Paper Group NANR 224
Comparing Top-Down and Bottom-Up Neural Generative Dependency Models. Pardon the Interruption: Automatic Analysis of Gender and Competitive Turn-Taking in United States Supreme Court Hearings. Summarizing Legal Rulings: Comparative Experiments. A Recurrent BERT-based Model for Question Generation. Learning from Positive and Unlabeled Data with a Se …
Comparing Top-Down and Bottom-Up Neural Generative Dependency Models
| Title | Comparing Top-Down and Bottom-Up Neural Generative Dependency Models |
| Authors | Austin Matthews, Graham Neubig, Chris Dyer |
| Abstract | Recurrent neural network grammars generate sentences using phrase-structure syntax and perform very well on both parsing and language modeling. To explore whether generative dependency models are similarly effective, we propose two new generative models of dependency syntax. Both models use recurrent neural nets to avoid making explicit independence assumptions, but they differ in the order used to construct the trees: one builds the tree bottom-up and the other top-down, which profoundly changes the estimation problem faced by the learner. We evaluate the two models on three typologically different languages: English, Arabic, and Japanese. While both generative models improve parsing performance over a discriminative baseline, they are significantly less effective than non-syntactic LSTM language models. Surprisingly, little difference between the construction orders is observed for either parsing or language modeling. |
| Tasks | Language Modelling |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1022/ |
| https://www.aclweb.org/anthology/K19-1022 | |
| PWC | https://paperswithcode.com/paper/comparing-top-down-and-bottom-up-neural |
| Repo | |
| Framework | |
Pardon the Interruption: Automatic Analysis of Gender and Competitive Turn-Taking in United States Supreme Court Hearings
| Title | Pardon the Interruption: Automatic Analysis of Gender and Competitive Turn-Taking in United States Supreme Court Hearings |
| Authors | Haley Lepp |
| Abstract | The United States Supreme Court plays a key role in defining the legal basis for gender discrimination throughout the country, yet there are few checks on gender bias within the court itself. In conversational turn-taking, interruptions have been documented as a marker of bias between speakers of different genders. The goal of this study is to automatically differentiate between respectful and disrespectful conversational turns taken during official hearings, which could help in detecting bias and finding remediation techniques for discourse in the courtroom. In this paper, I present a corpus of turns annotated by legal professionals, and describe the design of a semi-supervised classifier that will use acoustic and lexical features to analyze turn-taking at scale. On completion of annotations, this classifier will be trained to extract the likelihood that turns are respectful or disrespectful for use in studies of speech trends. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3645/ |
| https://www.aclweb.org/anthology/W19-3645 | |
| PWC | https://paperswithcode.com/paper/pardon-the-interruption-automatic-analysis-of |
| Repo | |
| Framework | |
Summarizing Legal Rulings: Comparative Experiments
| Title | Summarizing Legal Rulings: Comparative Experiments |
| Authors | Diego Feijo, Viviane Moreira |
| Abstract | In the context of text summarization, texts in the legal domain have peculiarities related to their length and to their specialized vocabulary. Recent neural network-based approaches can achieve high-quality scores for text summarization. However, these approaches have been used mostly for generating very short abstracts for news articles. Thus, their applicability to the legal domain remains an open issue. In this work, we experimented with ten extractive and four abstractive models in a real dataset of legal rulings. These models were compared with an extractive baseline based on heuristics to select the most relevant parts of the text. Our results show that abstractive approaches significantly outperform extractive methods in terms of ROUGE scores. |
| Tasks | Text Summarization |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1036/ |
| https://www.aclweb.org/anthology/R19-1036 | |
| PWC | https://paperswithcode.com/paper/summarizing-legal-rulings-comparative |
| Repo | |
| Framework | |
A Recurrent BERT-based Model for Question Generation
| Title | A Recurrent BERT-based Model for Question Generation |
| Authors | Ying-Hong Chan, Yao-Chung Fan |
