Paper Group NANR 147
IMSurReal: IMS at the Surface Realization Shared Task 2019. Topic-Guided Variational Auto-Encoder for Text Generation. Proceedings of the Natural Legal Language Processing Workshop 2019. The Concordia NLG Surface Realizer at SRST 2019. The DipInfoUniTo Realizer at SRST’19: Learning to Rank and Deep Morphology Prediction for Multilingual Surface Rea …
IMSurReal: IMS at the Surface Realization Shared Task 2019
| Title | IMSurReal: IMS at the Surface Realization Shared Task 2019 |
| Authors | Xiang Yu, Agnieszka Falenska, Marina Haid, Ngoc Thang Vu, Jonas Kuhn |
| Abstract | We introduce the IMS contribution to the Surface Realization Shared Task 2019. Our submission achieves the state-of-the-art performance without using any external resources. The system takes a pipeline approach consisting of five steps: linearization, completion, inflection, contraction, and detokenization. We compare the performance of our linearization algorithm with two external baselines and report results for each step in the pipeline. Furthermore, we perform detailed error analysis revealing correlation between word order freedom and difficulty of the linearization task. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6306/ |
| https://www.aclweb.org/anthology/D19-6306 | |
| PWC | https://paperswithcode.com/paper/imsurreal-ims-at-the-surface-realization |
| Repo | |
| Framework | |
Topic-Guided Variational Auto-Encoder for Text Generation
| Title | Topic-Guided Variational Auto-Encoder for Text Generation |
| Authors | Wenlin Wang, Zhe Gan, Hongteng Xu, Ruiyi Zhang, Guoyin Wang, Dinghan Shen, Changyou Chen, Lawrence Carin |
| Abstract | We propose a topic-guided variational auto-encoder (TGVAE) model for text generation. Distinct from existing variational auto-encoder (VAE) based approaches, which assume a simple Gaussian prior for latent code, our model specifies the prior as a Gaussian mixture model (GMM) parametrized by a neural topic module. Each mixture component corresponds to a latent topic, which provides a guidance to generate sentences under the topic. The neural topic module and the VAE-based neural sequence module in our model are learned jointly. In particular, a sequence of invertible Householder transformations is applied to endow the approximate posterior of the latent code with high flexibility during the model inference. Experimental results show that our TGVAE outperforms its competitors on both unconditional and conditional text generation, which can also generate semantically-meaningful sentences with various topics. |
| Tasks | Text Generation |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1015/ |
| https://www.aclweb.org/anthology/N19-1015 | |
| PWC | https://paperswithcode.com/paper/topic-guided-variational-auto-encoder-for |
| Repo | |
| Framework | |
Proceedings of the Natural Legal Language Processing Workshop 2019
| Title | Proceedings of the Natural Legal Language Processing Workshop 2019 |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2200/ |
| https://www.aclweb.org/anthology/W19-2200 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-natural-legal-language |
| Repo | |
| Framework | |
The Concordia NLG Surface Realizer at SRST 2019
| Title | The Concordia NLG Surface Realizer at SRST 2019 |
| Authors | Farhood Farahnak, Laya Rafiee, Leila Kosseim, Thomas Fevens |
| Abstract | This paper presents the model we developed for the shallow track of the 2019 NLG Surface Realization Shared Task. The model reconstructs sentences whose word order and word inflections were removed. We divided the problem into two sub-problems: reordering and inflecting. For the purpose of reordering, we used a pointer network integrated with a transformer model as its encoder-decoder modules. In order to generate the inflected forms of tokens, a Feed Forward Neural Network was employed. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6308/ |
| https://www.aclweb.org/anthology/D19-6308 | |
| PWC | https://paperswithcode.com/paper/the-concordia-nlg-surface-realizer-at-srst |
| Repo | |
| Framework | |
The DipInfoUniTo Realizer at SRST’19: Learning to Rank and Deep Morphology Prediction for Multilingual Surface Realization
| Title | The DipInfoUniTo Realizer at SRST’19: Learning to Rank and Deep Morphology Prediction for Multilingual Surface Realization |
| Authors | Aless Mazzei, ro, Valerio Basile |
| Abstract | We describe the system presented at the SR{'}19 shared task by the DipInfoUnito team. Our approach is based on supervised machine learning. In particular, we divide the SR task into two independent subtasks, namely word order prediction and morphology inflection prediction. Two neural networks with different architectures run on the same input structure, each producing a partial output which is recombined in the final step in order to produce the predicted surface form. This work is a direct successor of the architecture presented at SR{'}19. |
| Tasks | Learning-To-Rank |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6311/ |
| https://www.aclweb.org/anthology/D19-6311 | |
| PWC | https://paperswithcode.com/paper/the-dipinfounito-realizer-at-srst19-learning |
| Repo | |
| Framework | |
DepDist: Surface realization via regex and learned dependency-distance tolerance
| Title | DepDist: Surface realization via regex and learned dependency-distance tolerance |
| Authors | William Dyer |
| Abstract | This paper describes a method of inflecting and linearizing a lemmatized dependency tree by: (1) determining a regular expression and substitution to describe each productive wordform rule; (2) learning the dependency distance tolerance for each head-dependent pair, resulting in an edge-weighted directed acyclic graph (DAG); and (3) topologically sorting the DAG into a surface realization based on edge weight. The method{'}s output for 11 languages across 18 treebanks is competitive with the other submissions to the Second Multilingual Surface Realization Shared Task (SR {`}19). | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6303/ |
