Paper Group NANR 245
Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel. LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification. KSU at SemEval-2019 Task 3: Hybrid Features for Emotion Recognition in Textual Conversation. Split or Merge: Which is Better for Unsupervised RST Parsin …
Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel
| Title | Transformer Dissection: An Unified Understanding for Transformer’s Attention via the Lens of Kernel |
| Authors | Yao-Hung Hubert Tsai, Shaojie Bai, Makoto Yamada, Louis-Philippe Morency, Ruslan Salakhutdinov |
| Abstract | Transformer is a powerful architecture that achieves superior performance on various sequence learning tasks, including neural machine translation, language understanding, and sequence prediction. At the core of the Transformer is the attention mechanism, which concurrently processes all inputs in the streams. In this paper, we present a new formulation of attention via the lens of the kernel. To be more precise, we realize that the attention can be seen as applying kernel smoother over the inputs with the kernel scores being the similarities between inputs. This new formulation gives us a better way to understand individual components of the Transformer{'}s attention, such as the better way to integrate the positional embedding. Another important advantage of our kernel-based formulation is that it paves the way to a larger space of composing Transformer{'}s attention. As an example, we propose a new variant of Transformer{'}s attention which models the input as a product of symmetric kernels. This approach achieves competitive performance to the current state of the art model with less computation. In our experiments, we empirically study different kernel construction strategies on two widely used tasks: neural machine translation and sequence prediction. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1443/ |
| https://www.aclweb.org/anthology/D19-1443 | |
| PWC | https://paperswithcode.com/paper/transformer-dissection-an-unified-1 |
| Repo | |
| Framework | |
LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification
| Title | LexicalAT: Lexical-Based Adversarial Reinforcement Training for Robust Sentiment Classification |
| Authors | Jingjing Xu, Liang Zhao, Hanqi Yan, Qi Zeng, Yun Liang, Xu Sun |
| Abstract | Recent work has shown that current text classification models are fragile and sensitive to simple perturbations. In this work, we propose a novel adversarial training approach, LexicalAT, to improve the robustness of current classification models. The proposed approach consists of a generator and a classifier. The generator learns to generate examples to attack the classifier while the classifier learns to defend these attacks. Considering the diversity of attacks, the generator uses a large-scale lexical knowledge base, WordNet, to generate attacking examples by replacing some words in training examples with their synonyms (e.g., sad and unhappy), neighbor words (e.g., fox and wolf), or super-superior words (e.g., chair and armchair). Due to the discrete generation step in the generator, we use policy gradient, a reinforcement learning approach, to train the two modules. Experiments show LexicalAT outperforms strong baselines and reduces test errors on various neural networks, including CNN, RNN, and BERT. |
| Tasks | Sentiment Analysis, Text Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1554/ |
| https://www.aclweb.org/anthology/D19-1554 | |
| PWC | https://paperswithcode.com/paper/lexicalat-lexical-based-adversarial |
| Repo | |
| Framework | |
KSU at SemEval-2019 Task 3: Hybrid Features for Emotion Recognition in Textual Conversation
| Title | KSU at SemEval-2019 Task 3: Hybrid Features for Emotion Recognition in Textual Conversation |
| Authors | Nourah Alswaidan, Mohamed El Bachir Menai |
| Abstract | We proposed a model to address emotion recognition in textual conversation based on using automatically extracted features and human engineered features. The proposed model utilizes a fast gated-recurrent-unit backed by CuDNN, and a convolutional neural network to automatically extract features. The human engineered features take the frequency-inverse document frequency of semantic meaning and mood tags extracted from SinticNet. |
| Tasks | Emotion Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2041/ |
| https://www.aclweb.org/anthology/S19-2041 | |
| PWC | https://paperswithcode.com/paper/ksu-at-semeval-2019-task-3-hybrid-features |
| Repo | |
| Framework | |
Split or Merge: Which is Better for Unsupervised RST Parsing?