| Abstract | In this study, we investigate the employment of the pre-trained BERT language model to tackle question generation tasks. We introduce three neural architectures built on top of BERT for question generation tasks. The first one is a straightforward BERT employment, which reveals the defects of directly using BERT for text generation. Accordingly, we propose another two models by restructuring our BERT employment into a sequential manner for taking information from previous decoded results. Our models are trained and evaluated on the recent question-answering dataset SQuAD. Experiment results show that our best model yields state-of-the-art performance which advances the BLEU 4 score of the existing best models from 16.85 to 22.17. |
| Tasks | Language Modelling, Question Answering, Question Generation, Text Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5821/ |
| https://www.aclweb.org/anthology/D19-5821 | |
| PWC | https://paperswithcode.com/paper/a-recurrent-bert-based-model-for-question |
| Repo | |
| Framework | |
Learning from Positive and Unlabeled Data with a Selection Bias
| Title | Learning from Positive and Unlabeled Data with a Selection Bias |
| Authors | Masahiro Kato, Takeshi Teshima, Junya Honda |
| Abstract | We consider the problem of learning a binary classifier only from positive data and unlabeled data (PU learning). Recent methods of PU learning commonly assume that the labeled positive data are identically distributed as the unlabeled positive data. However, this assumption is unrealistic in many instances of PU learning because it fails to capture the existence of a selection bias in the labeling process. When the data has a selection bias, it is difficult to learn the Bayes optimal classifier by conventional methods of PU learning. In this paper, we propose a method to partially identify the classifier. The proposed algorithm learns a scoring function that preserves the order induced by the class posterior under mild assumptions, which can be used as a classifier by setting an appropriate threshold. Through experiments, we show that the method outperforms previous methods for PU learning on various real-world datasets. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=rJzLciCqKm |
| https://openreview.net/pdf?id=rJzLciCqKm | |
| PWC | https://paperswithcode.com/paper/learning-from-positive-and-unlabeled-data-1 |
| Repo | |
| Framework | |
Diversity-aware Event Prediction based on a Conditional Variational Autoencoder with Reconstruction
| Title | Diversity-aware Event Prediction based on a Conditional Variational Autoencoder with Reconstruction |
| Authors | Hirokazu Kiyomaru, Kazumasa Omura, Yugo Murawaki, Daisuke Kawahara, Sadao Kurohashi |
| Abstract | Typical event sequences are an important class of commonsense knowledge. Formalizing the task as the generation of a next event conditioned on a current event, previous work in event prediction employs sequence-to-sequence (seq2seq) models. However, what can happen after a given event is usually diverse, a fact that can hardly be captured by deterministic models. In this paper, we propose to incorporate a conditional variational autoencoder (CVAE) into seq2seq for its ability to represent diverse next events as a probabilistic distribution. We further extend the CVAE-based seq2seq with a reconstruction mechanism to prevent the model from concentrating on highly typical events. To facilitate fair and systematic evaluation of the diversity-aware models, we also extend existing evaluation datasets by tying each current event to multiple next events. Experiments show that the CVAE-based models drastically outperform deterministic models in terms of precision and that the reconstruction mechanism improves the recall of CVAE-based models without sacrificing precision. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6014/ |
| https://www.aclweb.org/anthology/D19-6014 | |
| PWC | https://paperswithcode.com/paper/diversity-aware-event-prediction-based-on-a |
| Repo | |
| Framework | |
Distributional Effects of Gender Contrasts Across Categories
| Title | Distributional Effects of Gender Contrasts Across Categories |
| Authors | Timothee Mickus, Olivier Bonami, Denis Paperno |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0118/ |
| https://www.aclweb.org/anthology/W19-0118 | |
| PWC | https://paperswithcode.com/paper/distributional-effects-of-gender-contrasts |
| Repo | |
| Framework | |
Case assignment in TSL syntax: a case study
| Title | Case assignment in TSL syntax: a case study |
| Authors | Mai Ha Vu, Nazila Shafiei, Thomas Graf |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0127/ |
| https://www.aclweb.org/anthology/W19-0127 | |
| PWC | https://paperswithcode.com/paper/case-assignment-in-tsl-syntax-a-case-study |
| Repo | |
| Framework | |
Are formal restrictions on crossing dependencies epiphenominal?
