Paper Group NANR 134
Exploring Variation of Natural Human Commands to a Robot in a Collaborative Navigation Task. Parametric Simplex Method for Sparse Learning. ``Deep’’ Learning : Detecting Metaphoricity in Adjective-Noun Pairs. Modeling Communicative Purpose with Functional Style: Corpus and Features for German Genre and Register Analysis. Analysing the Causes of Dep …
Exploring Variation of Natural Human Commands to a Robot in a Collaborative Navigation Task
| Title | Exploring Variation of Natural Human Commands to a Robot in a Collaborative Navigation Task |
| Authors | Matthew Marge, Claire Bonial, Ashley Foots, Cory Hayes, Cassidy Henry, Kimberly Pollard, Ron Artstein, Clare Voss, David Traum |
| Abstract | Robot-directed communication is variable, and may change based on human perception of robot capabilities. To collect training data for a dialogue system and to investigate possible communication changes over time, we developed a Wizard-of-Oz study that (a) simulates a robot{'}s limited understanding, and (b) collects dialogues where human participants build a progressively better mental model of the robot{'}s understanding. With ten participants, we collected ten hours of human-robot dialogue. We analyzed the structure of instructions that participants gave to a remote robot before it responded. Our findings show a general initial preference for including metric information (e.g., move forward 3 feet) over landmarks (e.g., move to the desk) in motion commands, but this decreased over time, suggesting changes in perception. |
| Tasks | |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/W17-2808/ |
| https://www.aclweb.org/anthology/W17-2808 | |
| PWC | https://paperswithcode.com/paper/exploring-variation-of-natural-human-commands |
| Repo | |
| Framework | |
Parametric Simplex Method for Sparse Learning
| Title | Parametric Simplex Method for Sparse Learning |
| Authors | Haotian Pang, Han Liu, Robert J. Vanderbei, Tuo Zhao |
| Abstract | High dimensional sparse learning has imposed a great computational challenge to large scale data analysis. In this paper, we investiage a broad class of sparse learning approaches formulated as linear programs parametrized by a {\em regularization factor}, and solve them by the parametric simplex method (PSM). PSM offers significant advantages over other competing methods: (1) PSM naturally obtains the complete solution path for all values of the regularization parameter; (2) PSM provides a high precision dual certificate stopping criterion; (3) PSM yields sparse solutions through very few iterations, and the solution sparsity significantly reduces the computational cost per iteration. Particularly, we demonstrate the superiority of PSM over various sparse learning approaches, including Dantzig selector for sparse linear regression, sparse support vector machine for sparse linear classification, and sparse differential network estimation. We then provide sufficient conditions under which PSM always outputs sparse solutions such that its computational performance can be significantly boosted. Thorough numerical experiments are provided to demonstrate the outstanding performance of the PSM method. |
| Tasks | Sparse Learning |
| Published | 2017-12-01 |
| URL | http://papers.nips.cc/paper/6623-parametric-simplex-method-for-sparse-learning |
| http://papers.nips.cc/paper/6623-parametric-simplex-method-for-sparse-learning.pdf | |
| PWC | https://paperswithcode.com/paper/parametric-simplex-method-for-sparse-learning |
| Repo | |
| Framework | |
``Deep’’ Learning : Detecting Metaphoricity in Adjective-Noun Pairs
| Title | ``Deep’’ Learning : Detecting Metaphoricity in Adjective-Noun Pairs | |
| Authors | Yuri Bizzoni, Stergios Chatzikyriakidis, Mehdi Ghanimifard |
| Abstract | Metaphor is one of the most studied and widespread figures of speech and an essential element of individual style. In this paper we look at metaphor identification in Adjective-Noun pairs. We show that using a single neural network combined with pre-trained vector embeddings can outperform the state of the art in terms of accuracy. In specific, the approach presented in this paper is based on two ideas: a) transfer learning via using pre-trained vectors representing adjective noun pairs, and b) a neural network as a model of composition that predicts a metaphoricity score as output. We present several different architectures for our system and evaluate their performances. Variations on dataset size and on the kinds of embeddings are also investigated. We show considerable improvement over the previous approaches both in terms of accuracy and w.r.t the size of annotated training data. |
| Tasks | Transfer Learning |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4906/ |
| https://www.aclweb.org/anthology/W17-4906 | |
| PWC | https://paperswithcode.com/paper/deep-learning-detecting-metaphoricity-in |
