Paper Group NANR 122
Modeling Financial Analysts’ Decision Making via the Pragmatics and Semantics of Earnings Calls. Assessing the Ability of Neural Machine Translation Models to Perform Syntactic Rewriting. Detecting Paraphrases of Standard Clause Titles in Insurance Contracts. Learning to Film From Professional Human Motion Videos. Incorporating Fine-grained Events …
Modeling Financial Analysts’ Decision Making via the Pragmatics and Semantics of Earnings Calls
| Title | Modeling Financial Analysts’ Decision Making via the Pragmatics and Semantics of Earnings Calls |
| Authors | Katherine Keith, Am Stent, a |
| Abstract | Every fiscal quarter, companies hold earnings calls in which company executives respond to questions from analysts. After these calls, analysts often change their price target recommendations, which are used in equity re- search reports to help investors make deci- sions. In this paper, we examine analysts{'} decision making behavior as it pertains to the language content of earnings calls. We identify a set of 20 pragmatic features of analysts{'} questions which we correlate with analysts{'} pre-call investor recommendations. We also analyze the degree to which semantic and pragmatic features from an earnings call complement market data in predicting analysts{'} post-call changes in price targets. Our results show that earnings calls are moderately predictive of analysts{'} decisions even though these decisions are influenced by a number of other factors including private communication with company executives and market conditions. A breakdown of model errors indicates disparate performance on calls from different market sectors. |
| Tasks | Decision Making |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1047/ |
| https://www.aclweb.org/anthology/P19-1047 | |
| PWC | https://paperswithcode.com/paper/modeling-financial-analysts-decision-making-1 |
| Repo | |
| Framework | |
Assessing the Ability of Neural Machine Translation Models to Perform Syntactic Rewriting
| Title | Assessing the Ability of Neural Machine Translation Models to Perform Syntactic Rewriting |
| Authors | Jahkel Robin, Alvin Grissom II, Matthew Roselli |
| Abstract | We describe work in progress for evaluating performance of sequence-to-sequence neural networks on the task of syntax-based reordering for rules applicable to simultaneous machine translation. We train models that attempt to rewrite English sentences using rules that are commonly used by human interpreters. We examine the performance of these models to determine which forms of rewriting are more difficult for them to learn and which architectures are the best at learning them. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3648/ |
| https://www.aclweb.org/anthology/W19-3648 | |
| PWC | https://paperswithcode.com/paper/assessing-the-ability-of-neural-machine |
| Repo | |
| Framework | |
Detecting Paraphrases of Standard Clause Titles in Insurance Contracts
| Title | Detecting Paraphrases of Standard Clause Titles in Insurance Contracts |
| Authors | Frieda Josi, Christian Wartena, Ulrich Heid |
| Abstract | For the analysis of contract texts, validated model texts, such as model clauses, can be used to identify reused contract clauses. This paper investigates how to calculate the similarity between titles of model clauses and headings extracted from contracts, and which similarity measure is most suitable for this. For the calculation of the similarities between title pairs we tested various variants of string similarity and token based similarity. We also compare two more semantic similarity measures based on word embeddings using pretrained embeddings and word embeddings trained on contract texts. The identification of the model clause title can be used as a starting point for the mapping of clauses found in contracts to verified clauses. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Word Embeddings |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0803/ |
| https://www.aclweb.org/anthology/W19-0803 | |
| PWC | https://paperswithcode.com/paper/detecting-paraphrases-of-standard-clause |
| Repo | |
| Framework | |
Learning to Film From Professional Human Motion Videos
| Title | Learning to Film From Professional Human Motion Videos |
| Authors | Chong Huang, Chuan-En Lin, Zhenyu Yang, Yan Kong, Peng Chen, Xin Yang, Kwang-Ting Cheng |
| Abstract | We investigate the problem of 6 degrees of freedom (DOF) camera planning for filming professional human motion videos using a camera drone. Existing methods either plan motions for only a pan-tilt-zoom (PTZ) camera, or adopt ad-hoc solutions without carefully considering the impact of video contents and previous camera motions on the future camera motions. As a result, they can hardly achieve satisfactory results in our drone cinematography task. In this study, we propose a learning-based framework which incorporates the video contents and previous camera motions to predict the future camera motions that enable the capture of professional videos. Specifically, the inputs of our framework are video contents which are represented using subject-related feature based on 2D skeleton and scene-related features extracted from background RGB images, and camera motions which are represented using optical flows. The correlation between the inputs and output future camera motions are learned via a sequence-to-sequence convolutional long short-term memory (Seq2Seq ConvLSTM) network from a large set of video clips. We deploy our approach to a real drone cinematography system by first predicting the future camera motions, and then converting them to the drone’s control commands via an odometer. Our experimental results on extensive datasets and showcases exhibit significant improvements in our approach over conventional baselines and our approach can successfully mimic the footage of a professional cameraman. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Huang_Learning_to_Film_From_Professional_Human_Motion_Videos_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Huang_Learning_to_Film_From_Professional_Human_Motion_Videos_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-film-from-professional-human |
| Repo | |
| Framework | |
Incorporating Fine-grained Events in Stock Movement Prediction
| Title | Incorporating Fine-grained Events in Stock Movement Prediction |
| Authors | Deli Chen, Yanyan Zou, Keiko Harimoto, Ruihan Bao, Xuancheng Ren, Xu Sun |
| Abstract | Considering event structure information has proven helpful in text-based stock movement prediction. However, existing works mainly adopt the coarse-grained events, which loses the specific semantic information of diverse event types. In this work, we propose to incorporate the fine-grained events in stock movement prediction. Firstly, we propose a professional finance event dictionary built by domain experts and use it to extract fine-grained events automatically from finance news. Then we design a neural model to combine finance news with fine-grained event structure and stock trade data to predict the stock movement. Besides, in order to improve the generalizability of the proposed method, we design an advanced model that uses the extracted fine-grained events as the distant supervised label to train a multi-task framework of event extraction and stock prediction. The experimental results show that our method outperforms all the baselines and has good generalizability. |
| Tasks | Stock Prediction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5105/ |
| https://www.aclweb.org/anthology/D19-5105 | |
| PWC | https://paperswithcode.com/paper/incorporating-fine-grained-events-in-stock |
| Repo | |
| Framework | |
Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network
| Title | Aspect Sentiment Classification Towards Question-Answering with Reinforced Bidirectional Attention Network |
| Authors | Jingjing Wang, Changlong Sun, Shoushan Li, Xiaozhong Liu, Luo Si, Min Zhang, Guodong Zhou |
| Abstract | In the literature, existing studies on aspect sentiment classification (ASC) focus on individual non-interactive reviews. This paper extends the research to interactive reviews and proposes a new research task, namely Aspect Sentiment Classification towards Question-Answering (ASC-QA), for real-world applications. This new task aims to predict sentiment polarities for specific aspects from interactive QA style reviews. In particular, a high-quality annotated corpus is constructed for ASC-QA to facilitate corresponding research. On this basis, a Reinforced Bidirectional Attention Network (RBAN) approach is proposed to address two inherent challenges in ASC-QA, i.e., semantic matching between question and answer, and data noise. Experimental results demonstrate the great advantage of the proposed approach to ASC-QA against several state-of-the-art baselines. |
| Tasks | Question Answering, Sentiment Analysis |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1345/ |
| https://www.aclweb.org/anthology/P19-1345 | |
| PWC | https://paperswithcode.com/paper/aspect-sentiment-classification-towards |
| Repo | |
| Framework | |
North S'ami morphological segmentation with low-resource semi-supervised sequence labeling
| Title | North S'ami morphological segmentation with low-resource semi-supervised sequence labeling |
| Authors | Stig-Arne Gr{"o}nroos, S{'a}mi Virpioja, Mikko Kurimo |
| Abstract | |
| Tasks | |
| Published | 2019-01-01 |
| URL | https://www.aclweb.org/anthology/W19-0302/ |
| https://www.aclweb.org/anthology/W19-0302 | |
| PWC | https://paperswithcode.com/paper/north-sami-morphological-segmentation-with |
| Repo | |
| Framework | |
Extraction of Message Sequence Charts from Software Use-Case Descriptions
| Title | Extraction of Message Sequence Charts from Software Use-Case Descriptions |
| Authors | Girish Palshikar, Nitin Ramrakhiyani, Sangameshwar Patil, Sachin Pawar, Swapnil Hingmire, Vasudeva Varma, Pushpak Bhattacharyya |
