Paper Group NANR 33
Learning with Noise-Contrastive Estimation: Easing training by learning to scale. Siamese Network-Based Supervised Topic Modeling. Automated Content Analysis: A Case Study of Computer Science Student Summaries. Explainable Autonomy: A Study of Explanation Styles for Building Clear Mental Models. Learning representations for sentiment classification …
Learning with Noise-Contrastive Estimation: Easing training by learning to scale
| Title | Learning with Noise-Contrastive Estimation: Easing training by learning to scale |
| Authors | Matthieu Labeau, Alex Allauzen, re |
| Abstract | Noise-Contrastive Estimation (NCE) is a learning criterion that is regularly used to train neural language models in place of Maximum Likelihood Estimation, since it avoids the computational bottleneck caused by the output softmax. In this paper, we analyse and explain some of the weaknesses of this objective function, linked to the mechanism of self-normalization, by closely monitoring comparative experiments. We then explore several remedies and modifications to propose tractable and efficient NCE training strategies. In particular, we propose to make the scaling factor a trainable parameter of the model, and to use the noise distribution to initialize the output bias. These solutions, yet simple, yield stable and competitive performances in either small and large scale language modelling tasks. |
| Tasks | Language Modelling, Machine Translation, Speech Recognition |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1261/ |
| https://www.aclweb.org/anthology/C18-1261 | |
| PWC | https://paperswithcode.com/paper/learning-with-noise-contrastive-estimation |
| Repo | |
| Framework | |
Siamese Network-Based Supervised Topic Modeling
| Title | Siamese Network-Based Supervised Topic Modeling |
| Authors | Minghui Huang, Yanghui Rao, Yuwei Liu, Haoran Xie, Fu Lee Wang |
| Abstract | Label-specific topics can be widely used for supporting personality psychology, aspect-level sentiment analysis, and cross-domain sentiment classification. To generate label-specific topics, several supervised topic models which adopt likelihood-driven objective functions have been proposed. However, it is hard for them to get a precise estimation on both topic discovery and supervised learning. In this study, we propose a supervised topic model based on the Siamese network, which can trade off label-specific word distributions with document-specific label distributions in a uniform framework. Experiments on real-world datasets validate that our model performs competitive in topic discovery quantitatively and qualitatively. Furthermore, the proposed model can effectively predict categorical or real-valued labels for new documents by generating word embeddings from a label-specific topical space. |
| Tasks | Sentiment Analysis, Topic Models, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1494/ |
| https://www.aclweb.org/anthology/D18-1494 | |
| PWC | https://paperswithcode.com/paper/siamese-network-based-supervised-topic |
| Repo | |
| Framework | |
Automated Content Analysis: A Case Study of Computer Science Student Summaries
| Title | Automated Content Analysis: A Case Study of Computer Science Student Summaries |
| Authors | Yanjun Gao, Patricia M. Davies, Rebecca J. Passonneau |
| Abstract | Technology is transforming Higher Education learning and teaching. This paper reports on a project to examine how and why automated content analysis could be used to assess precis writing by university students. We examine the case of one hundred and twenty-two summaries written by computer science freshmen. The texts, which had been hand scored using a teacher-designed rubric, were autoscored using the Natural Language Processing software, PyrEval. Pearson{'}s correlation coefficient and Spearman rank correlation were used to analyze the relationship between the teacher score and the PyrEval score for each summary. Three content models automatically constructed by PyrEval from different sets of human reference summaries led to consistent correlations, showing that the approach is reliable. Also observed was that, in cases where the focus of student assessment centers on formative feedback, categorizing the PyrEval scores by examining the average and standard deviations could lead to novel interpretations of their relationships. It is suggested that this project has implications for the ways in which automated content analysis could be used to help university students improve their summarization skills. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0531/ |