| Repo | |
| Framework | |
Modeling Communicative Purpose with Functional Style: Corpus and Features for German Genre and Register Analysis
| Title | Modeling Communicative Purpose with Functional Style: Corpus and Features for German Genre and Register Analysis |
| Authors | Thomas Haider, Alexis Palmer |
| Abstract | While there is wide acknowledgement in NLP of the utility of document characterization by genre, it is quite difficult to determine a definitive set of features or even a comprehensive list of genres. This paper addresses both issues. First, with prototype semantics, we develop a hierarchical taxonomy of discourse functions. We implement the taxonomy by developing a new text genre corpus of contemporary German to perform a text based comparative register analysis. Second, we extract a host of style features, both deep and shallow, aiming beyond linguistically motivated features at situational correlates in texts. The feature sets are used for supervised text genre classification, on which our models achieve high accuracy. The combination of the corpus typology and feature sets allows us to characterize types of communicative purpose in a comparative setup, by qualitative interpretation of style feature loadings of a regularized discriminant analysis. Finally, to determine the dependence of genre on topics (which are arguably the distinguishing factor of sub-genre), we compare and combine our style models with Latent Dirichlet Allocation features across different corpus settings with unstable topics. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4910/ |
| https://www.aclweb.org/anthology/W17-4910 | |
| PWC | https://paperswithcode.com/paper/modeling-communicative-purpose-with |
| Repo | |
| Framework | |
Analysing the Causes of Depressed Mood from Depression Vulnerable Individuals
| Title | Analysing the Causes of Depressed Mood from Depression Vulnerable Individuals |
| Authors | Noor Fazilla Abd Yusof, Chenghua Lin, Frank Guerin |
| Abstract | We develop a computational model to discover the potential causes of depression by analysing the topics in a usergenerated text. We show the most prominent causes, and how these causes evolve over time. Also, we highlight the differences in causes between students with low and high neuroticism. Our studies demonstrate that the topics reveal valuable clues about the causes contributing to depressed mood. Identifying causes can have a significant impact on improving the quality of depression care; thereby providing greater insights into a patient{'}s state for pertinent treatment recommendations. Hence, this study significantly expands the ability to discover the potential factors that trigger depression, making it possible to increase the efficiency of depression treatment. |
| Tasks | |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/W17-5802/ |
| https://www.aclweb.org/anthology/W17-5802 | |
| PWC | https://paperswithcode.com/paper/analysing-the-causes-of-depressed-mood-from |
| Repo | |
| Framework | |
Word Embeddings for Multi-label Document Classification
| Title | Word Embeddings for Multi-label Document Classification |
| Authors | Ladislav Lenc, Pavel Kr{'a}l |
| Abstract | In this paper, we analyze and evaluate word embeddings for representation of longer texts in the multi-label classification scenario. The embeddings are used in three convolutional neural network topologies. The experiments are realized on the Czech {\v{C}}TK and English Reuters-21578 standard corpora. We compare the results of word2vec static and trainable embeddings with randomly initialized word vectors. We conclude that initialization does not play an important role for classification. However, learning of word vectors is crucial to obtain good results. |
| Tasks | Document Classification, Multi-Label Classification, Sentiment Analysis, Text Classification, Word Embeddings |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/R17-1057/ |
| https://doi.org/10.26615/978-954-452-049-6_057 | |
| PWC | https://paperswithcode.com/paper/word-embeddings-for-multi-label-document |
| Repo | |
| Framework | |
Coreference Resolution on Math Problem Text in Japanese
| Title | Coreference Resolution on Math Problem Text in Japanese |
| Authors | Takumi Ito, Takuya Matsuzaki, Satoshi Sato |
| Abstract | This paper describes a coreference resolution system for math problem text. Case frame dictionaries and a math taxonomy are utilized for supplying domain knowledge. The system deals with various anaphoric phenomena beyond well-studied entity coreferences. |
| Tasks | Coreference Resolution |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2063/ |
| https://www.aclweb.org/anthology/I17-2063 | |
| PWC | https://paperswithcode.com/paper/coreference-resolution-on-math-problem-text |
| Repo | |
| Framework | |
Semantic Features Based on Word Alignments for Estimating Quality of Text Simplification