| Title | Are formal restrictions on crossing dependencies epiphenominal? |
| Authors | Himanshu Yadav, Samar Husain, Richard Futrell |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7802/ |
| https://www.aclweb.org/anthology/W19-7802 | |
| PWC | https://paperswithcode.com/paper/are-formal-restrictions-on-crossing |
| Repo | |
| Framework | |
Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation
| Title | Automatically Extracting Challenge Sets for Non-Local Phenomena in Neural Machine Translation |
| Authors | Leshem Choshen, Omri Abend |
| Abstract | We show that the state-of-the-art Transformer MT model is not biased towards monotonic reordering (unlike previous recurrent neural network models), but that nevertheless, long-distance dependencies remain a challenge for the model. Since most dependencies are short-distance, common evaluation metrics will be little influenced by how well systems perform on them. We therefore propose an automatic approach for extracting challenge sets rich with long-distance dependencies, and argue that evaluation using this methodology provides a complementary perspective on system performance. To support our claim, we compile challenge sets for English-German and German-English, which are much larger than any previously released challenge set for MT. The extracted sets are large enough to allow reliable automatic evaluation, which makes the proposed approach a scalable and practical solution for evaluating MT performance on the long-tail of syntactic phenomena. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1028/ |
| https://www.aclweb.org/anthology/K19-1028 | |
| PWC | https://paperswithcode.com/paper/automatically-extracting-challenge-sets-for-1 |
| Repo | |
| Framework | |
Distributional Semantics Meets Construction Grammar. towards a Unified Usage-Based Model of Grammar and Meaning
| Title | Distributional Semantics Meets Construction Grammar. towards a Unified Usage-Based Model of Grammar and Meaning |
| Authors | Giulia Rambelli, Emmanuele Chersoni, Philippe Blache, Chu-Ren Huang, Aless Lenci, ro |
| Abstract | In this paper, we propose a new type of semantic representation of Construction Grammar that combines constructions with the vector representations used in Distributional Semantics. We introduce a new framework, Distributional Construction Grammar, where grammar and meaning are systematically modeled from language use, and finally, we discuss the kind of contributions that distributional models can provide to CxG representation from a linguistic and cognitive perspective. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3312/ |
| https://www.aclweb.org/anthology/W19-3312 | |
| PWC | https://paperswithcode.com/paper/distributional-semantics-meets-construction |
| Repo | |
| Framework | |
Detecting Subevents using Discourse and Narrative Features
| Title | Detecting Subevents using Discourse and Narrative Features |
| Authors | Mohammed Aldawsari, Mark Finlayson |
| Abstract | Recognizing the internal structure of events is a challenging language processing task of great importance for text understanding. We present a supervised model for automatically identifying when one event is a subevent of another. Building on prior work, we introduce several novel features, in particular discourse and narrative features, that significantly improve upon prior state-of-the-art performance. Error analysis further demonstrates the utility of these features. We evaluate our model on the only two annotated corpora with event hierarchies: HiEve and the Intelligence Community corpus. No prior system has been evaluated on both corpora. Our model outperforms previous systems on both corpora, achieving 0.74 BLANC F1 on the Intelligence Community corpus and 0.70 F1 on the HiEve corpus, respectively a 15 and 5 percentage point improvement over previous models. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1471/ |
| https://www.aclweb.org/anthology/P19-1471 | |
| PWC | https://paperswithcode.com/paper/detecting-subevents-using-discourse-and |
| Repo | |
| Framework | |
Ensemble Deep Manifold Similarity Learning Using Hard Proxies
| Title | Ensemble Deep Manifold Similarity Learning Using Hard Proxies |
| Authors | Nicolas Aziere, Sinisa Todorovic |
