of sub-sequence analysis method to generate a tutorial Markov process for effective tutorial sessions. |
| Tasks | |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3704/ |
| https://www.aclweb.org/anthology/W18-3704 | |
| PWC | https://paperswithcode.com/paper/a-tutorial-markov-analysis-of-effective-human |
| Repo | |
| Framework | |