| https://www.aclweb.org/anthology/D19-6303 | |
| PWC | https://paperswithcode.com/paper/depdist-surface-realization-via-regex-and |
| Repo | |
| Framework | |
Social Web Observatory: An entity-driven, holistic information summarization platform across sources
| Title | Social Web Observatory: An entity-driven, holistic information summarization platform across sources |
| Authors | Leonidas Tsekouras, Georgios Petasis, Aris Kosmopoulos |
| Abstract | The Social Web Observatory is an entity-driven, sentiment-aware, event summarization web platform, combining various methods and tools to overview trends across social media and news sources in Greek. SWO crawls, clusters and summarizes information following an entity-centric view of text streams, allowing to monitor the public sentiment towards a specific person, organization or other entity. In this paper, we overview the platform, outline the analysis pipeline and describe a user study aimed to quantify the usefulness of the system and especially the meaningfulness and coherence of discovered events. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8907/ |
| https://www.aclweb.org/anthology/W19-8907 | |
| PWC | https://paperswithcode.com/paper/social-web-observatory-an-entity-driven |
| Repo | |
| Framework | |
Joint Semantic and Distributional Word Representations with Multi-Graph Embeddings
| Title | Joint Semantic and Distributional Word Representations with Multi-Graph Embeddings |
| Authors | Pierre Daix-Moreux, Matthias Gall{'e} |
| Abstract | Word embeddings continue to be of great use for NLP researchers and practitioners due to their training speed and easiness of use and distribution. Prior work has shown that the representation of those words can be improved by the use of semantic knowledge-bases. In this paper we propose a novel way of combining those knowledge-bases while the lexical information of co-occurrences of words remains. It is conceptually clear, as it consists in mapping both distributional and semantic information into a multi-graph and modifying existing node embeddings techniques to compute word representations. Our experiments show improved results compared to vanilla word embeddings, retrofitting and concatenation techniques using the same information, on a variety of data-sets of word similarities. |
| Tasks | Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5314/ |
| https://www.aclweb.org/anthology/D19-5314 | |
| PWC | https://paperswithcode.com/paper/joint-semantic-and-distributional-word |
| Repo | |
| Framework | |
Scalable Methods for Annotating Legal-Decision Corpora
| Title | Scalable Methods for Annotating Legal-Decision Corpora |
| Authors | Lisa Ferro, John Aberdeen, Karl Branting, Craig Pfeifer, Alex Yeh, er, Amartya Chakraborty |
| Abstract | Recent research has demonstrated that judicial and administrative decisions can be predicted by machine-learning models trained on prior decisions. However, to have any practical application, these predictions must be explainable, which in turn requires modeling a rich set of features. Such approaches face a roadblock if the knowledge engineering required to create these features is not scalable. We present an approach to developing a feature-rich corpus of administrative rulings about domain name disputes, an approach which leverages a small amount of manual annotation and prototypical patterns present in the case documents to automatically extend feature labels to the entire corpus. To demonstrate the feasibility of this approach, we report results from systems trained on this dataset. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2202/ |
| https://www.aclweb.org/anthology/W19-2202 | |
| PWC | https://paperswithcode.com/paper/scalable-methods-for-annotating-legal |
| Repo | |
| Framework | |
The Rationality of Semantic Change
| Title | The Rationality of Semantic Change |
| Authors | Omer Korat |
| Abstract | This study investigates the mutual effects over time of semantically related function words on each other{'}s distribution over syntactic environments. Words that can have the same meaning are observed to have opposite trends of change in frequency across different syntactic structures which correspond to the shared meaning. This phenomenon is demonstrated to have a rational basis: it increases communicative efficiency by prioritizing words differently in the environments on which they compete. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4719/ |
| https://www.aclweb.org/anthology/W19-4719 | |
| PWC | https://paperswithcode.com/paper/the-rationality-of-semantic-change |
| Repo | |
| Framework | |
Correcting Whitespace Errors in Digitized Historical Texts
| Title | Correcting Whitespace Errors in Digitized Historical Texts |
| Authors | S Soni, eep, Lauren Klein, Jacob Eisenstein |
| Abstract | Whitespace errors are common to digitized archives. This paper describes a lightweight unsupervised technique for recovering the original whitespace. Our approach is based on count statistics from Google n-grams, which are converted into a likelihood ratio test computed from interpolated trigram and bigram probabilities. To evaluate this approach, we annotate a small corpus of whitespace errors in a digitized corpus of newspapers from the 19th century United States. Our technique identifies and corrects most whitespace errors while introducing a minimal amount of oversegmentation: it achieves 77{%} recall at a false positive rate of less than 1{%}, and 91{%} recall at a false positive rate of less than 3{%}. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2513/ |