| Title | Semantic Features Based on Word Alignments for Estimating Quality of Text Simplification |
| Authors | Tomoyuki Kajiwara, Atsushi Fujita |
| Abstract | This paper examines the usefulness of semantic features based on word alignments for estimating the quality of text simplification. Specifically, we introduce seven types of alignment-based features computed on the basis of word embeddings and paraphrase lexicons. Through an empirical experiment using the QATS dataset, we confirm that we can achieve the state-of-the-art performance only with these features. |
| Tasks | Machine Translation, Reading Comprehension, Semantic Textual Similarity, Text Generation, Text Simplification, Word Embeddings |
| Published | 2017-11-01 |
| URL | https://www.aclweb.org/anthology/I17-2019/ |
| https://www.aclweb.org/anthology/I17-2019 | |
| PWC | https://paperswithcode.com/paper/semantic-features-based-on-word-alignments |
| Repo | |
| Framework | |
Assessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution
| Title | Assessing the Stylistic Properties of Neurally Generated Text in Authorship Attribution |
| Authors | Enrique Manjavacas, Jeroen De Gussem, Walter Daelemans, Mike Kestemont |
| Abstract | Recent applications of neural language models have led to an increased interest in the automatic generation of natural language. However impressive, the evaluation of neurally generated text has so far remained rather informal and anecdotal. Here, we present an attempt at the systematic assessment of one aspect of the quality of neurally generated text. We focus on a specific aspect of neural language generation: its ability to reproduce authorial writing styles. Using established models for authorship attribution, we empirically assess the stylistic qualities of neurally generated text. In comparison to conventional language models, neural models generate fuzzier text, that is relatively harder to attribute correctly. Nevertheless, our results also suggest that neurally generated text offers more valuable perspectives for the augmentation of training data. |
| Tasks | Data Augmentation, Language Modelling, Text Generation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4914/ |
| https://www.aclweb.org/anthology/W17-4914 | |
| PWC | https://paperswithcode.com/paper/assessing-the-stylistic-properties-of-1 |
| Repo | |
| Framework | |
Tweester at SemEval-2017 Task 4: Fusion of Semantic-Affective and pairwise classification models for sentiment analysis in Twitter
| Title | Tweester at SemEval-2017 Task 4: Fusion of Semantic-Affective and pairwise classification models for sentiment analysis in Twitter |
| Authors | Athanasia Kolovou, Filippos Kokkinos, Aris Fergadis, Pinelopi Papalampidi, Elias Iosif, Mal, Nikolaos rakis, Elisavet Palogiannidi, Haris Papageorgiou, Shrikanth Narayanan, Alex Potamianos, ros |
| Abstract | In this paper, we describe our submission to SemEval2017 Task 4: Sentiment Analysis in Twitter. Specifically the proposed system participated both to tweet polarity classification (two-, three- and five class) and tweet quantification (two and five-class) tasks. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2112/ |
| https://www.aclweb.org/anthology/S17-2112 | |
| PWC | https://paperswithcode.com/paper/tweester-at-semeval-2017-task-4-fusion-of |
| Repo | |
| Framework | |
EICA at SemEval-2017 Task 4: A Simple Convolutional Neural Network for Topic-based Sentiment Classification
| Title | EICA at SemEval-2017 Task 4: A Simple Convolutional Neural Network for Topic-based Sentiment Classification |
| Authors | Maoquan Wang, Shiyun Chen, Yufei Xie, Lu Zhao |
| Abstract | This paper describes our approach for SemEval-2017 Task 4 - Sentiment Analysis in Twitter (SAT). Its five subtasks are divided into two categories: (1) sentiment classification, i.e., predicting topic-based tweet sentiment polarity, and (2) sentiment quantification, that is, estimating the sentiment distributions of a set of given tweets. We build a convolutional sentence classification system for the task of SAT. Official results show that the experimental results of our system are comparative. |
| Tasks | Feature Engineering, Sentence Classification, Sentiment Analysis, Twitter Sentiment Analysis |
| Published | 2017-08-01 |
| URL | https://www.aclweb.org/anthology/S17-2124/ |
| https://www.aclweb.org/anthology/S17-2124 | |
| PWC | https://paperswithcode.com/paper/eica-at-semeval-2017-task-4-a-simple |
| Repo | |
| Framework | |
Preserving Distributional Information in Dialogue Act Classification
| Title | Preserving Distributional Information in Dialogue Act Classification |
| Authors | Quan Hung Tran, Ingrid Zukerman, Gholamreza Haffari |
