Paper Group NANR 137
Delimiting Adverbial Meanings. A corpus-based comparative study on Czech spatial prepositions and their English equivalents. Community Perspective on Replicability in Natural Language Processing. Quantitative Analysis on verb valence evolution of Chinese. Exploring Transfer Learning and Domain Data Selection for the Biomedical Translation. Filterin …
Delimiting Adverbial Meanings. A corpus-based comparative study on Czech spatial prepositions and their English equivalents
| Title | Delimiting Adverbial Meanings. A corpus-based comparative study on Czech spatial prepositions and their English equivalents |
| Authors | Marie Mikulov{'a}, Veronika Kol{'a}{\v{r}}ov{'a}, Jarmila Panevov{'a}, Eva Haji{\v{c}}ov{'a} |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7718/ |
| https://www.aclweb.org/anthology/W19-7718 | |
| PWC | https://paperswithcode.com/paper/delimiting-adverbial-meanings-a-corpus-based |
| Repo | |
| Framework | |
Community Perspective on Replicability in Natural Language Processing
| Title | Community Perspective on Replicability in Natural Language Processing |
| Authors | Margot Mieskes, Kar{"e}n Fort, Aur{'e}lie N{'e}v{'e}ol, Cyril Grouin, Kevin Cohen |
| Abstract | With recent efforts in drawing attention to the task of replicating and/or reproducing results, for example in the context of COLING 2018 and various LREC workshops, the question arises how the NLP community views the topic of replicability in general. Using a survey, in which we involve members of the NLP community, we investigate how our community perceives this topic, its relevance and options for improvement. Based on over two hundred participants, the survey results confirm earlier observations, that successful reproducibility requires more than having access to code and data. Additionally, the results show that the topic has to be tackled from the authors{'}, reviewers{'} and community{'}s side. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1089/ |
| https://www.aclweb.org/anthology/R19-1089 | |
| PWC | https://paperswithcode.com/paper/community-perspective-on-replicability-in |
| Repo | |
| Framework | |
Quantitative Analysis on verb valence evolution of Chinese
| Title | Quantitative Analysis on verb valence evolution of Chinese |
| Authors | Bingli Liu, Chunshan Xu |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7721/ |
| https://www.aclweb.org/anthology/W19-7721 | |
| PWC | https://paperswithcode.com/paper/quantitative-analysis-on-verb-valence |
| Repo | |
| Framework | |
Exploring Transfer Learning and Domain Data Selection for the Biomedical Translation
| Title | Exploring Transfer Learning and Domain Data Selection for the Biomedical Translation |
| Authors | Noor-e- Hira, Sadaf Abdul Rauf, Kiran Kiani, Ammara Zafar, Raheel Nawaz |
| Abstract | Transfer Learning and Selective data training are two of the many approaches being extensively investigated to improve the quality of Neural Machine Translation systems. This paper presents a series of experiments by applying transfer learning and selective data training for participation in the Bio-medical shared task of WMT19. We have used Information Retrieval to selectively choose related sentences from out-of-domain data and used them as additional training data using transfer learning. We also report the effect of tokenization on translation model performance. |
| Tasks | Information Retrieval, Machine Translation, Tokenization, Transfer Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5419/ |
| https://www.aclweb.org/anthology/W19-5419 | |
| PWC | https://paperswithcode.com/paper/exploring-transfer-learning-and-domain-data |
| Repo | |
| Framework | |
Filtering of Noisy Parallel Corpora Based on Hypothesis Generation
| Title | Filtering of Noisy Parallel Corpora Based on Hypothesis Generation |
| Authors | Zuzanna Parcheta, Germ{'a}n Sanchis-Trilles, Francisco Casacuberta |
| Abstract | The filtering task of noisy parallel corpora in WMT2019 aims to challenge participants to create filtering methods to be useful for training machine translation systems. In this work, we introduce a noisy parallel corpora filtering system based on generating hypotheses by means of a translation model. We train translation models in both language pairs: Nepali{–}English and Sinhala{–}English using provided parallel corpora. We select the training subset for three language pairs (Nepali, Sinhala and Hindi to English) jointly using bilingual cross-entropy selection to create the best possible translation model for both language pairs. Once the translation models are trained, we translate the noisy corpora and generate a hypothesis for each sentence pair. We compute the smoothed BLEU score between the target sentence and generated hypothesis. In addition, we apply several rules to discard very noisy or inadequate sentences which can lower the translation score. These heuristics are based on sentence length, source and target similarity and source language detection. We compare our results with the baseline published on the shared task website, which uses the Zipporah model, over which we achieve significant improvements in one of the conditions in the shared task. The designed filtering system is domain independent and all experiments are conducted using neural machine translation. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5439/ |
