Paper Group NANR 35
A Machine Learning Approach for Identifying Compound Words from a Sanskrit Text. Reflexives in Czech from a Dependency Perspective. hpGAT: High-order Proximity Informed Graph Attention Network. Experiments on human incremental parsing. Amharic Question Answering for Biography, Definition, and Description Questions. On reducing translation shifts in …
A Machine Learning Approach for Identifying Compound Words from a Sanskrit Text
| Title | A Machine Learning Approach for Identifying Compound Words from a Sanskrit Text |
| Authors | Premjith B, Ch V, ni Ch, ran, Shriganesh Bhat, Soman Kp, Prabaharan P |
| Abstract | |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-7504/ |
| https://www.aclweb.org/anthology/W19-7504 | |
| PWC | https://paperswithcode.com/paper/a-machine-learning-approach-for-identifying-1 |
| Repo | |
| Framework | |
Reflexives in Czech from a Dependency Perspective
| Title | Reflexives in Czech from a Dependency Perspective |
| Authors | Vaclava Kettnerova, Marketa Lopatkova |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7704/ |
| https://www.aclweb.org/anthology/W19-7704 | |
| PWC | https://paperswithcode.com/paper/reflexives-in-czech-from-a-dependency |
| Repo | |
| Framework | |
hpGAT: High-order Proximity Informed Graph Attention Network
| Title | hpGAT: High-order Proximity Informed Graph Attention Network |
| Authors | Zhining Liu, Weiyi Liu, Pin-yu Chen, Chenyi Zhuang, Chengyun Song |
| Abstract | Graph neural networks (GNNs) have recently made remarkable breakthroughs in the paradigm of learning with graph-structured data. However, most existing GNNs limit the receptive field of the node on each layer to its connected (one-hop) neighbors, which disregards the fact that large receptive field has been proven to be a critical factor in state-of-the-art neural networks. In this paper, we propose a novel approach to appropriately define a variable receptive field for GNNs by incorporating high-order proximity information extracted from the hierarchical topological structure of the input graph. Specifically, multiscale groups obtained from trainable hierarchical semi-nonnegative matrix factorization are used for adjusting the weights when aggregating one-hop neighbors. Integrated with the graph attention mechanism on attributes of neighboring nodes, the learnable parameters within the process of aggregation are optimized in an end-to-end manner. Extensive experiments show that the proposed method (hpGAT) outperforms state-of-the-art methods and demonstrate the importance of exploiting high-order proximity in handling noisy information of local neighborhood. |
| Tasks | Node Classification |
| Published | 2019-08-28 |
| URL | https://doi.org/10.1109/ACCESS.2019.2938039 |
| https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=8818141 | |
| PWC | https://paperswithcode.com/paper/hpgat-high-order-proximity-informed-graph |
| Repo | |
| Framework | |
Experiments on human incremental parsing
| Title | Experiments on human incremental parsing |
| Authors | Leonid Mityushin, Leonid Iomdin |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-7725/ |
| https://www.aclweb.org/anthology/W19-7725 | |
| PWC | https://paperswithcode.com/paper/experiments-on-human-incremental-parsing |
| Repo | |
| Framework | |
Amharic Question Answering for Biography, Definition, and Description Questions
| Title | Amharic Question Answering for Biography, Definition, and Description Questions |
| Authors | Tilahun Abedissa Taffa, Mulugeta Libsie |
| Abstract | A broad range of information needs can often be stated as a question. Question Answering (QA) systems attempt to provide users concise answer(s) to natural language questions. The existing Amharic QA systems handle fact-based questions that usually take named entities as an answer. To deal with more complex information needs we developed an Amharic non-factoid QA for biography, definition, and description questions. A hybrid approach has been used for the question classification. For document filtering and answer extraction we have used lexical patterns. On the other hand to answer biography questions we have used a summarizer and the generated summary is validated using a text classifier. Our QA system is evaluated and has shown a promising result. |
| Tasks | Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3635/ |
| https://www.aclweb.org/anthology/W19-3635 | |
| PWC | https://paperswithcode.com/paper/amharic-question-answering-for-biography |
| Repo | |
| Framework | |
On reducing translation shifts in translations intended for MT evaluation