| Abstract | This paper is about learning deep representations of images such that images belonging to the same class have more similar representations than those belonging to different classes. For this goal, prior work typically uses the triplet or N-pair loss, specified in terms of either l2-distances or dot-products between deep features. However, such formulations seem poorly suited to the highly non-Euclidean deep feature space. Our first contribution is in specifying the N-pair loss in terms of manifold similarities between deep features. We introduce a new time- and memory-efficient method for estimating the manifold similarities by using a closed-form convergence solution of the Random Walk algorithm. Our efficiency comes, in part, from following the recent work that randomly partitions the deep feature space, and expresses image distances via representatives of the resulting subspaces, a.k.a. proxies. Our second contribution is aimed at reducing overfitting by estimating hard proxies that are as close to one another as possible, but remain in their respective subspaces. Our evaluation demonstrates that we outperform the state of the art in both image retrieval and clustering on the benchmark CUB-200-2011, Cars196, and Stanford Online Products datasets. |
| Tasks | Image Retrieval |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Aziere_Ensemble_Deep_Manifold_Similarity_Learning_Using_Hard_Proxies_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Aziere_Ensemble_Deep_Manifold_Similarity_Learning_Using_Hard_Proxies_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/ensemble-deep-manifold-similarity-learning |
| Repo | |
| Framework | |
Quantifiers in a Multimodal World: Hallucinating Vision with Language and Sound
| Title | Quantifiers in a Multimodal World: Hallucinating Vision with Language and Sound |
| Authors | Alberto Testoni, S Pezzelle, ro, Raffaella Bernardi |
| Abstract | Inspired by the literature on multisensory integration, we develop a computational model to ground quantifiers in perception. The model learns to pick, out of nine quantifiers ({}few{'}, {}many{'}, {}all{'}, etc.), the one that is more likely to describe the percent of animals in a visual-auditory input containing both animals and artifacts. We show that relying on concurrent sensory inputs increases model performance on the quantification task. Moreover, we evaluate the model in a situation in which only the auditory modality is given, while the visual one is {}hallucinanted{'} either from the auditory input itself or from a linguistic caption describing the quantity of entities in the auditory input. This way, the model exploits prior associations between modalities. We show that the model profits from the prior knowledge and outperforms the auditory-only setting. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2912/ |
| https://www.aclweb.org/anthology/W19-2912 | |
| PWC | https://paperswithcode.com/paper/quantifiers-in-a-multimodal-world |
| Repo | |
| Framework | |
YouMakeup: A Large-Scale Domain-Specific Multimodal Dataset for Fine-Grained Semantic Comprehension
| Title | YouMakeup: A Large-Scale Domain-Specific Multimodal Dataset for Fine-Grained Semantic Comprehension |
| Authors | Weiying Wang, Yongcheng Wang, Shizhe Chen, Qin Jin |
| Abstract | Multimodal semantic comprehension has attracted increasing research interests recently such as visual question answering and caption generation. However, due to the data limitation, fine-grained semantic comprehension has not been well investigated, which requires to capture semantic details of multimodal contents. In this work, we introduce {``}YouMakeup{''}, a large-scale multimodal instructional video dataset to support fine-grained semantic comprehension research in specific domain. YouMakeup contains 2,800 videos from YouTube, spanning more than 420 hours in total. Each video is annotated with a sequence of natural language descriptions for instructional steps, grounded in temporal video range and spatial facial areas. The annotated steps in a video involve subtle difference in actions, products and regions, which requires fine-grained understanding and reasoning both temporally and spatially. In order to evaluate models{'} ability for fined-grained comprehension, we further propose two groups of tasks including generation tasks and visual question answering from different aspects. We also establish a baseline of step caption generation for future comparison. The dataset will be publicly available at https://github. com/AIM3-RUC/YouMakeup to support research investigation in fine-grained semantic comprehension. | |
| Tasks | Question Answering, Visual Question Answering |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1517/ |
| https://www.aclweb.org/anthology/D19-1517 | |
| PWC | https://paperswithcode.com/paper/youmakeup-a-large-scale-domain-specific |
| Repo | |
| Framework | |
