Paper Group NANR 144
Towards Accurate Text Verbalization for ASR Based on Audio Alignment. LayoutGAN: Generating Graphic Layouts with Wireframe Discriminator. Zero-Shot Cross-lingual Name Retrieval for Low-Resource Languages. Sentiment Analysis Model for Opinionated Awngi Text: Case of Music Reviews. Evaluation of Scientific Elements for Text Similarity in Biomedical P …
Towards Accurate Text Verbalization for ASR Based on Audio Alignment
| Title | Towards Accurate Text Verbalization for ASR Based on Audio Alignment |
| Authors | Diana Geneva, Georgi Shopov |
| Abstract | Verbalization of non-lexical linguistic units plays an important role in language modeling for automatic speech recognition systems. Most verbalization methods require valuable resources such as ground truth, large training corpus and expert knowledge which are often unavailable. On the other hand a considerable amount of audio data along with its transcribed text are freely available on the Internet and could be utilized for the task of verbalization. This paper presents a methodology for accurate verbalization of audio transcriptions based on phone-level alignment between the transcriptions and their corresponding audio recordings. Comparing this approach to a more general rule-based verbalization method shows a significant improvement in ASR recognition of non-lexical units. In the process of evaluating this approach we also expose the indirect influence of verbalization accuracy on the quality of acoustic models trained on automatically derived speech corpora. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-2007/ |
| https://www.aclweb.org/anthology/R19-2007 | |
| PWC | https://paperswithcode.com/paper/towards-accurate-text-verbalization-for-asr |
| Repo | |
| Framework | |
LayoutGAN: Generating Graphic Layouts with Wireframe Discriminator
| Title | LayoutGAN: Generating Graphic Layouts with Wireframe Discriminator |
| Authors | Jianan Li, Tingfa Xu, Jianming Zhang, Aaron Hertzmann, Jimei Yang |
| Abstract | Layouts are important for graphic design and scene generation. We propose a novel generative adversarial network, named as LayoutGAN, that synthesizes graphic layouts by modeling semantic and geometric relations of 2D elements. The generator of LayoutGAN takes as input a set of randomly placed 2D graphic elements and uses self-attention modules to refine their semantic and geometric parameters jointly to produce a meaningful layout. Accurate alignment is critical for good layouts. We thus propose a novel differentiable wireframe rendering layer that maps the generated layout to a wireframe image, upon which a CNN-based discriminator is used to optimize the layouts in visual domain. We validate the effectiveness of LayoutGAN in various experiments including MNIST digit generation, document layout generation, clipart abstract scene generation and tangram graphic design. |
| Tasks | Scene Generation |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJxB5sRcFQ |
| https://openreview.net/pdf?id=HJxB5sRcFQ | |
| PWC | https://paperswithcode.com/paper/layoutgan-generating-graphic-layouts-with-1 |
| Repo | |
| Framework | |
Zero-Shot Cross-lingual Name Retrieval for Low-Resource Languages
| Title | Zero-Shot Cross-lingual Name Retrieval for Low-Resource Languages |
| Authors | Kevin Blissett, Heng Ji |
| Abstract | In this paper we address a challenging cross-lingual name retrieval task. Given an English named entity query, we aim to find all name mentions in documents in low-resource languages. We present a novel method which relies on zero annotation or resources from the target language. By leveraging freely available, cross-lingual resources and a small amount of training data from another language, we are able to perform name retrieval on a new language without any additional training data. Our method proceeds in a multi-step process: first, we pre-train a language-independent orthographic encoder using Wikipedia inter-lingual links from dozens of languages. Next, we gather user expectations about important entities in an English comparable document and compare those expected entities with actual spans of the target language text in order to perform name finding. Our method shows 11.6{%} absolute F-score improvement over state-of-the-art methods. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6131/ |
| https://www.aclweb.org/anthology/D19-6131 | |
| PWC | https://paperswithcode.com/paper/zero-shot-cross-lingual-name-retrieval-for |
| Repo | |
| Framework | |
Sentiment Analysis Model for Opinionated Awngi Text: Case of Music Reviews
| Title | Sentiment Analysis Model for Opinionated Awngi Text: Case of Music Reviews |
| Authors | Melese Mihret, Muluneh Atinaf |