| Title | On reducing translation shifts in translations intended for MT evaluation |
| Authors | Maja Popovic |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6712/ |
| https://www.aclweb.org/anthology/W19-6712 | |
| PWC | https://paperswithcode.com/paper/on-reducing-translation-shifts-in |
| Repo | |
| Framework | |
Memory Grounded Conversational Reasoning
| Title | Memory Grounded Conversational Reasoning |
| Authors | Seungwhan Moon, Pararth Shah, Rajen Subba, Anuj Kumar |
| Abstract | We demonstrate a conversational system which engages the user through a multi-modal, multi-turn dialog over the user{'}s memories. The system can perform QA over memories by responding to user queries to recall specific attributes and associated media (e.g. photos) of past episodic memories. The system can also make proactive suggestions to surface related events or facts from past memories to make conversations more engaging and natural. To implement such a system, we collect a new corpus of memory grounded conversations, which comprises human-to-human role-playing dialogs given synthetic memory graphs with simulated attributes. Our proof-of-concept system operates on these synthetic memory graphs, however it can be trained and applied to real-world user memory data (e.g. photo albums, etc.) We present the architecture of the proposed conversational system, and example queries that the system supports. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3025/ |
| https://www.aclweb.org/anthology/D19-3025 | |
| PWC | https://paperswithcode.com/paper/memory-grounded-conversational-reasoning |
| Repo | |
| Framework | |
Unsupervised Learning of Discourse-Aware Text Representation for Essay Scoring
| Title | Unsupervised Learning of Discourse-Aware Text Representation for Essay Scoring |
| Authors | Farjana Sultana Mim, Naoya Inoue, Paul Reisert, Hiroki Ouchi, Kentaro Inui |
| Abstract | Existing document embedding approaches mainly focus on capturing sequences of words in documents. However, some document classification and regression tasks such as essay scoring need to consider discourse structure of documents. Although some prior approaches consider this issue and utilize discourse structure of text for document classification, these approaches are dependent on computationally expensive parsers. In this paper, we propose an unsupervised approach to capture discourse structure in terms of coherence and cohesion for document embedding that does not require any expensive parser or annotation. Extrinsic evaluation results show that the document representation obtained from our approach improves the performance of essay Organization scoring and Argument Strength scoring. |
| Tasks | Document Classification, Document Embedding |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2053/ |
| https://www.aclweb.org/anthology/P19-2053 | |
| PWC | https://paperswithcode.com/paper/unsupervised-learning-of-discourse-aware-text |
| Repo | |
| Framework | |
Using Meta-Morph Rules to develop Morphological Analysers: A case study concerning Tamil
| Title | Using Meta-Morph Rules to develop Morphological Analysers: A case study concerning Tamil |
| Authors | Kengatharaiyer Sarveswaran, Gihan Dias, Miriam Butt |
| Abstract | This paper describes a new and larger coverage Finite-State Morphological Analyser (FSM) and Generator for the Dravidian language Tamil. The FSM has been developed in the context of computational grammar engineering, adhering to the standards of the ParGram effort. Tamil is a morphologically rich language and the interaction between linguistic analysis and formal implementation is complex, resulting in a challenging task. In order to allow the development of the FSM to focus more on the linguistic analysis and less on the formal details, we have developed a system of meta-morph(ology) rules along with a script which translates these rules into FSM processable representations. The introduction of meta-morph rules makes it possible for computationally naive linguists to interact with the system and to expand it in future work. We found that the meta-morph rules help to express linguistic generalisations and reduce the manual effort of writing lexical classes for morphological analysis. Our Tamil FSM currently handles mainly the inflectional morphology of 3,300 verb roots and their 260 forms. Further, it also has a lexicon of approximately 100,000 nouns along with a guesser to handle out-of-vocabulary items. Although the Tamil FSM was primarily developed to be part of a computational grammar, it can also be used as a web or stand-alone application for other NLP tasks, as per general ParGram practice. |