| https://www.aclweb.org/anthology/W18-0531 | |
| PWC | https://paperswithcode.com/paper/automated-content-analysis-a-case-study-of |
| Repo | |
| Framework | |
Explainable Autonomy: A Study of Explanation Styles for Building Clear Mental Models
| Title | Explainable Autonomy: A Study of Explanation Styles for Building Clear Mental Models |
| Authors | Francisco Javier Chiyah Garcia, David A. Robb, Xingkun Liu, Atanas Laskov, Pedro Patron, Helen Hastie |
| Abstract | As unmanned vehicles become more autonomous, it is important to maintain a high level of transparency regarding their behaviour and how they operate. This is particularly important in remote locations where they cannot be directly observed. Here, we describe a method for generating explanations in natural language of autonomous system behaviour and reasoning. Our method involves deriving an interpretable model of autonomy through having an expert {`}speak aloud{'} and providing various levels of detail based on this model. Through an online evaluation study with operators, we show it is best to generate explanations with multiple possible reasons but tersely worded. This work has implications for designing interfaces for autonomy as well as for explainable AI and operator training. | |
| Tasks | Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6511/ |
| https://www.aclweb.org/anthology/W18-6511 | |
| PWC | https://paperswithcode.com/paper/explainable-autonomy-a-study-of-explanation |
| Repo | |
| Framework | |
Learning representations for sentiment classification using Multi-task framework
| Title | Learning representations for sentiment classification using Multi-task framework |
| Authors | Hardik Meisheri, Harshad Khadilkar |
| Abstract | Most of the existing state of the art sentiment classification techniques involve the use of pre-trained embeddings. This paper postulates a generalized representation that collates training on multiple datasets using a Multi-task learning framework. We incorporate publicly available, pre-trained embeddings with Bidirectional LSTM{'}s to develop the multi-task model. We validate the representations on an independent test Irony dataset that can contain several sentiments within each sample, with an arbitrary distribution. Our experiments show a significant improvement in results as compared to the available baselines for individual datasets on which independent models are trained. Results also suggest superior performance of the representations generated over Irony dataset. |
| Tasks | Multi-Task Learning, Sentiment Analysis |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6244/ |
| https://www.aclweb.org/anthology/W18-6244 | |
| PWC | https://paperswithcode.com/paper/learning-representations-for-sentiment |
| Repo | |
| Framework | |
SB@GU at the Complex Word Identification 2018 Shared Task
| Title | SB@GU at the Complex Word Identification 2018 Shared Task |
| Authors | David Alfter, Ildik{'o} Pil{'a}n |
| Abstract | In this paper, we describe our experiments for the Shared Task on Complex Word Identification (CWI) 2018 (Yimam et al., 2018), hosted by the 13th Workshop on Innovative Use of NLP for Building Educational Applications (BEA) at NAACL 2018. Our system for English builds on previous work for Swedish concerning the classification of words into proficiency levels. We investigate different features for English and compare their usefulness using feature selection methods. For the German, Spanish and French data we use simple systems based on character n-gram models and show that sometimes simple models achieve comparable results to fully feature-engineered systems. |
| Tasks | Complex Word Identification, Feature Selection, Language Modelling, Text Simplification, Word Embeddings |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0537/ |
| https://www.aclweb.org/anthology/W18-0537 | |
| PWC | https://paperswithcode.com/paper/sbgu-at-the-complex-word-identification-2018 |
| Repo | |
| Framework | |
A Rule-Based System for Disambiguating French Locative Verbs and Their Translation into Arabic
| Title | A Rule-Based System for Disambiguating French Locative Verbs and Their Translation into Arabic |
| Authors | Safa Boudhina, H{'e}la Fehri |