| Abstract | This paper introduces a novel training/decoding strategy for sequence labeling. Instead of greedily choosing a label at each time step, and using it for the next prediction, we retain the probability distribution over the current label, and pass this distribution to the next prediction. This approach allows us to avoid the effect of label bias and error propagation in sequence learning/decoding. Our experiments on dialogue act classification demonstrate the effectiveness of this approach. Even though our underlying neural network model is relatively simple, it outperforms more complex neural models, achieving state-of-the-art results on the MapTask and Switchboard corpora. |
| Tasks | Dialogue Act Classification, Language Modelling |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1229/ |
| https://www.aclweb.org/anthology/D17-1229 | |
| PWC | https://paperswithcode.com/paper/preserving-distributional-information-in |
| Repo | |
| Framework | |
Evaluation of Automatically Generated Pronoun Reference Questions
| Title | Evaluation of Automatically Generated Pronoun Reference Questions |
| Authors | Arief Yudha Satria, Takenobu Tokunaga |
| Abstract | This study provides a detailed analysis of evaluation of English pronoun reference questions which are created automatically by machine. Pronoun reference questions are multiple choice questions that ask test takers to choose an antecedent of a target pronoun in a reading passage from four options. The evaluation was performed from two perspectives: the perspective of English teachers and that of English learners. Item analysis suggests that machine-generated questions achieve comparable quality with human-made questions. Correlation analysis revealed a strong correlation between the scores of machine-generated questions and that of human-made questions. |
| Tasks | Reading Comprehension |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5008/ |
| https://www.aclweb.org/anthology/W17-5008 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-automatically-generated-pronoun |
| Repo | |
| Framework | |
Predicting Audience’s Laughter During Presentations Using Convolutional Neural Network
| Title | Predicting Audience’s Laughter During Presentations Using Convolutional Neural Network |
| Authors | Lei Chen, Chong Min Lee |
| Abstract | Public speakings play important roles in schools and work places and properly using humor contributes to effective presentations. For the purpose of automatically evaluating speakers{'} humor usage, we build a presentation corpus containing humorous utterances based on TED talks. Compared to previous data resources supporting humor recognition research, ours has several advantages, including (a) both positive and negative instances coming from a homogeneous data set, (b) containing a large number of speakers, and (c) being open. Focusing on using lexical cues for humor recognition, we systematically compare a newly emerging text classification method based on Convolutional Neural Networks (CNNs) with a well-established conventional method using linguistic knowledge. The advantages of the CNN method are both getting higher detection accuracies and being able to learn essential features automatically. |
| Tasks | Text Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5009/ |
| https://www.aclweb.org/anthology/W17-5009 | |
| PWC | https://paperswithcode.com/paper/predicting-audiences-laughter-during |
| Repo | |
| Framework | |
Exploring Relationships Between Writing & Broader Outcomes With Automated Writing Evaluation
| Title | Exploring Relationships Between Writing & Broader Outcomes With Automated Writing Evaluation |
| Authors | Jill Burstein, Dan McCaffrey, Beata Beigman Klebanov, Guangming Ling |
| Abstract | Writing is a challenge, especially for at-risk students who may lack the prerequisite writing skills required to persist in U.S. 4-year postsecondary (college) institutions. Educators teaching postsecondary courses requiring writing could benefit from a better understanding of writing achievement and its role in postsecondary success. In this paper, novel exploratory work examined how automated writing evaluation (AWE) can inform our understanding of the relationship between postsecondary writing skill and broader success outcomes. An exploratory study was conducted using test-taker essays from a standardized writing assessment of postsecondary student learning outcomes. Findings showed that for the essays, AWE features were found to be predictors of broader outcomes measures: college success and learning outcomes measures. Study findings illustrate AWE{'}s potential to support educational analytics {–} i.e., relationships between writing skill and broader outcomes {–} taking a step toward moving AWE beyond writing assessment and instructional use cases. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-5011/ |
| https://www.aclweb.org/anthology/W17-5011 | |
| PWC | https://paperswithcode.com/paper/exploring-relationships-between-writing |
| Repo | |
| Framework | |
