Paper Group NANR 62
Proceedings of the 13th International Workshop on Tree Adjoining Grammars and Related Formalisms. Modeling Dialogue Acts with Content Word Filtering and Speaker Preferences. Proceedings of the 14th International Conference on Natural Language Processing (ICON-2017). Robust Pseudo Random Fields for Light-Field Stereo Matching. Semantic annotation to …
Proceedings of the 13th International Workshop on Tree Adjoining Grammars and Related Formalisms
| Title | Proceedings of the 13th International Workshop on Tree Adjoining Grammars and Related Formalisms |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-6200/ |
| https://www.aclweb.org/anthology/W17-6200 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-13th-international |
| Repo | |
| Framework | |
Modeling Dialogue Acts with Content Word Filtering and Speaker Preferences
| Title | Modeling Dialogue Acts with Content Word Filtering and Speaker Preferences |
| Authors | Yohan Jo, Michael Yoder, Hyeju Jang, Carolyn Ros{'e} |
| Abstract | We present an unsupervised model of dialogue act sequences in conversation. By modeling topical themes as transitioning more slowly than dialogue acts in conversation, our model de-emphasizes content-related words in order to focus on conversational function words that signal dialogue acts. We also incorporate speaker tendencies to use some acts more than others as an additional predictor of dialogue act prevalence beyond temporal dependencies. According to the evaluation presented on two dissimilar corpora, the CNET forum and NPS Chat corpus, the effectiveness of each modeling assumption is found to vary depending on characteristics of the data. De-emphasizing content-related words yields improvement on the CNET corpus, while utilizing speaker tendencies is advantageous on the NPS corpus. The components of our model complement one another to achieve robust performance on both corpora and outperform state-of-the-art baseline models. |
| Tasks | Language Modelling |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1232/ |
| https://www.aclweb.org/anthology/D17-1232 | |
| PWC | https://paperswithcode.com/paper/modeling-dialogue-acts-with-content-word |
| Repo | |
| Framework | |
Proceedings of the 14th International Conference on Natural Language Processing (ICON-2017)
| Title | Proceedings of the 14th International Conference on Natural Language Processing (ICON-2017) |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-7500/ |
| https://www.aclweb.org/anthology/W17-7500 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-14th-international |
| Repo | |
| Framework | |
Robust Pseudo Random Fields for Light-Field Stereo Matching
| Title | Robust Pseudo Random Fields for Light-Field Stereo Matching |
| Authors | Chao-Tsung Huang |
| Abstract | Markov Random Fields are widely used to model light-field stereo matching problems. However, most previous approaches used fixed parameters and did not adapt to light-field statistics. Instead, they explored explicit vision cues to provide local adaptability and thus enhanced depth quality. But such additional assumptions could end up confining their applicability, e.g. algorithms designed for dense light fields are not suitable for sparse ones. In this paper, we develop an empirical Bayesian framework–Robust Pseudo Random Field–to explore intrinsic statistical cues for broad applicability. Based on pseudo-likelihood, it applies soft expectation-maximization (EM) for good model fitting and hard EM for robust depth estimation. We introduce novel pixel difference models to enable such adaptability and robustness simultaneously. We also devise an algorithm to employ this framework on dense, sparse, and even denoised light fields. Experimental results show that it estimates scene-dependent parameters robustly and converges quickly. In terms of depth accuracy and computation speed, it also outperforms state-of-the-art algorithms constantly. |
| Tasks | Depth Estimation, Stereo Matching, Stereo Matching Hand |
| Published | 2017-10-01 |
| URL | http://openaccess.thecvf.com/content_iccv_2017/html/Huang_Robust_Pseudo_Random_ICCV_2017_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2017/papers/Huang_Robust_Pseudo_Random_ICCV_2017_paper.pdf | |
| PWC | https://paperswithcode.com/paper/robust-pseudo-random-fields-for-light-field |
| Repo | |
| Framework | |
Semantic annotation to characterize contextual variation in terminological noun compounds: a pilot study
| Title | Semantic annotation to characterize contextual variation in terminological noun compounds: a pilot study |
| Authors | Melania Cabezas-Garc{'\i}a, Antonio San Mart{'\i}n |
| Abstract | Noun compounds (NCs) are semantically complex and not fully compositional, as is often assumed. This paper presents a pilot study regarding the semantic annotation of environmental NCs with a view to accessing their semantics and exploring their domain-based contextual variation. Our results showed that the semantic annotation of NCs afforded important insights into how context impacts their conceptualization. |