| https://www.aclweb.org/anthology/W19-2513 | |
| PWC | https://paperswithcode.com/paper/correcting-whitespace-errors-in-digitized |
| Repo | |
| Framework | |
Eigencharacter: An Embedding of Chinese Character Orthography
| Title | Eigencharacter: An Embedding of Chinese Character Orthography |
| Authors | Yu-Hsiang Tseng, Shu-Kai Hsieh |
| Abstract | Chinese characters are unique in its logographic nature, which inherently encodes world knowledge through thousands of years evolution. This paper proposes an embedding approach, namely eigencharacter (EC) space, which helps NLP application easily access the knowledge encoded in Chinese orthography. These EC representations are automatically extracted, encode both structural and radical information, and easily integrate with other computational models. We built EC representations of 5,000 Chinese characters, investigated orthography knowledge encoded in ECs, and demonstrated how these ECs identified visually similar characters with both structural and radical information. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6404/ |
| https://www.aclweb.org/anthology/D19-6404 | |
| PWC | https://paperswithcode.com/paper/eigencharacter-an-embedding-of-chinese |
| Repo | |
| Framework | |
Soft Q-Learning with Mutual-Information Regularization
| Title | Soft Q-Learning with Mutual-Information Regularization |
| Authors | Jordi Grau-Moya, Felix Leibfried, Peter Vrancx |
| Abstract | We propose a reinforcement learning (RL) algorithm that uses mutual-information regularization to optimize a prior action distribution for better performance and exploration. Entropy-based regularization has previously been shown to improve both exploration and robustness in challenging sequential decision-making tasks. It does so by encouraging policies to put probability mass on all actions. However, entropy regularization might be undesirable when actions have significantly different importance. In this paper, we propose a theoretically motivated framework that dynamically weights the importance of actions by using the mutual-information. In particular, we express the RL problem as an inference problem where the prior probability distribution over actions is subject to optimization. We show that the prior optimization introduces a mutual-information regularizer in the RL objective. This regularizer encourages the policy to be close to a non-uniform distribution that assigns higher probability mass to more important actions. We empirically demonstrate that our method significantly improves over entropy regularization methods and unregularized methods. |
| Tasks | Decision Making, Q-Learning |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HyEtjoCqFX |
| https://openreview.net/pdf?id=HyEtjoCqFX | |
| PWC | https://paperswithcode.com/paper/soft-q-learning-with-mutual-information |
| Repo | |
| Framework | |
Hierarchical User and Item Representation with Three-Tier Attention for Recommendation
| Title | Hierarchical User and Item Representation with Three-Tier Attention for Recommendation |
| Authors | Chuhan Wu, Fangzhao Wu, Junxin Liu, Yongfeng Huang |
| Abstract | Utilizing reviews to learn user and item representations is useful for recommender systems. Existing methods usually merge all reviews from the same user or for the same item into a long document. However, different reviews, sentences and even words usually have different informativeness for modeling users and items. In this paper, we propose a hierarchical user and item representation model with three-tier attention to learn user and item representations from reviews for recommendation. Our model contains three major components, i.e., a sentence encoder to learn sentence representations from words, a review encoder to learn review representations from sentences, and a user/item encoder to learn user/item representations from reviews. In addition, we incorporate a three-tier attention network in our model to select important words, sentences and reviews. Besides, we combine the user and item representations learned from the reviews with user and item embeddings based on IDs as the final representations to capture the latent factors of individual users and items. Extensive experiments on four benchmark datasets validate the effectiveness of our approach. |
| Tasks | Recommendation Systems |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1180/ |
| https://www.aclweb.org/anthology/N19-1180 | |
| PWC | https://paperswithcode.com/paper/hierarchical-user-and-item-representation |
| Repo | |
| Framework | |
Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back-Translation
| Title | Improving Neural Machine Translation Robustness via Data Augmentation: Beyond Back-Translation |
| Authors | Zhenhao Li, Lucia Specia |
| Abstract | Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of {``}domain{''} adaption to noise. The recently created Machine Translation on Noisy Text task corpus provides noisy-clean parallel data for a few language pairs, but this data is very limited in size and diversity. The state-of-the-art approaches are heavily dependent on large volumes of back-translated data. This paper has two main contributions: Firstly, we propose new data augmentation methods to extend limited noisy data and further improve NMT robustness to noise while keeping the models small. Secondly, we explore the effect of utilizing noise from external data in the form of speech transcripts and show that it could help robustness. | |
| Tasks | Data Augmentation, Domain Adaptation, Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5543/ |
| https://www.aclweb.org/anthology/D19-5543 | |
| PWC | https://paperswithcode.com/paper/improving-neural-machine-translation-1 |
| Repo | |
| Framework | |
