Paper Group NANR 138
A Deep Learning-Based System for PharmaCoNER. Term Based Semantic Clusters for Very Short Text Classification. A Robust Self-Learning Framework for Cross-Lingual Text Classification. Similar Minds Post Alike: Assessment of Suicide Risk Using a Hybrid Model. Controlling Japanese Honorifics in English-to-Japanese Neural Machine Translation. Surface R …
A Deep Learning-Based System for PharmaCoNER
| Title | A Deep Learning-Based System for PharmaCoNER |
| Authors | Ying Xiong, Yedan Shen, Yuanhang Huang, Shuai Chen, Buzhou Tang, Xiaolong Wang, Qingcai Chen, Jun Yan, Yi Zhou |
| Abstract | The Biological Text Mining Unit at BSC and CNIO organized the first shared task on chemical {&} drug mention recognition from Spanish medical texts called PharmaCoNER (Pharmacological Substances, Compounds and proteins and Named Entity Recognition track) in 2019, which includes two tracks: one for NER offset and entity classification (track 1) and the other one for concept indexing (track 2). We developed a pipeline system based on deep learning methods for this shared task, specifically, a subsystem based on BERT (Bidirectional Encoder Representations from Transformers) for NER offset and entity classification and a subsystem based on Bpool (Bi-LSTM with max/mean pooling) for concept indexing. Evaluation conducted on the shared task data showed that our system achieves a micro-average F1-score of 0.9105 on track 1 and a micro-average F1-score of 0.8391 on track 2. |
| Tasks | Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5706/ |
| https://www.aclweb.org/anthology/D19-5706 | |
| PWC | https://paperswithcode.com/paper/a-deep-learning-based-system-for-pharmaconer |
| Repo | |
| Framework | |
Term Based Semantic Clusters for Very Short Text Classification
| Title | Term Based Semantic Clusters for Very Short Text Classification |
| Authors | Jasper Paalman, Shantanu Mullick, Kalliopi Zervanou, Yingqian Zhang |
| Abstract | Very short texts, such as tweets and invoices, present challenges in classification. Although term occurrences are strong indicators of content, in very short texts, the sparsity of these texts makes it difficult to capture important semantic relationships. A solution calls for a method that not only considers term occurrence, but also handles sparseness well. In this work, we introduce such an approach, the Term Based Semantic Clusters (TBSeC) that employs terms to create distinctive semantic concept clusters. These clusters are ranked using a semantic similarity function which in turn defines a semantic feature space that can be used for text classification. Our method is evaluated in an invoice classification task. Compared to well-known content representation methods the proposed method performs competitively. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Text Classification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1102/ |
| https://www.aclweb.org/anthology/R19-1102 | |
| PWC | https://paperswithcode.com/paper/term-based-semantic-clusters-for-very-short |
| Repo | |
| Framework | |
A Robust Self-Learning Framework for Cross-Lingual Text Classification
| Title | A Robust Self-Learning Framework for Cross-Lingual Text Classification |
| Authors | Xin Dong, Gerard de Melo |
| Abstract | Based on massive amounts of data, recent pretrained contextual representation models have made significant strides in advancing a number of different English NLP tasks. However, for other languages, relevant training data may be lacking, while state-of-the-art deep learning methods are known to be data-hungry. In this paper, we present an elegantly simple robust self-learning framework to include unlabeled non-English samples in the fine-tuning process of pretrained multilingual representation models. We leverage a multilingual model{'}s own predictions on unlabeled non-English data in order to obtain additional information that can be used during further fine-tuning. Compared with original multilingual models and other cross-lingual classification models, we observe significant gains in effectiveness on document and sentiment classification for a range of diverse languages. |
| Tasks | Sentiment Analysis, Text Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1658/ |
| https://www.aclweb.org/anthology/D19-1658 | |
| PWC | https://paperswithcode.com/paper/a-robust-self-learning-framework-for-cross |
| Repo | |
| Framework | |
Similar Minds Post Alike: Assessment of Suicide Risk Using a Hybrid Model
| Title | Similar Minds Post Alike: Assessment of Suicide Risk Using a Hybrid Model |
| Authors | Lushi Chen, Abeer Aldayel, Nikolay Bogoychev, Tao Gong |