| Abstract | Software Requirement Specification documents provide natural language descriptions of the core functional requirements as a set of use-cases. Essentially, each use-case contains a set of actors and sequences of steps describing the interactions among them. Goals of use-case reviews and analyses include their correctness, completeness, detection of ambiguities, prototyping, verification, test case generation and traceability. Message Sequence Chart (MSC) have been proposed as a expressive, rigorous yet intuitive visual representation of use-cases. In this paper, we describe a linguistic knowledge-based approach to extract MSCs from use-cases. Compared to existing techniques, we extract richer constructs of the MSC notation such as timers, conditions and alt-boxes. We apply this tool to extract MSCs from several real-life software use-case descriptions and show that it performs better than the existing techniques. We also discuss the benefits and limitations of the extracted MSCs to meet the above goals. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-2017/ |
| https://www.aclweb.org/anthology/N19-2017 | |
| PWC | https://paperswithcode.com/paper/extraction-of-message-sequence-charts-from |
| Repo | |
| Framework | |
TILM: Neural Language Models with Evolving Topical Influence
| Title | TILM: Neural Language Models with Evolving Topical Influence |
| Authors | Shubhra Kanti Karmaker Santu, Kalyan Veeramachaneni, Chengxiang Zhai |
| Abstract | Content of text data are often influenced by contextual factors which often evolve over time (e.g., content of social media are often influenced by topics covered in the major news streams). Existing language models do not consider the influence of such related evolving topics, and thus are not optimal. In this paper, we propose to incorporate such topical-influence into a language model to both improve its accuracy and enable cross-stream analysis of topical influences. Specifically, we propose a novel language model called Topical Influence Language Model (TILM), which is a novel extension of a neural language model to capture the influences on the contents in one text stream by the evolving topics in another related (or possibly same) text stream. Experimental results on six different text stream data comprised of conference paper titles show that the incorporation of evolving topical influence into a language model is beneficial and TILM outperforms multiple baselines in a challenging task of text forecasting. In addition to serving as a language model, TILM further enables interesting analysis of topical influence among multiple text streams. |
| Tasks | Language Modelling |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1073/ |
| https://www.aclweb.org/anthology/K19-1073 | |
| PWC | https://paperswithcode.com/paper/tilm-neural-language-models-with-evolving |
| Repo | |
| Framework | |
Is the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts
| Title | Is the Red Square Big? MALeViC: Modeling Adjectives Leveraging Visual Contexts |
| Authors | S Pezzelle, ro, Raquel Fern{'a}ndez |
| Abstract | This work aims at modeling how the meaning of gradable adjectives of size ({}big{'}, {}small{'}) can be learned from visually-grounded contexts. Inspired by cognitive and linguistic evidence showing that the use of these expressions relies on setting a threshold that is dependent on a specific context, we investigate the ability of multi-modal models in assessing whether an object is {}big{'} or {}small{'} in a given visual scene. In contrast with the standard computational approach that simplistically treats gradable adjectives as {`}fixed{'} attributes, we pose the problem as relational: to be successful, a model has to consider the full visual context. By means of four main tasks, we show that state-of-the-art models (but not a relatively strong baseline) can learn the function subtending the meaning of size adjectives, though their performance is found to decrease while moving from simple to more complex tasks. Crucially, models fail in developing abstract representations of gradable adjectives that can be used compositionally. | |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1285/ |
| https://www.aclweb.org/anthology/D19-1285 | |
| PWC | https://paperswithcode.com/paper/is-the-red-square-big-malevic-modeling-1 |
| Repo | |
| Framework | |
PuppetGAN: Cross-Domain Image Manipulation by Demonstration
| Title | PuppetGAN: Cross-Domain Image Manipulation by Demonstration |
| Authors | Ben Usman, Nick Dufour, Kate Saenko, Chris Bregler |
| Abstract | In this work we propose a model that can manipulate individual visual attributes of objects in a real scene using examples of how respective attribute manipulations affect the output of a simulation. As an example, we train our model to manipulate the expression of a human face using nonphotorealistic 3D renders of a face with varied expression. Our model manages to preserve all other visual attributes of a real face, such as head orientation, even though this and other attributes are not labeled in either real or synthetic domain. Since our model learns to manipulate a specific property in isolation using only “synthetic demonstrations” of such manipulations without explicitly provided labels, it can be applied to shape, texture, lighting, and other properties that are difficult to measure or represent as real-valued vectors. We measure the degree to which our model preserves other attributes of a real image when a single specific attribute is manipulated. We use digit datasets to analyze how discrepancy in attribute distributions affects the performance of our model, and demonstrate results in a far more difficult setting: learning to manipulate real human faces using nonphotorealistic 3D renders. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Usman_PuppetGAN_Cross-Domain_Image_Manipulation_by_Demonstration_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Usman_PuppetGAN_Cross-Domain_Image_Manipulation_by_Demonstration_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/puppetgan-cross-domain-image-manipulation-by |