| https://www.aclweb.org/anthology/W19-5439 | |
| PWC | https://paperswithcode.com/paper/filtering-of-noisy-parallel-corpora-based-on |
| Repo | |
| Framework | |
Deep Asymmetric Metric Learning via Rich Relationship Mining
| Title | Deep Asymmetric Metric Learning via Rich Relationship Mining |
| Authors | Xinyi Xu, Yanhua Yang, Cheng Deng, Feng Zheng |
| Abstract | Learning effective distance metric between data has gained increasing popularity, for its promising performance on various tasks, such as face verification, zero-shot learning, and image retrieval. A major line of researches employs hard data mining, which makes efforts on searching a subset of significant data. However, hard data mining based approaches only rely on a small percentage of data, which is apt to overfitting. This motivates us to propose a novel framework, named deep asymmetric metric learning via rich relationship mining (DAMLRRM), to mine rich relationship under satisfying sampling size. DAMLRRM constructs two asymmetric data streams that are differently structured and of unequal length. The asymmetric structure enables the two data streams to interlace each other, which allows for the informative comparison between new data pairs over iterations. To improve the generalization ability, we further relax the constraint on the intra-class relationship. Rather than greedily connecting all possible positive pairs, DAMLRRM builds a minimum-cost spanning tree within each category to ensure the formation of a connected region. As such there exists at least one direct or indirect path between arbitrary positive pairs to bridge intra-class relevance. Extensive experimental results on three benchmark datasets including CUB-200-2011, Cars196, and Stanford Online Products show that DAMLRRM effectively boosts the performance of existing deep metric learning approaches. |
| Tasks | Face Verification, Image Retrieval, Metric Learning, Zero-Shot Learning |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Xu_Deep_Asymmetric_Metric_Learning_via_Rich_Relationship_Mining_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Xu_Deep_Asymmetric_Metric_Learning_via_Rich_Relationship_Mining_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/deep-asymmetric-metric-learning-via-rich |
| Repo | |
| Framework | |
Discourse-Aware Hierarchical Attention Network for Extractive Single-Document Summarization
| Title | Discourse-Aware Hierarchical Attention Network for Extractive Single-Document Summarization |
| Authors | Tatsuya Ishigaki, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura |
| Abstract | Discourse relations between sentences are often represented as a tree, and the tree structure provides important information for summarizers to create a short and coherent summary. However, current neural network-based summarizers treat the source document as just a sequence of sentences and ignore the tree-like discourse structure inherent in the document. To incorporate the information of a discourse tree structure into the neural network-based summarizers, we propose a discourse-aware neural extractive summarizer which can explicitly take into account the discourse dependency tree structure of the source document. Our discourse-aware summarizer can jointly learn the discourse structure and the salience score of a sentence by using novel hierarchical attention modules, which can be trained on automatically parsed discourse dependency trees. Experimental results showed that our model achieved competitive or better performances against state-of-the-art models in terms of ROUGE scores on the DailyMail dataset. We further conducted manual evaluations. The results showed that our approach also gained the coherence of the output summaries. |
| Tasks | Document Summarization |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1059/ |
| https://www.aclweb.org/anthology/R19-1059 | |
| PWC | https://paperswithcode.com/paper/discourse-aware-hierarchical-attention |
| Repo | |
| Framework | |
Overcoming the bottleneck in traditional assessments of verbal memory: Modeling human ratings and classifying clinical group membership
| Title | Overcoming the bottleneck in traditional assessments of verbal memory: Modeling human ratings and classifying clinical group membership |
| Authors | Ch, Chelsea ler, Peter W. Foltz, Jian Cheng, Jared C. Bernstein, Elizabeth P. Rosenfeld, Alex S. Cohen, Terje B. Holmlund, Brita Elvev{\aa}g |