| Abstract | This paper presents a rule-based system for disambiguating frensh locative verbs and their translation to Arabic language. The disambiguation phase is based on the use of the French Verb dictionary (LVF) of Dubois and Dubois Charlier as a linguistic resource, from which a base of disambiguation rules is extracted. The extracted rules thus take the form of transducers which will be subsequently applied to texts. The translation phase consists in translating the disambiguated locative verbs returned by the disambiguation phase. The translation takes into account the verb{'}s tense used as well as the inflected form of the verb. This phase is based on bilingual dictionaries that contain the different French locative verbs and their translation into the Arabic language. The experimentation and the evaluation are done in the linguistic platform NooJ. The obtained results are satisfactory. |
| Tasks | Machine Translation, Word Sense Disambiguation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-3806/ |
| https://www.aclweb.org/anthology/W18-3806 | |
| PWC | https://paperswithcode.com/paper/a-rule-based-system-for-disambiguating-french |
| Repo | |
| Framework | |
A New Approach to Animacy Detection
| Title | A New Approach to Animacy Detection |
| Authors | Labiba Jahan, Geeticka Chauhan, Mark Finlayson |
| Abstract | Animacy is a necessary property for a referent to be an agent, and thus animacy detection is useful for a variety of natural language processing tasks, including word sense disambiguation, co-reference resolution, semantic role labeling, and others. Prior work treated animacy as a word-level property, and has developed statistical classifiers to classify words as either animate or inanimate. We discuss why this approach to the problem is ill-posed, and present a new approach based on classifying the animacy of co-reference chains. We show that simple voting approaches to inferring the animacy of a chain from its constituent words perform relatively poorly, and then present a hybrid system merging supervised machine learning (ML) and a small number of hand-built rules to compute the animacy of referring expressions and co-reference chains. This method achieves state of the art performance. The supervised ML component leverages features such as word embeddings over referring expressions, parts of speech, and grammatical and semantic roles. The rules take into consideration parts of speech and the hypernymy structure encoded in WordNet. The system achieves an F1 of 0.88 for classifying the animacy of referring expressions, which is comparable to state of the art results for classifying the animacy of words, and achieves an F1 of 0.75 for classifying the animacy of coreference chains themselves. We release our training and test dataset, which includes 142 texts (all narratives) comprising 156,154 words, 34,698 referring expressions, and 10,941 co-reference chains. We test the method on a subset of the OntoNotes dataset, showing using manual sampling that animacy classification is 90{%} +/- 2{%} accurate for coreference chains, and 92{%} +/- 1{%} for referring expressions. The data also contains 46 folktales, which present an interesting challenge because they often involve characters who are members of traditionally inanimate classes (e.g., stoves that walk, trees that talk). We show that our system is able to detect the animacy of these unusual referents with an F1 of 0.95. |
| Tasks | Coreference Resolution, Semantic Role Labeling, Word Embeddings, Word Sense Disambiguation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1001/ |
| https://www.aclweb.org/anthology/C18-1001 | |
| PWC | https://paperswithcode.com/paper/a-new-approach-to-animacy-detection |
| Repo | |
| Framework | |
A Deep Dive into Word Sense Disambiguation with LSTM
| Title | A Deep Dive into Word Sense Disambiguation with LSTM |
| Authors | Minh Le, Marten Postma, Jacopo Urbani, Piek Vossen |
| Abstract | LSTM-based language models have been shown effective in Word Sense Disambiguation (WSD). In particular, the technique proposed by Yuan et al. (2016) returned state-of-the-art performance in several benchmarks, but neither the training data nor the source code was released. This paper presents the results of a reproduction study and analysis of this technique using only openly available datasets (GigaWord, SemCor, OMSTI) and software (TensorFlow). Our study showed that similar results can be obtained with much less data than hinted at by Yuan et al. (2016). Detailed analyses shed light on the strengths and weaknesses of this method. First, adding more unannotated training data is useful, but is subject to diminishing returns. Second, the model can correctly identify both popular and unpopular meanings. Finally, the limited sense coverage in the annotated datasets is a major limitation. All code and trained models are made freely available. |