| Repo | |
| Framework | |
Active Learning for Financial Investment Reports
| Title | Active Learning for Financial Investment Reports |
| Authors | Sian Gooding, Ted Briscoe |
| Abstract | |
| Tasks | Active Learning |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6404/ |
| https://www.aclweb.org/anthology/W19-6404 | |
| PWC | https://paperswithcode.com/paper/active-learning-for-financial-investment |
| Repo | |
| Framework | |
Sentiment Independent Topic Detection in Rated Hospital Reviews
| Title | Sentiment Independent Topic Detection in Rated Hospital Reviews |
| Authors | Christian Wartena, S, Uwe er, Christiane Patzelt |
| Abstract | We present a simple method to find topics in user reviews that accompany ratings for products or services. Standard topic analysis will perform sub-optimal on such data since the word distributions in the documents are not only determined by the topics but by the sentiment as well. We reduce the influence of the sentiment on the topic selection by adding two explicit topics, representing positive and negative sentiment. We evaluate the proposed method on a set of over 15,000 hospital reviews. We show that the proposed method, Latent Semantic Analysis with explicit word features, finds topics with a much smaller bias for sentiments than other similar methods. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0509/ |
| https://www.aclweb.org/anthology/W19-0509 | |
| PWC | https://paperswithcode.com/paper/sentiment-independent-topic-detection-in |
| Repo | |
| Framework | |
Multi-Task Learning for Semantic Parsing with Cross-Domain Sketch
| Title | Multi-Task Learning for Semantic Parsing with Cross-Domain Sketch |
| Authors | Huan Wang, Yuxiang Hu, Li Dong, Feijun Jiang, Zaiqing Nie |
| Abstract | Semantic parsing which maps a natural language sentence into a formal machine-readable representation of its meaning, is highly constrained by the limited annotated training data. Inspired by the idea of coarse-to-fine, we propose a general-to-detailed neural network(GDNN) by incorporating cross-domain sketch(CDS) among utterances and their logic forms. For utterances in different domains, the General Network will extract CDS using an encoder-decoder model in a multi-task learning setup. Then for some utterances in a specific domain, the Detailed Network will generate the detailed target parts using sequence-to-sequence architecture with advanced attention to both utterance and generated CDS. Our experiments show that compared to direct multi-task learning, CDS has improved the performance in semantic parsing task which converts users’ requests into meaning representation language(MRL). We also use experiments to illustrate that CDS works by adding some constraints to the target decoding process, which further proves the effectiveness and rationality of CDS. |
| Tasks | Multi-Task Learning, Semantic Parsing |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=r1fO8oC9Y7 |
| https://openreview.net/pdf?id=r1fO8oC9Y7 | |
| PWC | https://paperswithcode.com/paper/multi-task-learning-for-semantic-parsing-with |
| Repo | |
| Framework | |
Findings of the WMT 2019 Shared Task on Automatic Post-Editing
| Title | Findings of the WMT 2019 Shared Task on Automatic Post-Editing |
| Authors | Rajen Chatterjee, Christian Federmann, Matteo Negri, Marco Turchi |
| Abstract | We present the results from the 5th round of the WMT task on MT Automatic Post-Editing. The task consists in automatically correcting the output of a {``}black-box{''} machine translation system by learning from human corrections. Keeping the same general evaluation setting of the previous four rounds, this year we focused on two language pairs (English-German and English-Russian) and on domain-specific data (In-formation Technology). For both the language directions, MT outputs were produced by neural systems unknown to par-ticipants. Seven teams participated in the English-German task, with a total of 18 submitted runs. The evaluation, which was performed on the same test set used for the 2018 round, shows a slight progress in APE technology: 4 teams achieved better results than last year{'}s winning system, with improvements up to -0.78 TER and +1.23 BLEU points over the baseline. Two teams participated in theEnglish-Russian task submitting 2 runs each. On this new language direction, characterized by a higher quality of the original translations, the task proved to be particularly challenging. None of the submitted runs improved the very high results of the strong system used to produce the initial translations(16.16 TER, 76.20 BLEU). | |
| Tasks | Automatic Post-Editing, Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5402/ |
| https://www.aclweb.org/anthology/W19-5402 | |
| PWC | https://paperswithcode.com/paper/findings-of-the-wmt-2019-shared-task-on |
| Repo | |
| Framework | |