| Abstract | Verbal memory is affected by numerous clinical conditions and most neuropsychological and clinical examinations evaluate it. However, a bottleneck exists in such endeavors because traditional methods require expert human review, and usually only a couple of test versions exist, thus limiting the frequency of administration and clinical applications. The present study overcomes this bottleneck by automating the administration, transcription, analysis and scoring of story recall. A large group of healthy participants (n = 120) and patients with mental illness (n = 105) interacted with a mobile application that administered a wide range of assessments, including verbal memory. The resulting speech generated by participants when retelling stories from the memory task was transcribed using automatic speech recognition tools, which was compared with human transcriptions (overall word error rate = 21{%}). An assortment of surface-level and semantic language-based features were extracted from the verbal recalls. A final set of three features were used to both predict expert human ratings with a ridge regression model (r = 0.88) and to differentiate patients from healthy individuals with an ensemble of logistic regression classifiers (accuracy = 76{%}). This is the first {`}outside of the laboratory{'} study to showcase the viability of the complete pipeline of automated assessment of verbal memory in naturalistic settings. | |
| Tasks | Speech Recognition |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-3016/ |
| https://www.aclweb.org/anthology/W19-3016 | |
| PWC | https://paperswithcode.com/paper/overcoming-the-bottleneck-in-traditional |
| Repo | |
| Framework | |
Analyzing the use of existing systems for the CLPsych 2019 Shared Task
| Title | Analyzing the use of existing systems for the CLPsych 2019 Shared Task |
| Authors | Alej Gonz{'a}lez Hevia, ro, Rebeca Cerezo Men{'e}ndez, Daniel Gayo-Avello |
| Abstract | In this paper we describe the UniOvi-WESO classification systems proposed for the 2019 Computational Linguistics and Clinical Psychology (CLPsych) Shared Task. We explore the use of two systems trained with ReachOut data from the 2016 CLPsych task, and compare them to a baseline system trained with the data provided for this task. All the classifiers were trained with features extracted just from the text of each post, without using any other metadata. We found out that the baseline system performs slightly better than the pretrained systems, mainly due to the differences in labeling between the two tasks. However, they still work reasonably well and can detect if a user is at risk of suicide or not. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-3017/ |
| https://www.aclweb.org/anthology/W19-3017 | |
| PWC | https://paperswithcode.com/paper/analyzing-the-use-of-existing-systems-for-the |
| Repo | |
| Framework | |
Towards Fine-grained Text Sentiment Transfer
| Title | Towards Fine-grained Text Sentiment Transfer |
| Authors | Fuli Luo, Peng Li, Pengcheng Yang, Jie Zhou, Yutong Tan, Baobao Chang, Zhifang Sui, Xu Sun |
| Abstract | In this paper, we focus on the task of fine-grained text sentiment transfer (FGST). This task aims to revise an input sequence to satisfy a given sentiment intensity, while preserving the original semantic content. Different from the conventional sentiment transfer task that only reverses the sentiment polarity (positive/negative) of text, the FTST task requires more nuanced and fine-grained control of sentiment. To remedy this, we propose a novel Seq2SentiSeq model. Specifically, the numeric sentiment intensity value is incorporated into the decoder via a Gaussian kernel layer to finely control the sentiment intensity of the output. Moreover, to tackle the problem of lacking parallel data, we propose a cycle reinforcement learning algorithm to guide the model training. In this framework, the elaborately designed rewards can balance both sentiment transformation and content preservation, while not requiring any ground truth output. Experimental results show that our approach can outperform existing methods by a large margin in both automatic evaluation and human evaluation. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1194/ |
| https://www.aclweb.org/anthology/P19-1194 | |
| PWC | https://paperswithcode.com/paper/towards-fine-grained-text-sentiment-transfer |
| Repo | |
| Framework | |
Question Generation using a Scratchpad Encoder
| Title | Question Generation using a Scratchpad Encoder |
| Authors | Ryan Y Benmalek, Madian Khabsa, Suma Desu, Claire Cardie, Michele Banko |
| Abstract | In this paper we introduce the Scratchpad Encoder, a novel addition to the sequence to sequence (seq2seq) framework and explore its effectiveness in generating natural language questions from a given logical form. The Scratchpad encoder enables the decoder at each time step to modify all the encoder outputs, thus using the encoder as a “scratchpad” memory to keep track of what has been generated so far and to guide future generation. Experiments on a knowledge based question generation dataset show that our approach generates more fluent and expressive questions according to quantitative metrics and human judgments. |
| Tasks | Question Generation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HklAhi09Y7 |
| https://openreview.net/pdf?id=HklAhi09Y7 | |
| PWC | https://paperswithcode.com/paper/question-generation-using-a-scratchpad |
| Repo | |
| Framework | |
Dependency-Based Relative Positional Encoding for Transformer NMT
| Title | Dependency-Based Relative Positional Encoding for Transformer NMT |