| Title | Split or Merge: Which is Better for Unsupervised RST Parsing? |
| Authors | Naoki Kobayashi, Tsutomu Hirao, Kengo Nakamura, Hidetaka Kamigaito, Manabu Okumura, Masaaki Nagata |
| Abstract | Rhetorical Structure Theory (RST) parsing is crucial for many downstream NLP tasks that require a discourse structure for a text. Most of the previous RST parsers have been based on supervised learning approaches. That is, they require an annotated corpus of sufficient size and quality, and heavily rely on the language and domain dependent corpus. In this paper, we present two language-independent unsupervised RST parsing methods based on dynamic programming. The first one builds the optimal tree in terms of a dissimilarity score function that is defined for splitting a text span into smaller ones. The second builds the optimal tree in terms of a similarity score function that is defined for merging two adjacent spans into a large one. Experimental results on English and German RST treebanks showed that our parser based on span merging achieved the best score, around 0.8 F$_1$ score, which is close to the scores of the previous supervised parsers. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1587/ |
| https://www.aclweb.org/anthology/D19-1587 | |
| PWC | https://paperswithcode.com/paper/split-or-merge-which-is-better-for |
| Repo | |
| Framework | |
Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN)
| Title | Proceedings of the Beyond Vision and LANguage: inTEgrating Real-world kNowledge (LANTERN) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6400/ |
| https://www.aclweb.org/anthology/D19-6400 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-beyond-vision-and-language |
| Repo | |
| Framework | |
Combining Knowledge Hunting and Neural Language Models to Solve the Winograd Schema Challenge
| Title | Combining Knowledge Hunting and Neural Language Models to Solve the Winograd Schema Challenge |
| Authors | Ashok Prakash, Arpit Sharma, Arindam Mitra, Chitta Baral |
| Abstract | Winograd Schema Challenge (WSC) is a pronoun resolution task which seems to require reasoning with commonsense knowledge. The needed knowledge is not present in the given text. Automatic extraction of the needed knowledge is a bottleneck in solving the challenge. The existing state-of-the-art approach uses the knowledge embedded in their pre-trained language model. However, the language models only embed part of the knowledge, the ones related to frequently co-existing concepts. This limits the performance of such models on the WSC problems. In this work, we build-up on the language model based methods and augment them with a commonsense knowledge hunting (using automatic extraction from text) module and an explicit reasoning module. Our end-to-end system built in such a manner improves on the accuracy of two of the available language model based approaches by 5.53{%} and 7.7{%} respectively. Overall our system achieves the state-of-the-art accuracy of 71.06{%} on the WSC dataset, an improvement of 7.36{%} over the previous best. |
| Tasks | Language Modelling |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1614/ |
| https://www.aclweb.org/anthology/P19-1614 | |
| PWC | https://paperswithcode.com/paper/combining-knowledge-hunting-and-neural |
| Repo | |
| Framework | |
Linguistic features and proficiency classification in L2 Spanish and L2Portuguese.
| Title | Linguistic features and proficiency classification in L2 Spanish and L2Portuguese. |
| Authors | Iria del R{'\i}o |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6304/ |
| https://www.aclweb.org/anthology/W19-6304 | |
| PWC | https://paperswithcode.com/paper/linguistic-features-and-proficiency |
| Repo | |
| Framework | |
Applying BERT to Document Retrieval with Birch
| Title | Applying BERT to Document Retrieval with Birch |
| Authors | Zeynep Akkalyoncu Yilmaz, Shengjin Wang, Wei Yang, Haotian Zhang, Jimmy Lin |
| Abstract | We present Birch, a system that applies BERT to document retrieval via integration with the open-source Anserini information retrieval toolkit to demonstrate end-to-end search over large document collections. Birch implements simple ranking models that achieve state-of-the-art effectiveness on standard TREC newswire and social media test collections. This demonstration focuses on technical challenges in the integration of NLP and IR capabilities, along with the design rationale behind our approach to tightly-coupled integration between Python (to support neural networks) and the Java Virtual Machine (to support document retrieval using the open-source Lucene search library). We demonstrate integration of Birch with an existing search interface as well as interactive notebooks that highlight its capabilities in an easy-to-understand manner. |
| Tasks | Information Retrieval |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3004/ |
| https://www.aclweb.org/anthology/D19-3004 | |