| Tasks | Language Modelling, Word Sense Disambiguation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1030/ |
| https://www.aclweb.org/anthology/C18-1030 | |
| PWC | https://paperswithcode.com/paper/a-deep-dive-into-word-sense-disambiguation |
| Repo | |
| Framework | |
Synonymy in Bilingual Context: The CzEngClass Lexicon
| Title | Synonymy in Bilingual Context: The CzEngClass Lexicon |
| Authors | Zde{\v{n}}ka Ure{\v{s}}ov{'a}, Eva Fu{\v{c}}{'\i}kov{'a}, Eva Haji{\v{c}}ov{'a}, Jan Haji{\v{c}} |
| Abstract | This paper describes CzEngClass, a bilingual lexical resource being built to investigate verbal synonymy in bilingual context and to relate semantic roles common to one synonym class to verb arguments (verb valency). In addition, the resource is linked to existing resources with the same of a similar aim: English and Czech WordNet, FrameNet, PropBank, VerbNet (SemLink), and valency lexicons for Czech and English (PDT-Vallex, Vallex, and EngVallex). There are several goals of this work and resource: (a) to provide gold standard data for automatic experiments in the future (such as automatic discovery of synonym classes, word sense disambiguation, assignment of classes to occurrences of verbs in text, coreferential linking of verb and event arguments in text, etc.), (b) to build a core (bilingual) lexicon linked to existing resources, for comparative studies and possibly for training automatic tools, and (c) to enrich the annotation of a parallel treebank, the Prague Czech English Dependency Treebank, which so far contained valency annotation but has not linked synonymous senses of verbs together. The method used for extracting the synonym classes is a semi-automatic process with a substantial amount of manual work during filtering, role assignment to classes and individual Class members{'} arguments, and linking to the external lexical resources. We present the first version with 200 classes (about 1800 verbs) and evaluate interannotator agreement using several metrics. |
| Tasks | Word Sense Disambiguation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1208/ |
| https://www.aclweb.org/anthology/C18-1208 | |
| PWC | https://paperswithcode.com/paper/synonymy-in-bilingual-context-the-czengclass |
| Repo | |
| Framework | |
Deep-BGT at PARSEME Shared Task 2018: Bidirectional LSTM-CRF Model for Verbal Multiword Expression Identification
| Title | Deep-BGT at PARSEME Shared Task 2018: Bidirectional LSTM-CRF Model for Verbal Multiword Expression Identification |
| Authors | G{"o}zde Berk, Berna Erden, Tunga G{"u}ng{"o}r |
| Abstract | This paper describes the Deep-BGT system that participated to the PARSEME shared task 2018 on automatic identification of verbal multiword expressions (VMWEs). Our system is language-independent and uses the bidirectional Long Short-Term Memory model with a Conditional Random Field layer on top (bidirectional LSTM-CRF). To the best of our knowledge, this paper is the first one that employs the bidirectional LSTM-CRF model for VMWE identification. Furthermore, the gappy 1-level tagging scheme is used for discontiguity and overlaps. Our system was evaluated on 10 languages in the open track and it was ranked the second in terms of the general ranking metric. |
| Tasks | |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4927/ |
| https://www.aclweb.org/anthology/W18-4927 | |
| PWC | https://paperswithcode.com/paper/deep-bgt-at-parseme-shared-task-2018 |
| Repo | |
| Framework | |
Using Word Embeddings for Unsupervised Acronym Disambiguation
| Title | Using Word Embeddings for Unsupervised Acronym Disambiguation |
| Authors | Jean Charbonnier, Christian Wartena |
| Abstract | Scientific papers from all disciplines contain many abbreviations and acronyms. In many cases these acronyms are ambiguous. We present a method to choose the contextual correct definition of an acronym that does not require training for each acronym and thus can be applied to a large number of different acronyms with only few instances. We constructed a set of 19,954 examples of 4,365 ambiguous acronyms from image captions in scientific papers along with their contextually correct definition from different domains. We learn word embeddings for all words in the corpus and compare the averaged context vector of the words in the expansion of an acronym with the weighted average vector of the words in the context of the acronym. We show that this method clearly outperforms (classical) cosine similarity. Furthermore, we show that word embeddings learned from a 1 billion word corpus of scientific texts outperform word embeddings learned on much large general corpora. |