| Tasks | Morphological Analysis |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-3111/ |
| https://www.aclweb.org/anthology/W19-3111 | |
| PWC | https://paperswithcode.com/paper/using-meta-morph-rules-to-develop |
| Repo | |
| Framework | |
MultiSeg: Semantically Meaningful, Scale-Diverse Segmentations From Minimal User Input
| Title | MultiSeg: Semantically Meaningful, Scale-Diverse Segmentations From Minimal User Input |
| Authors | Jun Hao Liew, Scott Cohen, Brian Price, Long Mai, Sim-Heng Ong, Jiashi Feng |
| Abstract | Existing deep learning-based interactive image segmentation approaches typically assume the target-of-interest is always a single object and fail to account for the potential diversity in user expectations, thus requiring excessive user input when it comes to segmenting an object part or a group of objects instead. Motivated by the observation that the object part, full object, and a collection of objects essentially differ in size, we propose a new concept called scale-diversity, which characterizes the spectrum of segmentations w.r.t. different scales. To address this, we present MultiSeg, a scale-diverse interactive image segmentation network that incorporates a set of two-dimensional scale priors into the model to generate a set of scale-varying proposals that conform to the user input. We explicitly encourage segmentation diversity during training by synthesizing diverse training samples for a given image. As a result, our method allows the user to quickly locate the closest segmentation target for further refinement if necessary. Despite its simplicity, experimental results demonstrate that our proposed model is capable of quickly producing diverse yet plausible segmentation outputs, reducing the user interaction required, especially in cases where many types of segmentations (object parts or groups) are expected. |
| Tasks | Semantic Segmentation |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Liew_MultiSeg_Semantically_Meaningful_Scale-Diverse_Segmentations_From_Minimal_User_Input_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Liew_MultiSeg_Semantically_Meaningful_Scale-Diverse_Segmentations_From_Minimal_User_Input_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/multiseg-semantically-meaningful-scale |
| Repo | |
| Framework | |
The Private Income Tax Shock Premium
| Title | The Private Income Tax Shock Premium |
| Authors | Zornitsa Todorova |
| Abstract | This paper investigates the asset pricing implications of tax policy changes. News about tax cuts decreases future tax revenues and increases future consumer demand and output. Using cross-sectional variation in industry exposure to structurally identified tax news, I develop a factor mimicking private income tax shocks. I construct an investment strategy, which generates annualized risk-adjusted returns of 5.16 % over the Fama-French 3-factor model. I rationalize the finding by arguing that firms with more elastic demands bear higher consumption risk, which works through a wealth effect. |
| Tasks | |
| Published | 2019-07-30 |
| URL | https://ijbassnet.com/publication/248/details |
| https://ijbassnet.com/storage/app/publications/5d40181c3bf5911564481564.pdf | |
| PWC | https://paperswithcode.com/paper/the-private-income-tax-shock-premium |
| Repo | |
| Framework | |
Phonetic Normalization for Machine Translation of User Generated Content
| Title | Phonetic Normalization for Machine Translation of User Generated Content |
| Authors | Jos{'e} Carlos Rosales N{'u}{~n}ez, Djam{'e} Seddah, Guillaume Wisniewski |
| Abstract | We present an approach to correct noisy User Generated Content (UGC) in French aiming to produce a pretreatement pipeline to improve Machine Translation for this kind of non-canonical corpora. In order to do so, we have implemented a character-based neural model phonetizer to produce IPA pronunciations of words. In this way, we intend to correct grammar, vocabulary and accentuation errors often present in noisy UGC corpora. Our method leverages on the fact that some errors are due to confusion induced by words with similar pronunciation which can be corrected using a phonetic look-up table to produce normalization candidates. These potential corrections are then encoded in a lattice and ranked using a language model to output the most probable corrected phrase. Compare to using other phonetizers, our method boosts a transformer-based machine translation system on UGC. |
| Tasks | Language Modelling, Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5553/ |