| PWC | https://paperswithcode.com/paper/applying-bert-to-document-retrieval-with |
| Repo | |
| Framework | |
CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection
| Title | CapSal: Leveraging Captioning to Boost Semantics for Salient Object Detection |
| Authors | Lu Zhang, Jianming Zhang, Zhe Lin, Huchuan Lu, You He |
| Abstract | Detecting salient objects in cluttered scenes is a big challenge. To address this problem, we argue that the model needs to learn discriminative semantic features for salient objects. To this end, we propose to leverage captioning as an auxiliary semantic task to boost salient object detection in complex scenarios. Specifically, we develop a CapSal model which consists of two sub-networks, the Image Captioning Network (ICN) and the Local-Global Perception Network (LGPN). ICN encodes the embedding of a generated caption to capture the semantic information of major objects in the scene, while LGPN incorporates the captioning embedding with local-global visual contexts for predicting the saliency map. ICN and LGPN are jointly trained to model high-level semantics as well as visual saliency. Extensive experiments demonstrate the effectiveness of image captioning in boosting the performance of salient object detection. In particular, our model performs significantly better than the state-of-the-art methods on several challenging datasets of complex scenarios. |
| Tasks | Image Captioning, Object Detection, Salient Object Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhang_CapSal_Leveraging_Captioning_to_Boost_Semantics_for_Salient_Object_Detection_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhang_CapSal_Leveraging_Captioning_to_Boost_Semantics_for_Salient_Object_Detection_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/capsal-leveraging-captioning-to-boost |
| Repo | |
| Framework | |
Unsupervised 3D Reconstruction Networks
| Title | Unsupervised 3D Reconstruction Networks |
| Authors | Geonho Cha, Minsik Lee, Songhwai Oh |
| Abstract | In this paper, we propose 3D unsupervised reconstruction networks (3D-URN), which reconstruct the 3D structures of instances in a given object category from their 2D feature points under an orthographic camera model. 3D-URN consists of a 3D shape reconstructor and a rotation estimator, which are trained in a fully-unsupervised manner incorporating the proposed unsupervised loss functions. The role of the 3D shape reconstructor is to reconstruct the 3D shape of an instance from its 2D feature points, and the rotation estimator infers the camera pose. After training, 3D-URN can infer the 3D structure of an unseen instance in the same category, which is not possible in the conventional schemes of non-rigid structure from motion and structure from category. The experimental result shows the state-of-the-art performance, which demonstrates the effectiveness of the proposed method. |
| Tasks | 3D Reconstruction |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Cha_Unsupervised_3D_Reconstruction_Networks_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Cha_Unsupervised_3D_Reconstruction_Networks_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-3d-reconstruction-networks |
| Repo | |
| Framework | |
Enthymemetic Conditionals: Topoi as a guide for acceptability
| Title | Enthymemetic Conditionals: Topoi as a guide for acceptability |
| Authors | Eimear Maguire |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1008/ |
| https://www.aclweb.org/anthology/W19-1008 | |
| PWC | https://paperswithcode.com/paper/enthymemetic-conditionals-topoi-as-a-guide |
| Repo | |
| Framework | |
Cross-sectional Learning of Extremal Dependence among Financial Assets
| Title | Cross-sectional Learning of Extremal Dependence among Financial Assets |
| Authors | Xing Yan, Qi Wu, Wen Zhang |
| Abstract | We propose a novel probabilistic model to facilitate the learning of multivariate tail dependence of multiple financial assets. Our method allows one to construct from known random vectors, e.g., standard normal, sophisticated joint heavy-tailed random vectors featuring not only distinct marginal tail heaviness, but also flexible tail dependence structure. The novelty lies in that pairwise tail dependence between any two dimensions is modeled separately from their correlation, and can vary respectively according to its own parameter rather than the correlation parameter, which is an essential advantage over many commonly used methods such as multivariate $t$ or elliptical distribution. It is also intuitive to interpret, easy to track, and simple to sample comparing to the copula approach. We show its flexible tail dependence structure through simulation. Coupled with a GARCH model to eliminate serial dependence of each individual asset return series, we use this novel method to model and forecast multivariate conditional distribution of stock returns, and obtain notable performance improvements in multi-dimensional coverage tests. Besides, our empirical finding about the asymmetry of tails of the idiosyncratic component as well as the market component is interesting and worth to be well studied in the future. |