| Abstract | Abstract The analysis of sentiments is imperative to make a decision for individuals, organizations, and governments. Due to the rapid growth of Awngi (Agew) text on the web, there is no available corpus annotated for sentiment analysis. In this paper, we present a SA model for the Awngi language spoken in Ethiopia, by using a supervised machine learning approach. We developed our corpus by collecting around 1500 posts from online sources. This research is begun to build and evaluate the model for opinionated Awngi music reviews. Thus, pre-processing techniques have been employed to clean the data, to convert transliterations to the native Ethiopic script for accessibility and convenience to typing and to change the words to their base form by removing the inflectional morphemes. After pre-processing, the corpus is manually annotated by three the language professional for giving polarity, and rate, their level of confidence in their selection and sentiment intensity scale values. To improve the calculation method of feature selection and weighting and proposed a more suitable SA algorithm for feature extraction named CHI and weight calculation named TF IDF, increasing the proportion and weight of sentiment words in the feature words. We employed Support Vector Machines (SVM), Na{"\i}ve Bayes (NB) and Maximum Entropy (MxEn) machine learning algorithms. Generally, the results are encouraging, despite the morphological challenge in Awngi, the data cleanness and small size of data. We are believed that the results could improve further with a larger corpus. |
| Tasks | Feature Selection, Sentiment Analysis |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3617/ |
| https://www.aclweb.org/anthology/W19-3617 | |
| PWC | https://paperswithcode.com/paper/sentiment-analysis-model-for-opinionated |
| Repo | |
| Framework | |
Evaluation of Scientific Elements for Text Similarity in Biomedical Publications
| Title | Evaluation of Scientific Elements for Text Similarity in Biomedical Publications |
| Authors | Mariana Neves, Daniel Butzke, Barbara Grune |
| Abstract | Rhetorical elements from scientific publications provide a more structured view of the document and allow algorithms to focus on particular parts of the text. We surveyed the literature for previously proposed schemes for rhetorical elements and present an overview of its current state of the art. We also searched for available tools using these schemes and applied four tools for our particular task of ranking biomedical abstracts based on text similarity. Comparison of the tools with two strong baselines shows that the predictions provided by the ArguminSci tool can support our use case of mining alternative methods for animal experiments. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4515/ |
| https://www.aclweb.org/anthology/W19-4515 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-scientific-elements-for-text |
| Repo | |
| Framework | |
Evaluation of Stacked Embeddings for Bulgarian on the Downstream Tasks POS and NERC
| Title | Evaluation of Stacked Embeddings for Bulgarian on the Downstream Tasks POS and NERC |
| Authors | Iva Marinova |
| Abstract | This paper reports on experiments with different stacks of word embeddings and evaluation of their usefulness for Bulgarian downstream tasks such as Named Entity Recognition and Classification (NERC) and Part-of-speech (POS) Tagging. Word embeddings stay in the core of the development of NLP, with several key language models being created over the last two years like FastText (CITATION), ElMo (CITATION), BERT (CITATION) and Flair (CITATION). Stacking or combining different word embeddings is another technique used in this paper and still not reported for Bulgarian NERC. Well-established architecture is used for the sequence tagging task such as BI-LSTM-CRF, and different pre-trained language models are combined in the embedding layer to decide which combination of them scores better. |
| Tasks | Named Entity Recognition, Part-Of-Speech Tagging, Word Embeddings |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-2008/ |
| https://www.aclweb.org/anthology/R19-2008 | |
| PWC | https://paperswithcode.com/paper/evaluation-of-stacked-embeddings-for |
| Repo | |
| Framework | |
Overview on NLP Techniques for Content-based Recommender Systems for Books
| Title | Overview on NLP Techniques for Content-based Recommender Systems for Books |
| Authors | Melania Berbatova |
| Abstract | Recommender systems are an essential part of today{'}s largest websites. Without them, it would be hard for users to find the right products and content. One of the most popular methods for recommendations is content-based filtering. It relies on analysing product metadata, a great part of which is textual data. Despite their frequent use, there is still no standard procedure for developing and evaluating content-based recommenders. In this paper, we will first examine current approaches for designing, training and evaluating recommender systems based on textual data for books recommendations for GoodReads{'} website. We will give critiques on existing methods and suggest how natural language techniques can be employed for the improvement of content-based recommenders. |