| Tasks | |
| Published | 2017-04-01 |
| URL | https://www.aclweb.org/anthology/W17-1714/ |
| https://www.aclweb.org/anthology/W17-1714 | |
| PWC | https://paperswithcode.com/paper/semantic-annotation-to-characterize |
| Repo | |
| Framework | |
Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction
| Title | Multi-View Unsupervised User Feature Embedding for Social Media-based Substance Use Prediction |
| Authors | Tao Ding, Warren K. Bickel, Shimei Pan |
| Abstract | In this paper, we demonstrate how the state-of-the-art machine learning and text mining techniques can be used to build effective social media-based substance use detection systems. Since a substance use ground truth is difficult to obtain on a large scale, to maximize system performance, we explore different unsupervised feature learning methods to take advantage of a large amount of unsupervised social media data. We also demonstrate the benefit of using multi-view unsupervised feature learning to combine heterogeneous user information such as Facebook {}likes{''} and {}status updates{''} to enhance system performance. Based on our evaluation, our best models achieved 86{%} AUC for predicting tobacco use, 81{%} for alcohol use and 84{%} for illicit drug use, all of which significantly outperformed existing methods. Our investigation has also uncovered interesting relations between a user{'}s social media behavior (e.g., word usage) and substance use. |
| Tasks | |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1241/ |
| https://www.aclweb.org/anthology/D17-1241 | |
| PWC | https://paperswithcode.com/paper/multi-view-unsupervised-user-feature |
| Repo | |
| Framework | |
Joint Sentence-Document Model for Manifesto Text Analysis
| Title | Joint Sentence-Document Model for Manifesto Text Analysis |
| Authors | Shivashankar Subramanian, Trevor Cohn, Timothy Baldwin, Julian Brooke |
| Abstract | |
| Tasks | Sentence Classification |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/U17-1003/ |
| https://www.aclweb.org/anthology/U17-1003 | |
| PWC | https://paperswithcode.com/paper/joint-sentence-document-model-for-manifesto |
| Repo | |
| Framework | |
Automatic Negation and Speculation Detection in Veterinary Clinical Text
| Title | Automatic Negation and Speculation Detection in Veterinary Clinical Text |
| Authors | Katherine Cheng, Timothy Baldwin, Karin Verspoor |
| Abstract | |
| Tasks | Speculation Detection |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/U17-1008/ |
| https://www.aclweb.org/anthology/U17-1008 | |
| PWC | https://paperswithcode.com/paper/automatic-negation-and-speculation-detection |
| Repo | |
| Framework | |
A Comparative Study of Two Statistical Modelling Approaches for Estimating Multivariate Likelihood Ratios in Forensic Voice Comparison
| Title | A Comparative Study of Two Statistical Modelling Approaches for Estimating Multivariate Likelihood Ratios in Forensic Voice Comparison |
| Authors | Shunichi Ishihara |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/U17-1007/ |
| https://www.aclweb.org/anthology/U17-1007 | |
| PWC | https://paperswithcode.com/paper/a-comparative-study-of-two-statistical |
| Repo | |
| Framework | |
Controlling Human Perception of Basic User Traits
| Title | Controlling Human Perception of Basic User Traits |
| Authors | Daniel Preo{\c{t}}iuc-Pietro, Ch, Sharath ra Guntuku, Lyle Ungar |
| Abstract | Much of our online communication is text-mediated and, lately, more common with automated agents. Unlike interacting with humans, these agents currently do not tailor their language to the type of person they are communicating to. In this pilot study, we measure the extent to which human perception of basic user trait information {–} gender and age {–} is controllable through text. Using automatic models of gender and age prediction, we estimate which tweets posted by a user are more likely to mis-characterize his traits. We perform multiple controlled crowdsourcing experiments in which we show that we can reduce the human prediction accuracy of gender to almost random {–} an over 20{%} drop in accuracy. Our experiments show that it is practically feasible for multiple applications such as text generation, text summarization or machine translation to be tailored to specific traits and perceived as such. |
| Tasks | Machine Translation, Text Generation, Text Summarization |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1248/ |
| https://www.aclweb.org/anthology/D17-1248 | |
| PWC | https://paperswithcode.com/paper/controlling-human-perception-of-basic-user |
| Repo | |
| Framework | |
Towards the Use of Deep Reinforcement Learning with Global Policy for Query-based Extractive Summarisation