| Tasks | |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/8641-cross-sectional-learning-of-extremal-dependence-among-financial-assets |
| http://papers.nips.cc/paper/8641-cross-sectional-learning-of-extremal-dependence-among-financial-assets.pdf | |
| PWC | https://paperswithcode.com/paper/cross-sectional-learning-of-extremal |
| Repo | |
| Framework | |
Towards Incremental Learning of Word Embeddings Using Context Informativeness
| Title | Towards Incremental Learning of Word Embeddings Using Context Informativeness |
| Authors | Alex Kabbach, re, Kristina Gulordava, Aur{'e}lie Herbelot |
| Abstract | In this paper, we investigate the task of learning word embeddings from very sparse data in an incremental, cognitively-plausible way. We focus on the notion of {`}informativeness{'}, that is, the idea that some content is more valuable to the learning process than other. We further highlight the challenges of online learning and argue that previous systems fall short of implementing incrementality. Concretely, we incorporate informativeness in a previously proposed model of nonce learning, using it for context selection and learning rate modulation. We test our system on the task of learning new words from definitions, as well as on the task of learning new words from potentially uninformative contexts. We demonstrate that informativeness is crucial to obtaining state-of-the-art performance in a truly incremental setup. | |
| Tasks | Learning Word Embeddings, Word Embeddings |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2022/ |
| https://www.aclweb.org/anthology/P19-2022 | |
| PWC | https://paperswithcode.com/paper/towards-incremental-learning-of-word |
| Repo | |
| Framework | |
G3raphGround: Graph-Based Language Grounding
| Title | G3raphGround: Graph-Based Language Grounding |
| Authors | Mohit Bajaj, Lanjun Wang, Leonid Sigal |
| Abstract | In this paper we present an end-to-end framework for grounding of phrases in images. In contrast to previous works, our model, which we call GraphGround, uses graphs to formulate more complex, non-sequential dependencies among proposal image regions and phrases. We capture intra-modal dependencies using a separate graph neural network for each modality (visual and lingual), and then use conditional message-passing in another graph neural network to fuse their outputs and capture cross-modal relationships. This final representation results in grounding decisions. The framework supports many-to-many matching and is able to ground single phrase to multiple image regions and vice versa. We validate our design choices through a series of ablation studies and illustrate state-of-the-art performance on Flickr30k and ReferIt Game benchmark datasets. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Bajaj_G3raphGround_Graph-Based_Language_Grounding_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Bajaj_G3raphGround_Graph-Based_Language_Grounding_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/g3raphground-graph-based-language-grounding |
| Repo | |
| Framework | |
Mixture-Kernel Graph Attention Network for Situation Recognition
| Title | Mixture-Kernel Graph Attention Network for Situation Recognition |
| Authors | Mohammed Suhail, Leonid Sigal |
| Abstract | Understanding images beyond salient actions involves reasoning about scene context, objects, and the roles they play in the captured event. Situation recognition has recently been introduced as the task of jointly reasoning about the verbs (actions) and a set of semantic-role and entity (noun) pairs in the form of action frames. Labeling an image with an action frame requires an assignment of values (nouns) to the roles based on the observed image content. Among the inherent challenges are the rich conditional structured dependencies between the output role assignments and the overall semantic sparsity. In this paper, we propose a novel mixture-kernel attention graph neural network (GNN) architecture designed to address these challenges. Our GNN enables dynamic graph structure during training and inference, through the use of a graph attention mechanism, and context-aware interactions between role pairs. We illustrate the efficacy of our model and design choices by conducting experiments on imSitu benchmark dataset, with accuracy improvements of up to 10% over the state-of-the-art. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Suhail_Mixture-Kernel_Graph_Attention_Network_for_Situation_Recognition_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Suhail_Mixture-Kernel_Graph_Attention_Network_for_Situation_Recognition_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mixture-kernel-graph-attention-network-for |
| Repo | |
| Framework | |
