Paper Group NANR 67
Grounding Semantic Roles in Images. DNN Multimodal Fusion Techniques for Predicting Video Sentiment. Deconvolutional Time Series Regression: A Technique for Modeling Temporally Diffuse Effects. Is this Sentence Difficult? Do you Agree?. Seeing Temporal Modulation of Lights From Standard Cameras. Neural Transition Based Parsing of Web Queries: An En …
Grounding Semantic Roles in Images
| Title | Grounding Semantic Roles in Images |
| Authors | Carina Silberer, Manfred Pinkal |
| Abstract | We address the task of visual semantic role labeling (vSRL), the identification of the participants of a situation or event in a visual scene, and their labeling with their semantic relations to the event or situation. We render candidate participants as image regions of objects, and train a model which learns to ground roles in the regions which depict the corresponding participant. Experimental results demonstrate that we can train a vSRL model without reliance on prohibitive image-based role annotations, by utilizing noisy data which we extract automatically from image captions using a linguistic SRL system. Furthermore, our model induces frame{—}semantic visual representations, and their comparison to previous work on supervised visual verb sense disambiguation yields overall better results. |
| Tasks | Image Captioning, Question Answering, Semantic Role Labeling |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1282/ |
| https://www.aclweb.org/anthology/D18-1282 | |
| PWC | https://paperswithcode.com/paper/grounding-semantic-roles-in-images |
| Repo | |
| Framework | |
DNN Multimodal Fusion Techniques for Predicting Video Sentiment
| Title | DNN Multimodal Fusion Techniques for Predicting Video Sentiment |
| Authors | Jennifer Williams, Ramona Comanescu, Oana Radu, Leimin Tian |
| Abstract | We present our work on sentiment prediction using the benchmark MOSI dataset from the CMU-MultimodalDataSDK. Previous work on multimodal sentiment analysis have been focused on input-level feature fusion or decision-level fusion for multimodal fusion. Here, we propose an intermediate-level feature fusion, which merges weights from each modality (audio, video, and text) during training with subsequent additional training. Moreover, we tested principle component analysis (PCA) for feature selection. We found that applying PCA increases unimodal performance, and multimodal fusion outperforms unimodal models. Our experiments show that our proposed intermediate-level feature fusion outperforms other fusion techniques, and it achieves the best performance with an overall binary accuracy of 74.0{%} on video+text modalities. Our work also improves feature selection for unimodal sentiment analysis, while proposing a novel and effective multimodal fusion architecture for this task. |
| Tasks | Feature Selection, Multimodal Sentiment Analysis, Sentiment Analysis |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/W18-3309/ |
| https://www.aclweb.org/anthology/W18-3309 | |
| PWC | https://paperswithcode.com/paper/dnn-multimodal-fusion-techniques-for |
| Repo | |
| Framework | |
Deconvolutional Time Series Regression: A Technique for Modeling Temporally Diffuse Effects
| Title | Deconvolutional Time Series Regression: A Technique for Modeling Temporally Diffuse Effects |
| Authors | Cory Shain, William Schuler |
| Abstract | Researchers in computational psycholinguistics frequently use linear models to study time series data generated by human subjects. However, time series may violate the assumptions of these models through temporal diffusion, where stimulus presentation has a lingering influence on the response as the rest of the experiment unfolds. This paper proposes a new statistical model that borrows from digital signal processing by recasting the predictors and response as convolutionally-related signals, using recent advances in machine learning to fit latent impulse response functions (IRFs) of arbitrary shape. A synthetic experiment shows successful recovery of true latent IRFs, and psycholinguistic experiments reveal plausible, replicable, and fine-grained estimates of latent temporal dynamics, with comparable or improved prediction quality to widely-used alternatives. |
| Tasks | Time Series |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1288/ |
| https://www.aclweb.org/anthology/D18-1288 | |
| PWC | https://paperswithcode.com/paper/deconvolutional-time-series-regression-a |
| Repo | |
| Framework | |
Is this Sentence Difficult? Do you Agree?
