Paper Group NANR 75
Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension. Evaluation of automatic collocation extraction methods for language learning. How Well Do Embedding Models Capture Non-compositionality? A View from Multiword Expressions. Analytic Score Prediction and Justification Identification in Automated Shor …
Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension
| Title | Enhancing Pre-Trained Language Representations with Rich Knowledge for Machine Reading Comprehension |
| Authors | An Yang, Quan Wang, Jing Liu, Kai Liu, Yajuan Lyu, Hua Wu, Qiaoqiao She, Sujian Li |
| Abstract | Machine reading comprehension (MRC) is a crucial and challenging task in NLP. Recently, pre-trained language models (LMs), especially BERT, have achieved remarkable success, presenting new state-of-the-art results in MRC. In this work, we investigate the potential of leveraging external knowledge bases (KBs) to further improve BERT for MRC. We introduce KT-NET, which employs an attention mechanism to adaptively select desired knowledge from KBs, and then fuses selected knowledge with BERT to enable context- and knowledge-aware predictions. We believe this would combine the merits of both deep LMs and curated KBs towards better MRC. Experimental results indicate that KT-NET offers significant and consistent improvements over BERT, outperforming competitive baselines on ReCoRD and SQuAD1.1 benchmarks. Notably, it ranks the 1st place on the ReCoRD leaderboard, and is also the best single model on the SQuAD1.1 leaderboard at the time of submission (March 4th, 2019). |
| Tasks | Machine Reading Comprehension, Reading Comprehension |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1226/ |
| https://www.aclweb.org/anthology/P19-1226 | |
| PWC | https://paperswithcode.com/paper/enhancing-pre-trained-language |
| Repo | |
| Framework | |
Evaluation of automatic collocation extraction methods for language learning
| Title | Evaluation of automatic collocation extraction methods for language learning |
| Authors | Vishal Bhalla, Klara Klimcikova |
| Abstract | A number of methods have been proposed to automatically extract collocations, i.e., conventionalized lexical combinations, from text corpora. However, the attempts to evaluate and compare them with a specific application in mind lag behind. This paper compares three end-to-end resources for collocation learning, all of which used the same corpus but different methods. Adopting a gold-standard evaluation method, the results show that the method of dependency parsing outperforms regex-over-pos in collocation identification. The lexical association measures (AMs) used for collocation ranking perform about the same overall but differently for individual collocation types. Further analysis has also revealed that there are considerable differences between other commonly used AMs. |
| Tasks | Dependency Parsing |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4428/ |
| https://www.aclweb.org/anthology/W19-4428 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-automatic-collocation |
| Repo | |
| Framework | |
How Well Do Embedding Models Capture Non-compositionality? A View from Multiword Expressions
| Title | How Well Do Embedding Models Capture Non-compositionality? A View from Multiword Expressions |
| Authors | N, Navnita akumar, Timothy Baldwin, Bahar Salehi |
| Abstract | In this paper, we apply various embedding methods on multiword expressions to study how well they capture the nuances of non-compositional data. Our results from a pool of word-, character-, and document-level embbedings suggest that Word2vec performs the best, followed by FastText and Infersent. Moreover, we find that recently-proposed contextualised embedding models such as Bert and ELMo are not adept at handling non-compositionality in multiword expressions. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2004/ |
| https://www.aclweb.org/anthology/W19-2004 | |
| PWC | https://paperswithcode.com/paper/how-well-do-embedding-models-capture-non |
| Repo | |
| Framework | |
Analytic Score Prediction and Justification Identification in Automated Short Answer Scoring
| Title | Analytic Score Prediction and Justification Identification in Automated Short Answer Scoring |
| Authors | Tomoya Mizumoto, Hiroki Ouchi, Yoriko Isobe, Paul Reisert, Ryo Nagata, Satoshi Sekine, Kentaro Inui |
| Abstract | This paper provides an analytical assessment of student short answer responses with a view to potential benefits in pedagogical contexts. We first propose and formalize two novel analytical assessment tasks: analytic score prediction and justification identification, and then provide the first dataset created for analytic short answer scoring research. Subsequently, we present a neural baseline model and report our extensive empirical results to demonstrate how our dataset can be used to explore new and intriguing technical challenges in short answer scoring. The dataset is publicly available for research purposes. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4433/ |