| Tasks | Image Captioning, Word Embeddings, Word Sense Disambiguation |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1221/ |
| https://www.aclweb.org/anthology/C18-1221 | |
| PWC | https://paperswithcode.com/paper/using-word-embeddings-for-unsupervised |
| Repo | |
| Framework | |
What Makes You Stressed? Finding Reasons From Tweets
| Title | What Makes You Stressed? Finding Reasons From Tweets |
| Authors | Reshmi Gopalakrishna Pillai, Mike Thelwall, Constantin Orasan |
| Abstract | Detecting stress from social media gives a non-intrusive and inexpensive alternative to traditional tools such as questionnaires or physiological sensors for monitoring mental state of individuals. This paper introduces a novel framework for finding reasons for stress from tweets, analyzing multiple categories for the first time. Three word-vector based methods are evaluated on collections of tweets about politics or airlines and are found to be more accurate than standard machine learning algorithms. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6239/ |
| https://www.aclweb.org/anthology/W18-6239 | |
| PWC | https://paperswithcode.com/paper/what-makes-you-stressed-finding-reasons-from |
| Repo | |
| Framework | |
K-means Algorithm Based on Improved Density Peak Algorithm
| Title | K-means Algorithm Based on Improved Density Peak Algorithm |
| Authors | Du Hongbo，Bai Azhenl，Zhu Lijun |
| Abstract | Abstract：The initial clustering centers and the number Of clusters need to be selected manually in traditional K—means al— gorithm，SO the result of clustering is unstable and easy to fall into local optimal solution．To deal with this problem，this paper proposes a K—means algorithm based on the improved algorithm of density peak(DPC)．The proposed algorithm firstly uses the improved DPC algorithm to select the initial clustering center，SO as to make up for the flaw that the random selection of initial elustering center of[k-means]algorithm leads to the easily trapped local optimal solution，and then uses the K-means algorithm to itcrate and introduce the entropy method to calculate the distance to optimize clustering．The result of experiment on the UCI dataset shows that the proposed algorithm can obtain relatively better initial clustering centers and relatively more stable clustering results，with a faster convergence，thus proving the feasibility of the algorithm． |
| Tasks | |
| Published | 2018-02-05 |
| URL | http://g.wanfangdata.com.cn/details/detail.do?_type=perio&id=tjyjc201818004 |
| http://g.wanfangdata.com.cn/details/detail.do?_type=perio&id=tjyjc201818004 | |
| PWC | https://paperswithcode.com/paper/k-means-algorithm-based-on-improved-density |
| Repo | |
| Framework | |
Summarization Evaluation in the Absence of Human Model Summaries Using the Compositionality of Word Embeddings
| Title | Summarization Evaluation in the Absence of Human Model Summaries Using the Compositionality of Word Embeddings |
| Authors | Elaheh ShafieiBavani, Mohammad Ebrahimi, Raymond Wong, Fang Chen |
| Abstract | We present a new summary evaluation approach that does not require human model summaries. Our approach exploits the compositional capabilities of corpus-based and lexical resource-based word embeddings to develop the features reflecting coverage, diversity, informativeness, and coherence of summaries. The features are then used to train a learning model for predicting the summary content quality in the absence of gold models. We evaluate the proposed metric in replicating the human assigned scores for summarization systems and summaries on data from query-focused and update summarization tasks in TAC 2008 and 2009. The results show that our feature combination provides reliable estimates of summary content quality when model summaries are not available. |
| Tasks | Text Summarization, Word Embeddings |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1077/ |
| https://www.aclweb.org/anthology/C18-1077 | |
| PWC | https://paperswithcode.com/paper/summarization-evaluation-in-the-absence-of |
| Repo | |
| Framework | |