| Title | Is this Sentence Difficult? Do you Agree? |
| Authors | Dominique Brunato, Lorenzo De Mattei, Felice Dell{'}Orletta, Benedetta Iavarone, Giulia Venturi |
| Abstract | In this paper, we present a crowdsourcing-based approach to model the human perception of sentence complexity. We collect a large corpus of sentences rated with judgments of complexity for two typologically-different languages, Italian and English. We test our approach in two experimental scenarios aimed to investigate the contribution of a wide set of lexical, morpho-syntactic and syntactic phenomena in predicting i) the degree of agreement among annotators independently from the assigned judgment and ii) the perception of sentence complexity. |
| Tasks | Language Acquisition |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1289/ |
| https://www.aclweb.org/anthology/D18-1289 | |
| PWC | https://paperswithcode.com/paper/is-this-sentence-difficult-do-you-agree |
| Repo | |
| Framework | |
Seeing Temporal Modulation of Lights From Standard Cameras
| Title | Seeing Temporal Modulation of Lights From Standard Cameras |
| Authors | Naoki Sakakibara, Fumihiko Sakaue, Jun Sato |
| Abstract | In this paper, we propose a novel method for measuring the temporal modulation of lights by using off-the-shelf cameras. In particular, we show that the invisible flicker patterns of various lights such as fluorescent lights can be measured by a simple combination of an off-the-shelf camera and any moving object with specular reflection. Unlike the existing methods, we do not need high speed cameras nor specially designed coded exposure cameras. Based on the extracted flicker patterns of environment lights, we also propose an efficient method for deblurring motion blurs in images. The proposed method enables us to deblur images with better frequency characteristics, which are induced by the flicker patterns of environment lights. The real image experiments show the efficiency of the proposed method. |
| Tasks | Deblurring |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Sakakibara_Seeing_Temporal_Modulation_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Sakakibara_Seeing_Temporal_Modulation_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/seeing-temporal-modulation-of-lights-from |
| Repo | |
| Framework | |
Neural Transition Based Parsing of Web Queries: An Entity Based Approach
| Title | Neural Transition Based Parsing of Web Queries: An Entity Based Approach |
| Authors | Rivka Malca, Roi Reichart |
| Abstract | Web queries with question intent manifest a complex syntactic structure and the processing of this structure is important for their interpretation. Pinter et al. (2016) has formalized the grammar of these queries and proposed semi-supervised algorithms for the adaptation of parsers originally designed to parse according to the standard dependency grammar, so that they can account for the unique forest grammar of queries. However, their algorithms rely on resources typically not available outside of big web corporates. We propose a new BiLSTM query parser that: (1) Explicitly accounts for the unique grammar of web queries; and (2) Utilizes named entity (NE) information from a BiLSTM NE tagger, that can be jointly trained with the parser. In order to train our model we annotate the query treebank of Pinter et al. (2016) with NEs. When trained on 2500 annotated queries our parser achieves UAS of 83.5{%} and segmentation F1-score of 84.5, substantially outperforming existing state-of-the-art parsers. |
| Tasks | Community Question Answering, Question Answering |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1290/ |
| https://www.aclweb.org/anthology/D18-1290 | |
| PWC | https://paperswithcode.com/paper/neural-transition-based-parsing-of-web |
| Repo | |
| Framework | |
Incremental Computation of Infix Probabilities for Probabilistic Finite Automata
| Title | Incremental Computation of Infix Probabilities for Probabilistic Finite Automata |
| Authors | Marco Cognetta, Yo-Sub Han, Soon Chan Kwon |
| Abstract | In natural language processing, a common task is to compute the probability of a phrase appearing in a document or to calculate the probability of all phrases matching a given pattern. For instance, one computes affix (prefix, suffix, infix, etc.) probabilities of a string or a set of strings with respect to a probability distribution of patterns. The problem of computing infix probabilities of strings when the pattern distribution is given by a probabilistic context-free grammar or by a probabilistic finite automaton is already solved, yet it was open to compute the infix probabilities in an incremental manner. The incremental computation is crucial when a new query is built from a previous query. We tackle this problem and suggest a method that computes infix probabilities incrementally for probabilistic finite automata by representing all the probabilities of matching strings as a series of transition matrix calculations. We show that the proposed approach is theoretically faster than the previous method and, using real world data, demonstrate that our approach has vastly better performance in practice. |