| Authors | Yutaro Omote, Akihiro Tamura, Takashi Ninomiya |
| Abstract | This paper proposes a new Transformer neural machine translation model that incorporates syntactic distances between two source words into the relative position representations of the self-attention mechanism. In particular, the proposed model encodes pair-wise relative depths on a source dependency tree, which are differences between the depths of the two source words, in the encoder{'}s self-attention. The experiments show that our proposed model achieves 0.5 point gain in BLEU on the Asian Scientific Paper Excerpt Corpus Japanese-to-English translation task. |
| Tasks | Machine Translation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1099/ |
| https://www.aclweb.org/anthology/R19-1099 | |
| PWC | https://paperswithcode.com/paper/dependency-based-relative-positional-encoding |
| Repo | |
| Framework | |
Combinatorial Persistency Criteria for Multicut and Max-Cut
| Title | Combinatorial Persistency Criteria for Multicut and Max-Cut |
| Authors | Jan-Hendrik Lange, Bjoern Andres, Paul Swoboda |
| Abstract | In combinatorial optimization, partial variable assignments are called persistent if they agree with some optimal solution. We propose persistency criteria for the multicut and max-cut problem as well as fast combinatorial routines to verify them. The criteria that we derive are based on mappings that improve feasible multicuts, respectively cuts. Our elementary criteria can be checked enumeratively. The more advanced ones rely on fast algorithms for upper and lower bounds for the respective cut problems and max-flow techniques for auxiliary min-cut problems. Our methods can be used as a preprocessing technique for reducing problem sizes or for computing partial optimality guarantees for solutions output by heuristic solvers. We show the efficacy of our methods on instances of both problems from computer vision, biomedical image analysis and statistical physics. |
| Tasks | Combinatorial Optimization |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Lange_Combinatorial_Persistency_Criteria_for_Multicut_and_Max-Cut_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Lange_Combinatorial_Persistency_Criteria_for_Multicut_and_Max-Cut_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/combinatorial-persistency-criteria-for |
| Repo | |
| Framework | |
Using Ontologies To Improve Performance In Massively Multi-label Prediction
| Title | Using Ontologies To Improve Performance In Massively Multi-label Prediction |
| Authors | Ethan Steinberg, Peter J. Liu |
| Abstract | Massively multi-label prediction/classification problems arise in environments like health-care or biology where it is useful to make very precise predictions. One challenge with massively multi-label problems is that there is often a long-tailed frequency distribution for the labels, resulting in few positive examples for the rare labels. We propose a solution to this problem by modifying the output layer of a neural network to create a Bayesian network of sigmoids which takes advantage of ontology relationships between the labels to help share information between the rare and the more common labels. We apply this method to the two massively multi-label tasks of disease prediction (ICD-9 codes) and protein function prediction (Gene Ontology terms) and obtain significant improvements in per-label AUROC and average precision. |
| Tasks | Disease Prediction, Protein Function Prediction |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1g1LoAcFm |
| https://openreview.net/pdf?id=r1g1LoAcFm | |
| PWC | https://paperswithcode.com/paper/using-ontologies-to-improve-performance-in |
| Repo | |
| Framework | |
ArbDialectID at MADAR Shared Task 1: Language Modelling and Ensemble Learning for Fine Grained Arabic Dialect Identification
| Title | ArbDialectID at MADAR Shared Task 1: Language Modelling and Ensemble Learning for Fine Grained Arabic Dialect Identification |
| Authors | Kathrein Abu Kwaik, Motaz Saad |
| Abstract | In this paper, we present a Dialect Identification system (ArbDialectID) that competed at Task 1 of the MADAR shared task, MADARTravel Domain Dialect Identification. We build a course and a fine-grained identification model to predict the label (corresponding to a dialect of Arabic) of a given text. We build two language models by extracting features at two levels (words and characters). We firstly build a coarse identification model to classify each sentence into one out of six dialects, then use this label as a feature for the fine-grained model that classifies the sentence among 26 dialects from different Arab cities, after that we apply ensemble voting classifier on both sub-systems. Our system ranked 1st that achieving an f-score of 67.32{%}. Both the models and our feature engineering tools are made available to the research community. |
| Tasks | Feature Engineering, Language Modelling |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4632/ |
| https://www.aclweb.org/anthology/W19-4632 | |
| PWC | https://paperswithcode.com/paper/arbdialectid-at-madar-shared-task-1-language |
| Repo | |
| Framework | |