| https://www.aclweb.org/anthology/D19-5553 | |
| PWC | https://paperswithcode.com/paper/phonetic-normalization-for-machine |
| Repo | |
| Framework | |
Grounded Word Sense Translation
| Title | Grounded Word Sense Translation |
| Authors | Chiraag Lala, Pranava Madhyastha, Lucia Specia |
| Abstract | Recent work on visually grounded language learning has focused on broader applications of grounded representations, such as visual question answering and multimodal machine translation. In this paper we consider grounded word sense translation, i.e. the task of correctly translating an ambiguous source word given the corresponding textual and visual context. Our main objective is to investigate the extent to which images help improve word-level (lexical) translation quality. We do so by first studying the dataset for this task to understand the scope and challenges of the task. We then explore different data settings, image features, and ways of grounding to investigate the gain from using images in each of the combinations. We find that grounding on the image is specially beneficial in weaker unidirectional recurrent translation models. We observe that adding structured image information leads to stronger gains in lexical translation accuracy. |
| Tasks | Machine Translation, Multimodal Machine Translation, Question Answering, Visual Question Answering |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1808/ |
| https://www.aclweb.org/anthology/W19-1808 | |
| PWC | https://paperswithcode.com/paper/grounded-word-sense-translation |
| Repo | |
| Framework | |
HITSZ-ICRC: A Report for SMM4H Shared Task 2019-Automatic Classification and Extraction of Adverse Effect Mentions in Tweets
| Title | HITSZ-ICRC: A Report for SMM4H Shared Task 2019-Automatic Classification and Extraction of Adverse Effect Mentions in Tweets |
| Authors | Shuai Chen, Yuanhang Huang, Xiaowei Huang, Haoming Qin, Jun Yan, Buzhou Tang |
| Abstract | This is the system description of the Harbin Institute of Technology Shenzhen (HITSZ) team for the first and second subtasks of the fourth Social Media Mining for Health Applications (SMM4H) shared task in 2019. The two subtasks are automatic classification and extraction of adverse effect mentions in tweets. The systems for the two subtasks are based on bidirectional encoder representations from transformers (BERT), and achieves promising results. Among the systems we developed for subtask1, the best F1-score was 0.6457, for subtask2, the best relaxed F1-score and the best strict F1-score were 0.614 and 0.407 respectively. Our system ranks first among all systems on subtask1. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3206/ |
| https://www.aclweb.org/anthology/W19-3206 | |
| PWC | https://paperswithcode.com/paper/hitsz-icrc-a-report-for-smm4h-shared-task |
| Repo | |
| Framework | |
KFU NLP Team at SMM4H 2019 Tasks: Want to Extract Adverse Drugs Reactions from Tweets? BERT to The Rescue
| Title | KFU NLP Team at SMM4H 2019 Tasks: Want to Extract Adverse Drugs Reactions from Tweets? BERT to The Rescue |
| Authors | Zulfat Miftahutdinov, Ilseyar Alimova, Elena Tutubalina |
| Abstract | This paper describes a system developed for the Social Media Mining for Health (SMM4H) 2019 shared tasks. Specifically, we participated in three tasks. The goals of the first two tasks are to classify whether a tweet contains mentions of adverse drug reactions (ADR) and extract these mentions, respectively. The objective of the third task is to build an end-to-end solution: first, detect ADR mentions and then map these entities to concepts in a controlled vocabulary. We investigate the use of a language representation model BERT trained to obtain semantic representations of social media texts. Our experiments on a dataset of user reviews showed that BERT is superior to state-of-the-art models based on recurrent neural networks. The BERT-based system for Task 1 obtained an F1 of 57.38{%}, with improvements up to +7.19{%} F1 over a score averaged across all 43 submissions. The ensemble of neural networks with a voting scheme for named entity recognition ranked first among 9 teams at the SMM4H 2019 Task 2 and obtained a relaxed F1 of 65.8{%}. The end-to-end model based on BERT for ADR normalization ranked first at the SMM4H 2019 Task 3 and obtained a relaxed F1 of 43.2{%}. |
| Tasks | Named Entity Recognition |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3207/ |
| https://www.aclweb.org/anthology/W19-3207 | |
| PWC | https://paperswithcode.com/paper/kfu-nlp-team-at-smm4h-2019-tasks-want-to |
| Repo | |
| Framework | |