| Tasks | |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1293/ |
| https://www.aclweb.org/anthology/D18-1293 | |
| PWC | https://paperswithcode.com/paper/incremental-computation-of-infix |
| Repo | |
| Framework | |
Last Words: What Can Be Accomplished with the State of the Art in Information Extraction? A Personal View
| Title | Last Words: What Can Be Accomplished with the State of the Art in Information Extraction? A Personal View |
| Authors | Ralph Weischedel, Elizabeth Boschee |
| Abstract | Though information extraction (IE) research has more than a 25-year history, F1 scores remain low. Thus, one could question continued investment in IE research. In this article, we present three applications where information extraction of entities, relations, and/or events has been used, and note the common features that seem to have led to success. We also identify key research challenges whose solution seems essential for broader successes. Because a few practical deployments already exist and because breakthroughs on particular challenges would greatly broaden the technology{'}s deployment, further R and D investments are justified. |
| Tasks | Named Entity Recognition |
| Published | 2018-12-01 |
| URL | https://www.aclweb.org/anthology/J18-4004/ |
| https://www.aclweb.org/anthology/J18-4004 | |
| PWC | https://paperswithcode.com/paper/last-words-what-can-be-accomplished-with-the |
| Repo | |
| Framework | |
Implicit Subjective and Sentimental Usages in Multi-sense Word Embeddings
| Title | Implicit Subjective and Sentimental Usages in Multi-sense Word Embeddings |
| Authors | Yuqi Sun, Haoyue Shi, Junfeng Hu |
| Abstract | In multi-sense word embeddings, contextual variations in corpus may cause a univocal word to be embedded into different sense vectors. Shi et al. (2016) show that this kind of \textit{pseudo multi-senses} can be eliminated by linear transformations. In this paper, we show that \textit{pseudo multi-senses} may come from a uniform and meaningful phenomenon such as subjective and sentimental usage, though they are seemingly redundant. In this paper, we present an unsupervised algorithm to find a linear transformation which can minimize the transformed distance of a group of sense pairs. The major shrinking direction of this transformation is found to be related with subjective shift. Therefore, we can not only eliminate \textit{pseudo multi-senses} in multisense embeddings, but also identify these subjective senses and tag the subjective and sentimental usage of words in the corpus automatically. |
| Tasks | Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6203/ |
| https://www.aclweb.org/anthology/W18-6203 | |
| PWC | https://paperswithcode.com/paper/implicit-subjective-and-sentimental-usages-in |
| Repo | |
| Framework | |
Sentiment-Stance-Specificity (SSS) Dataset: Identifying Support-based Entailment among Opinions.
| Title | Sentiment-Stance-Specificity (SSS) Dataset: Identifying Support-based Entailment among Opinions. |
| Authors | Pavithra Rajendran, Danushka Bollegala, Simon Parsons |
| Abstract | |
| Tasks | Argument Mining, Natural Language Inference |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1099/ |
| https://www.aclweb.org/anthology/L18-1099 | |
| PWC | https://paperswithcode.com/paper/sentiment-stance-specificity-sss-dataset |
| Repo | |
| Framework | |
A mostly unlexicalized model for recognizing textual entailment
| Title | A mostly unlexicalized model for recognizing textual entailment |
| Authors | Mithun Paul, Rebecca Sharp, Mihai Surdeanu |
| Abstract | Many approaches to automatically recognizing entailment relations have employed classifiers over hand engineered lexicalized features, or deep learning models that implicitly capture lexicalization through word embeddings. This reliance on lexicalization may complicate the adaptation of these tools between domains. For example, such a system trained in the news domain may learn that a sentence like {``}Palestinians recognize Texas as part of Mexico{''} tends to be unsupported, but this fact (and its corresponding lexicalized cues) have no value in, say, a scientific domain. To mitigate this dependence on lexicalized information, in this paper we propose a model that reads two sentences, from any given domain, to determine entailment without using lexicalized features. Instead our model relies on features that are either unlexicalized or are domain independent such as proportion of negated verbs, antonyms, or noun overlap. In its current implementation, this model does not perform well on the FEVER dataset, due to two reasons. First, for the information retrieval portion of the task we used the baseline system provided, since this was not the aim of our project. Second, this is work in progress and we still are in the process of identifying more features and gradually increasing the accuracy of our model. In the end, we hope to build a generic end-to-end classifier, which can be used in a domain outside the one in which it was trained, with no or minimal re-training. | |