| https://www.aclweb.org/anthology/W19-4433 | |
| PWC | https://paperswithcode.com/paper/analytic-score-prediction-and-justification |
| Repo | |
| Framework | |
Solving the Rubik’s Cube with Approximate Policy Iteration
| Title | Solving the Rubik’s Cube with Approximate Policy Iteration |
| Authors | Stephen McAleer, Forest Agostinelli, Alexander Shmakov, Pierre Baldi |
| Abstract | Recently, Approximate Policy Iteration (API) algorithms have achieved super-human proficiency in two-player zero-sum games such as Go, Chess, and Shogi without human data. These API algorithms iterate between two policies: a slow policy (tree search), and a fast policy (a neural network). In these two-player games, a reward is always received at the end of the game. However, the Rubik’s Cube has only a single solved state, and episodes are not guaranteed to terminate. This poses a major problem for these API algorithms since they rely on the reward received at the end of the game. We introduce Autodidactic Iteration: an API algorithm that overcomes the problem of sparse rewards by training on a distribution of states that allows the reward to propagate from the goal state to states farther away. Autodidactic Iteration is able to learn how to solve the Rubik’s Cube and the 15-puzzle without relying on human data. Our algorithm is able to solve 100% of randomly scrambled cubes while achieving a median solve length of 30 moves — less than or equal to solvers that employ human domain knowledge. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Hyfn2jCcKm |
| https://openreview.net/pdf?id=Hyfn2jCcKm | |
| PWC | https://paperswithcode.com/paper/solving-the-rubiks-cube-with-approximate |
| Repo | |
| Framework | |
Polysemous Language in Child Directed Speech
| Title | Polysemous Language in Child Directed Speech |
| Authors | Sammy Floyd, Libby Barak, Adele Goldberg, Casey Lew-Williams |
| Abstract | Polysemous Language in Child Directed Speech Learning the meaning of words is one of the fundamental building blocks of verbal communication. Models of child language acquisition have generally made the simplifying assumption that each word appears in child-directed speech with a single meaning. To understand naturalistic word learning during childhood, it is essential to know whether children hear input that is in fact constrained to single meaning per word, or whether the environment naturally contains multiple senses.In this study, we use a topic modeling approach to automatically induce word senses from child-directed speech. Our results confirm the plausibility of our automated analysis approach and reveal an increasing rate of using multiple senses in child-directed speech, starting with corpora from children as early as the first year of life. |
| Tasks | Language Acquisition |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3636/ |
| https://www.aclweb.org/anthology/W19-3636 | |
| PWC | https://paperswithcode.com/paper/polysemous-language-in-child-directed-speech |
| Repo | |
| Framework | |
See-Through-Text Grouping for Referring Image Segmentation
| Title | See-Through-Text Grouping for Referring Image Segmentation |
| Authors | Ding-Jie Chen, Songhao Jia, Yi-Chen Lo, Hwann-Tzong Chen, Tyng-Luh Liu |
| Abstract | Motivated by the conventional grouping techniques to image segmentation, we develop their DNN counterpart to tackle the referring variant. The proposed method is driven by a convolutional-recurrent neural network (ConvRNN) that iteratively carries out top-down processing of bottom-up segmentation cues. Given a natural language referring expression, our method learns to predict its relevance to each pixel and derives a See-through-Text Embedding Pixelwise (STEP) heatmap, which reveals segmentation cues of pixel level via the learned visual-textual co-embedding. The ConvRNN performs a top-down approximation by converting the STEP heatmap into a refined one, whereas the improvement is expected from training the network with a classification loss from the ground truth. With the refined heatmap, we update the textual representation of the referring expression by re-evaluating its attention distribution and then compute a new STEP heatmap as the next input to the ConvRNN. Boosting by such collaborative learning, the framework can progressively and simultaneously yield the desired referring segmentation and reasonable attention distribution over the referring sentence. Our method is general and does not rely on, say, the outcomes of object detection from other DNN models, while achieving state-of-the-art performance in all of the four datasets in the experiments. |
| Tasks | Object Detection, Semantic Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Chen_See-Through-Text_Grouping_for_Referring_Image_Segmentation_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Chen_See-Through-Text_Grouping_for_Referring_Image_Segmentation_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/see-through-text-grouping-for-referring-image |