| Tasks | Recommendation Systems |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-2009/ |
| https://www.aclweb.org/anthology/R19-2009 | |
| PWC | https://paperswithcode.com/paper/overview-on-nlp-techniques-for-content-based |
| Repo | |
| Framework | |
Persuasion of the Undecided: Language vs. the Listener
| Title | Persuasion of the Undecided: Language vs. the Listener |
| Authors | Liane Longpre, Esin Durmus, Claire Cardie |
| Abstract | This paper examines the factors that govern persuasion for a priori UNDECIDED versus DECIDED audience members in the context of on-line debates. We separately study two types of influences: linguistic factors {—} features of the language of the debate itself; and audience factors {—} features of an audience member encoding demographic information, prior beliefs, and debate platform behavior. In a study of users of a popular debate platform, we find first that different combinations of linguistic features are critical for predicting persuasion outcomes for UNDECIDED versus DECIDED members of the audience. We additionally find that audience factors have more influence on predicting the side (PRO/CON) that persuaded UNDECIDED users than for DECIDED users that flip their stance to the opposing side. Our results emphasize the importance of considering the undecided and decided audiences separately when studying linguistic factors of persuasion. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4519/ |
| https://www.aclweb.org/anthology/W19-4519 | |
| PWC | https://paperswithcode.com/paper/persuasion-of-the-undecided-language-vs-the |
| Repo | |
| Framework | |
Learning Structure-And-Motion-Aware Rolling Shutter Correction
| Title | Learning Structure-And-Motion-Aware Rolling Shutter Correction |
| Authors | Bingbing Zhuang, Quoc-Huy Tran, Pan Ji, Loong-Fah Cheong, Manmohan Chandraker |
| Abstract | An exact method of correcting the rolling shutter (RS) effect requires recovering the underlying geometry, i.e. the scene structures and the camera motions between scanlines or between views. However, the multiple-view geometry for RS cameras is much more complicated than its global shutter (GS) counterpart, with various degeneracies. In this paper, we first make a theoretical contribution by showing that RS two-view geometry is degenerate in the case of pure translational camera motion. In view of the complex RS geometry, we then propose a Convolutional Neural Network (CNN)-based method which learns the underlying geometry (camera motion and scene structure) from just a single RS image and perform RS image correction. We call our method structure-and-motion-aware RS correction because it reasons about the concealed motions between the scanlines as well as the scene structure. Our method learns from a large-scale dataset synthesized in a geometrically meaningful way where the RS effect is generated in a manner consistent with the camera motion and scene structure. In extensive experiments, our method achieves superior performance compared to other state-of-the-art methods for single image RS correction and subsequent Structure from Motion (SfM) applications. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Zhuang_Learning_Structure-And-Motion-Aware_Rolling_Shutter_Correction_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Zhuang_Learning_Structure-And-Motion-Aware_Rolling_Shutter_Correction_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-structure-and-motion-aware-rolling |
| Repo | |
| Framework | |
Cross-document coreference: An approach to capturing coreference without context
| Title | Cross-document coreference: An approach to capturing coreference without context |
| Authors | Kristin Wright-Bettner, Martha Palmer, Guergana Savova, Piet de Groen, Timothy Miller |
| Abstract | This paper discusses a cross-document coreference annotation schema that was developed to further automatic extraction of timelines in the clinical domain. Lexical senses and coreference choices are determined largely by context, but cross-document work requires reasoning across contexts that are not necessarily coherent. We found that an annotation approach that relies less on context-guided annotator intuitions and more on schematic rules was most effective in creating meaningful and consistent cross-document relations. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-6201/ |
| https://www.aclweb.org/anthology/D19-6201 | |
| PWC | https://paperswithcode.com/paper/cross-document-coreference-an-approach-to |