| Tasks | Fake News Detection, Information Retrieval, Natural Language Inference, Word Embeddings |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5528/ |
| https://www.aclweb.org/anthology/W18-5528 | |
| PWC | https://paperswithcode.com/paper/a-mostly-unlexicalized-model-for-recognizing |
| Repo | |
| Framework | |
Word Embedding Approach for Synonym Extraction of Multi-Word Terms
| Title | Word Embedding Approach for Synonym Extraction of Multi-Word Terms |
| Authors | Amir Hazem, B{'e}atrice Daille |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation, Text Simplification, Word Embeddings, Word Sense Disambiguation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1045/ |
| https://www.aclweb.org/anthology/L18-1045 | |
| PWC | https://paperswithcode.com/paper/word-embedding-approach-for-synonym |
| Repo | |
| Framework | |
The Lazy Encoder: A Fine-Grained Analysis of the Role of Morphology in Neural Machine Translation
| Title | The Lazy Encoder: A Fine-Grained Analysis of the Role of Morphology in Neural Machine Translation |
| Authors | Arianna Bisazza, Clara Tump |
| Abstract | Neural sequence-to-sequence models have proven very effective for machine translation, but at the expense of model interpretability. To shed more light into the role played by linguistic structure in the process of neural machine translation, we perform a fine-grained analysis of how various source-side morphological features are captured at different levels of the NMT encoder while varying the target language. Differently from previous work, we find no correlation between the accuracy of source morphology encoding and translation quality. We do find that morphological features are only captured in context and only to the extent that they are directly transferable to the target words. |
| Tasks | Machine Translation, Word Embeddings |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/D18-1313/ |
| https://www.aclweb.org/anthology/D18-1313 | |
| PWC | https://paperswithcode.com/paper/the-lazy-encoder-a-fine-grained-analysis-of |
| Repo | |
| Framework | |
Combining Deep Learning and Topic Modeling for Review Understanding in Context-Aware Recommendation
| Title | Combining Deep Learning and Topic Modeling for Review Understanding in Context-Aware Recommendation |
| Authors | Mingmin Jin, Xin Luo, Huiling Zhu, Hankz Hankui Zhuo |
| Abstract | With the rise of e-commerce, people are accustomed to writing their reviews after receiving the goods. These comments are so important that a bad review can have a direct impact on others buying. Besides, the abundant information within user reviews is very useful for extracting user preferences and item properties. In this paper, we investigate the approach to effectively utilize review information for recommender systems. The proposed model is named LSTM-Topic matrix factorization (LTMF) which integrates both LSTM and Topic Modeling for review understanding. In the experiments on popular review dataset Amazon , our LTMF model outperforms previous proposed HFT model and ConvMF model in rating prediction. Furthermore, LTMF shows the better ability on making topic clustering than traditional topic model based method, which implies integrating the information from deep learning and topic modeling is a meaningful approach to make a better understanding of reviews. |
| Tasks | Recommendation Systems |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/N18-1145/ |
| https://www.aclweb.org/anthology/N18-1145 | |
| PWC | https://paperswithcode.com/paper/combining-deep-learning-and-topic-modeling |
| Repo | |
| Framework | |
Questionable Answers in Question Answering Research: Reproducibility and Variability of Published Results
| Title | Questionable Answers in Question Answering Research: Reproducibility and Variability of Published Results |
| Authors | Matt Crane |
| Abstract | {``}Based on theoretical reasoning it has been suggested that the reliability of findings published in the scientific literature decreases with the popularity of a research field{''} (Pfeiffer and Hoffmann, 2009). As we know, deep learning is very popular and the ability to reproduce results is an important part of science. There is growing concern within the deep learning community about the reproducibility of results that are presented. In this paper we present a number of controllable, yet unreported, effects that can substantially change the effectiveness of a sample model, and thusly the reproducibility of those results. Through these environmental effects we show that the commonly held belief that distribution of source code is all that is needed for reproducibility is not enough. Source code without a reproducible environment does not mean anything at all. In addition the range of results produced from these effects can be larger than the majority of incremental improvement reported. | |
| Tasks | Information Retrieval, Question Answering |
| Published | 2018-01-01 |
| URL | https://www.aclweb.org/anthology/Q18-1018/ |
| https://www.aclweb.org/anthology/Q18-1018 | |
| PWC | https://paperswithcode.com/paper/questionable-answers-in-question-answering |
| Repo | |
| Framework | |