| Repo | |
| Framework | |
Measuring Text Complexity for Italian as a Second Language Learning Purposes
| Title | Measuring Text Complexity for Italian as a Second Language Learning Purposes |
| Authors | Luciana Forti, Alfredo Milani, Luisa Piersanti, Filippo Santarelli, Valentino Santucci, Stefania Spina |
| Abstract | The selection of texts for second language learning purposes typically relies on teachers{'} and test developers{'} individual judgment of the observable qualitative properties of a text. Little or no consideration is generally given to the quantitative dimension within an evidence-based framework of reproducibility. This study aims to fill the gap by evaluating the effectiveness of an automatic tool trained to assess text complexity in the context of Italian as a second language learning. A dataset of texts labeled by expert test developers was used to evaluate the performance of three classifier models (decision tree, random forest, and support vector machine), which were trained using linguistic features measured quantitatively and extracted from the texts. The experimental analysis provided satisfactory results, also in relation to which kind of linguistic trait contributed the most to the final outcome. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4438/ |
| https://www.aclweb.org/anthology/W19-4438 | |
| PWC | https://paperswithcode.com/paper/measuring-text-complexity-for-italian-as-a |
| Repo | |
| Framework | |
Saagie at Semeval-2019 Task 5: From Universal Text Embeddings and Classical Features to Domain-specific Text Classification
| Title | Saagie at Semeval-2019 Task 5: From Universal Text Embeddings and Classical Features to Domain-specific Text Classification |
| Authors | Miriam Benballa, Sebastien Collet, Romain Picot-Clemente |
| Abstract | This paper describes our contribution to SemEval 2019 Task 5: Hateval. We propose to investigate how domain-specific text classification task can benefit from pretrained state of the art language models and how they can be combined with classical handcrafted features. For this purpose, we propose an approach based on a feature-level Meta-Embedding to let the model choose which features to keep and how to use them. |
| Tasks | Text Classification |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2083/ |
| https://www.aclweb.org/anthology/S19-2083 | |
| PWC | https://paperswithcode.com/paper/saagie-at-semeval-2019-task-5-from-universal |
| Repo | |
| Framework | |
HATERecognizer at SemEval-2019 Task 5: Using Features and Neural Networks to Face Hate Recognition
| Title | HATERecognizer at SemEval-2019 Task 5: Using Features and Neural Networks to Face Hate Recognition |
| Authors | Victor Nina-Alcocer |
| Abstract | This paper presents a detailed description of our participation in task 5 on SemEval-2019. This task consists of classifying English and Spanish tweets that contain hate towards women or immigrants. We carried out several experiments; for a finer-grained study of the task, we analyzed different features and designing architectures of neural networks. Additionally, to face the lack of hate content in tweets, we include data augmentation as a technique to in- crease hate content in our datasets. |
| Tasks | Data Augmentation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2072/ |
| https://www.aclweb.org/anthology/S19-2072 | |
| PWC | https://paperswithcode.com/paper/haterecognizer-at-semeval-2019-task-5-using |
| Repo | |
| Framework | |
Few-shot Classification on Graphs with Structural Regularized GCNs
| Title | Few-shot Classification on Graphs with Structural Regularized GCNs |
| Authors | Shengzhong Zhang, Ziang Zhou, Zengfeng Huang, Zhongyu Wei |
| Abstract | We consider the fundamental problem of semi-supervised node classification in attributed graphs with a focus on \emph{few-shot} learning. Here, we propose Structural Regularized Graph Convolutional Networks (SRGCN), novel neural network architectures extending the well-known GCN structures by stacking transposed convolutional layers for reconstruction of input features. We add a reconstruction error term in the loss function as a regularizer. Unlike standard regularization such as $L_1$ or $L_2$, which controls the model complexity by including a penalty term depends solely on parameters, our regularization function is parameterized by a trainable neural network whose structure depends on the topology of the underlying graph. The new approach effectively addresses the shortcomings of previous graph convolution-based techniques for learning classifiers in the few-shot regime and significantly improves generalization performance over original GCNs when the number of labeled samples is insufficient. Experimental studies on three challenging benchmarks demonstrate that the proposed approach has matched state-of-the-art results and can improve classification accuracies by a notable margin when there are very few examples from each class. |