| Repo | |
| Framework | |
Proceedings of the 2nd Clinical Natural Language Processing Workshop
| Title | Proceedings of the 2nd Clinical Natural Language Processing Workshop |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1900/ |
| https://www.aclweb.org/anthology/W19-1900 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2nd-clinical-natural |
| Repo | |
| Framework | |
Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
| Title | Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5900/ |
| https://www.aclweb.org/anthology/W19-5900 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-20th-annual-sigdial |
| Repo | |
| Framework | |
Arabic Named Entity Recognition: What Works and What’s Next
| Title | Arabic Named Entity Recognition: What Works and What’s Next |
| Authors | Liyuan Liu, Jingbo Shang, Jiawei Han |
| Abstract | This paper presents the winning solution to the Arabic Named Entity Recognition challenge run by Topcoder.com. The proposed model integrates various tailored techniques together, including representation learning, feature engineering, sequence labeling, and ensemble learning. The final model achieves a test F{_}1 score of 75.82{%} on the AQMAR dataset and outperforms baselines by a large margin. Detailed analyses are conducted to reveal both its strengths and limitations. Specifically, we observe that (1) representation learning modules can significantly boost the performance but requires a proper pre-processing and (2) the resulting embedding can be further enhanced with feature engineering due to the limited size of the training data. All implementations and pre-trained models are made public. |
| Tasks | Feature Engineering, Named Entity Recognition, Representation Learning |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4607/ |
| https://www.aclweb.org/anthology/W19-4607 | |
| PWC | https://paperswithcode.com/paper/arabic-named-entity-recognition-what-works |
| Repo | |
| Framework | |
HEvAS: Headline Evaluation and Analysis System
| Title | HEvAS: Headline Evaluation and Analysis System |
| Authors | Marina Litvak, Natalia Vanetik, Itzhak Eretz Kdosha |
| Abstract | Automatic headline generation is a subtask of one-line summarization with many reported applications. Evaluation of systems generating headlines is a very challenging and undeveloped area. We introduce the Headline Evaluation and Analysis System (HEvAS) that performs automatic evaluation of systems in terms of a quality of the generated headlines. HEvAS provides two types of metrics{–} one which measures the informativeness of a headline, and another that measures its readability. The results of evaluation can be compared to the results of baseline methods which are implemented in HEvAS. The system also performs the statistical analysis of the evaluation results and provides different visualization charts. This paper describes all evaluation metrics, baselines, analysis, and architecture, utilized by our system. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8910/ |
| https://www.aclweb.org/anthology/W19-8910 | |
| PWC | https://paperswithcode.com/paper/hevas-headline-evaluation-and-analysis-system |
| Repo | |
| Framework | |
MrMep: Joint Extraction of Multiple Relations and Multiple Entity Pairs Based on Triplet Attention
| Title | MrMep: Joint Extraction of Multiple Relations and Multiple Entity Pairs Based on Triplet Attention |
| Authors | Jiayu Chen, Caixia Yuan, Xiaojie Wang, Ziwei Bai |
| Abstract | This paper focuses on how to extract multiple relational facts from unstructured text. Neural encoder-decoder models have provided a viable new approach for jointly extracting relations and entity pairs. However, these models either fail to deal with entity overlapping among relational facts, or neglect to produce the whole entity pairs. In this work, we propose a novel architecture that augments the encoder and decoder in two elegant ways. First, we apply a binary CNN classifier for each relation, which identifies all possible relations maintained in the text, while retaining the target relation representation to aid entity pair recognition. Second, we perform a multi-head attention over the text and a triplet attention with the target relation interacting with every token of the text to precisely produce all possible entity pairs in a sequential manner. Experiments on three benchmark datasets show that our proposed method successfully addresses the multiple relations and multiple entity pairs even with complex overlapping and significantly outperforms the state-of-the-art methods. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1055/ |
| https://www.aclweb.org/anthology/K19-1055 | |
| PWC | https://paperswithcode.com/paper/mrmep-joint-extraction-of-multiple-relations |
| Repo | |
| Framework | |