| Title | Towards the Use of Deep Reinforcement Learning with Global Policy for Query-based Extractive Summarisation |
| Authors | Diego Moll{'a}-Aliod |
| Abstract | |
| Tasks | |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/U17-1012/ |
| https://www.aclweb.org/anthology/U17-1012 | |
| PWC | https://paperswithcode.com/paper/towards-the-use-of-deep-reinforcement-1 |
| Repo | |
| Framework | |
Tree as a Pivot: Syntactic Matching Methods in Pivot Translation
| Title | Tree as a Pivot: Syntactic Matching Methods in Pivot Translation |
| Authors | Akiva Miura, Graham Neubig, Katsuhito Sudoh, Satoshi Nakamura |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/W17-4709/ |
| https://www.aclweb.org/anthology/W17-4709 | |
| PWC | https://paperswithcode.com/paper/tree-as-a-pivot-syntactic-matching-methods-in |
| Repo | |
| Framework | |
Assessing Objective Recommendation Quality through Political Forecasting
| Title | Assessing Objective Recommendation Quality through Political Forecasting |
| Authors | H. Andrew Schwartz, Masoud Rouhizadeh, Michael Bishop, Philip Tetlock, Barbara Mellers, Lyle Ungar |
| Abstract | Recommendations are often rated for their subjective quality, but few researchers have studied comment quality in terms of objective utility. We explore recommendation quality assessment with respect to both subjective (i.e. users{'} ratings) and objective (i.e., did it influence? did it improve decisions?) metrics in a massive online geopolitical forecasting system, ultimately comparing linguistic characteristics of each quality metric. Using a variety of features, we predict all types of quality with better accuracy than the simple yet strong baseline of comment length. Looking at the most predictive content illustrates rater biases; for example, forecasters are subjectively biased in favor of comments mentioning business transactions or dealings as well as material things, even though such comments do not indeed prove any more useful objectively. Additionally, more complex sentence constructions, as evidenced by subordinate conjunctions, are characteristic of comments leading to objective improvements in forecasting. |
| Tasks | Sentiment Analysis |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1250/ |
| https://www.aclweb.org/anthology/D17-1250 | |
| PWC | https://paperswithcode.com/paper/assessing-objective-recommendation-quality |
| Repo | |
| Framework | |
The Impact of Modeling Overall Argumentation with Tree Kernels
| Title | The Impact of Modeling Overall Argumentation with Tree Kernels |
| Authors | Henning Wachsmuth, Giovanni Da San Martino, Dora Kiesel, Benno Stein |
| Abstract | Several approaches have been proposed to model either the explicit sequential structure of an argumentative text or its implicit hierarchical structure. So far, the adequacy of these models of overall argumentation remains unclear. This paper asks what type of structure is actually important to tackle downstream tasks in computational argumentation. We analyze patterns in the overall argumentation of texts from three corpora. Then, we adapt the idea of positional tree kernels in order to capture sequential and hierarchical argumentative structure together for the first time. In systematic experiments for three text classification tasks, we find strong evidence for the impact of both types of structure. Our results suggest that either of them is necessary while their combination may be beneficial. |
| Tasks | Text Classification |
| Published | 2017-09-01 |
| URL | https://www.aclweb.org/anthology/D17-1253/ |
| https://www.aclweb.org/anthology/D17-1253 | |
| PWC | https://paperswithcode.com/paper/the-impact-of-modeling-overall-argumentation |
| Repo | |
| Framework | |
Analyzing the Impact of Spelling Errors on POS-Tagging and Chunking in Learner English
| Title | Analyzing the Impact of Spelling Errors on POS-Tagging and Chunking in Learner English |
| Authors | Tomoya Mizumoto, Ryo Nagata |
| Abstract | Part-of-speech (POS) tagging and chunking have been used in tasks targeting learner English; however, to the best our knowledge, few studies have evaluated their performance and no studies have revealed the causes of POS-tagging/chunking errors in detail. Therefore, we investigate performance and analyze the causes of failure. We focus on spelling errors that occur frequently in learner English. We demonstrate that spelling errors reduced POS-tagging performance by 0.23{%} owing to spelling errors, and that a spell checker is not necessary for POS-tagging/chunking of learner English. |
| Tasks | Chunking, Grammatical Error Correction, Part-Of-Speech Tagging |
| Published | 2017-12-01 |
| URL | https://www.aclweb.org/anthology/W17-5909/ |
| https://www.aclweb.org/anthology/W17-5909 | |
| PWC | https://paperswithcode.com/paper/analyzing-the-impact-of-spelling-errors-on |
| Repo | |
| Framework | |