| Tasks | Few-Shot Learning, Node Classification |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1znKiAcY7 |
| https://openreview.net/pdf?id=r1znKiAcY7 | |
| PWC | https://paperswithcode.com/paper/few-shot-classification-on-graphs-with |
| Repo | |
| Framework | |
On Sanskrit and Information Retrieval
| Title | On Sanskrit and Information Retrieval |
| Authors | Micha{"e}l Meyer |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-7507/ |
| https://www.aclweb.org/anthology/W19-7507 | |
| PWC | https://paperswithcode.com/paper/on-sanskrit-and-information-retrieval |
| Repo | |
| Framework | |
Learning Heuristics for Automated Reasoning through Reinforcement Learning
| Title | Learning Heuristics for Automated Reasoning through Reinforcement Learning |
| Authors | Gil Lederman, Markus N. Rabe, Edward A. Lee, Sanjit A. Seshia |
| Abstract | We demonstrate how to learn efficient heuristics for automated reasoning algorithms through deep reinforcement learning. We focus on backtracking search algorithms for quantified Boolean logics, which already can solve formulas of impressive size - up to 100s of thousands of variables. The main challenge is to find a representation of these formulas that lends itself to making predictions in a scalable way. For challenging problems, the heuristic learned through our approach reduces execution time by a factor of 10 compared to the existing handwritten heuristics. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HkeyZhC9F7 |
| https://openreview.net/pdf?id=HkeyZhC9F7 | |
| PWC | https://paperswithcode.com/paper/learning-heuristics-for-automated-reasoning-1 |
| Repo | |
| Framework | |
MVSCRF: Learning Multi-View Stereo With Conditional Random Fields
| Title | MVSCRF: Learning Multi-View Stereo With Conditional Random Fields |
| Authors | Youze Xue, Jiansheng Chen, Weitao Wan, Yiqing Huang, Cheng Yu, Tianpeng Li, Jiayu Bao |
| Abstract | We present a deep-learning architecture for multi-view stereo with conditional random fields (MVSCRF). Given an arbitrary number of input images, we first use a U-shape neural network to extract deep features incorporating both global and local information, and then build a 3D cost volume for the reference camera. Unlike previous learning based methods, we explicitly constraint the smoothness of depth maps by using conditional random fields (CRFs) after the stage of cost volume regularization. The CRFs module is implemented as recurrent neural networks so that the whole pipeline can be trained end-to-end. Our results show that the proposed pipeline outperforms previous state-of-the-arts on large-scale DTU dataset. We also achieve comparable results with state-of-the-art learning based methods on outdoor Tanks and Temples dataset without fine-tuning, which demonstrates our method’s generalization ability. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Xue_MVSCRF_Learning_Multi-View_Stereo_With_Conditional_Random_Fields_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Xue_MVSCRF_Learning_Multi-View_Stereo_With_Conditional_Random_Fields_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/mvscrf-learning-multi-view-stereo-with |
| Repo | |
| Framework | |
Using time series and natural language processing to identify viral moments in the 2016 U.S. Presidential Debate
| Title | Using time series and natural language processing to identify viral moments in the 2016 U.S. Presidential Debate |
| Authors | Josephine Lukito, Prathusha K Sarma, Jordan Foley, Aman Abhishek |
| Abstract | This paper proposes a method for identifying and studying viral moments or highlights during a political debate. Using a combined strategy of time series analysis and domain adapted word embeddings, this study provides an in-depth analysis of several key moments during the 2016 U.S. Presidential election. First, a time series outlier analysis is used to identify key moments during the debate. These moments had to result in a long-term shift in attention towards either Hillary Clinton or Donald Trump (i.e., a transient change outlier or an intervention, resulting in a permanent change in the time series). To assess whether these moments also resulted in a discursive shift, two corpora are produced for each potential viral moment (a pre-viral corpus and post-viral corpus). A domain adaptation layer learns weights to combine a generic and domain-specific (DS) word embedding into a domain adapted (DA) embedding. Words are then classified using a generic encoder+ classifier framework that relies on these word embeddings as inputs. Results suggest that both Clinton and Trump were able to induce discourse-shifting viral moments, though the former is much better at producing a topically-specific discursive shift. |
| Tasks | Domain Adaptation, Time Series, Time Series Analysis, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2107/ |
| https://www.aclweb.org/anthology/W19-2107 | |
| PWC | https://paperswithcode.com/paper/using-time-series-and-natural-language |
| Repo | |
| Framework | |