| Abstract | This paper describes our system submission for the CLPsych 2019 shared task B on suicide risk assessment. We approached the problem with three separate models: a behaviour model; a language model and a hybrid model. For the behavioral model approach, we model each user{'}s behaviour and thoughts with four groups of features: posting behaviour, sentiment, motivation, and content of the user{'}s posting. We use these features as an input in a support vector machine (SVM). For the language model approach, we trained a language model for each risk level using all the posts from the users as the training corpora. Then, we computed the perplexity of each user{'}s posts to determine how likely his/her posts were to belong to each risk level. Finally, we built a hybrid model that combines both the language model and the behavioral model, which demonstrates the best performance in detecting the suicide risk level. |
| Tasks | Language Modelling |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-3018/ |
| https://www.aclweb.org/anthology/W19-3018 | |
| PWC | https://paperswithcode.com/paper/similar-minds-post-alike-assessment-of |
| Repo | |
| Framework | |
Controlling Japanese Honorifics in English-to-Japanese Neural Machine Translation
| Title | Controlling Japanese Honorifics in English-to-Japanese Neural Machine Translation |
| Authors | Weston Feely, Eva Hasler, Adri{`a} de Gispert |
| Abstract | In the Japanese language different levels of honorific speech are used to convey respect, deference, humility, formality and social distance. In this paper, we present a method for controlling the level of formality of Japanese output in English-to-Japanese neural machine translation (NMT). By using heuristics to identify honorific verb forms, we classify Japanese sentences as being one of three levels of informal, polite, or formal speech in parallel text. The English source side is marked with a feature that identifies the level of honorific speech present in the Japanese target side. We use this parallel text to train an English-Japanese NMT model capable of producing Japanese translations in different honorific speech styles for the same English input sentence. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5203/ |
| https://www.aclweb.org/anthology/D19-5203 | |
| PWC | https://paperswithcode.com/paper/controlling-japanese-honorifics-in-english-to |
| Repo | |
| Framework | |
Surface Reconstruction From Normals: A Robust DGP-Based Discontinuity Preservation Approach
| Title | Surface Reconstruction From Normals: A Robust DGP-Based Discontinuity Preservation Approach |
| Authors | Wuyuan Xie, Miaohui Wang, Mingqiang Wei, Jianmin Jiang, Jing Qin |
| Abstract | In 3D surface reconstruction from normals, discontinuity preservation is an important but challenging task. However, existing studies fail to address the discontinuous normal maps by enforcing the surface integrability in the continuous domain. This paper introduces a robust approach to preserve the surface discontinuity in the discrete geometry way. Firstly, we design two representative normal incompatibility features and propose an efficient discontinuity detection scheme to determine the splitting pattern for a discrete mesh. Secondly, we model the discontinuity preservation problem as a light-weight energy optimization framework by jointly considering the discontinuity detection and the overall reconstruction error. Lastly, we further shrink the feasible solution space to reduce the complexity based on the prior knowledge. Experiments show that the proposed method achieves the best performance on an extensive 3D dataset compared with the state-of-the-arts in terms of mean angular error and computational complexity. |
| Tasks | |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Xie_Surface_Reconstruction_From_Normals_A_Robust_DGP-Based_Discontinuity_Preservation_Approach_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Xie_Surface_Reconstruction_From_Normals_A_Robust_DGP-Based_Discontinuity_Preservation_Approach_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/surface-reconstruction-from-normals-a-robust |
| Repo | |
| Framework | |
A New Perspective on Pool-Based Active Classification and False-Discovery Control
| Title | A New Perspective on Pool-Based Active Classification and False-Discovery Control |
| Authors | Lalit Jain, Kevin G. Jamieson |
| Abstract | In many scientific settings there is a need for adaptive experimental design to guide the process of identifying regions of the search space that contain as many true positives as possible subject to a low rate of false discoveries (i.e. false alarms). Such regions of the search space could differ drastically from a predicted set that minimizes 0/1 error and accurate identification could require very different sampling strategies. Like active learning for binary classification, this experimental design cannot be optimally chosen a priori, but rather the data must be taken sequentially and adaptively in a closed loop. However, unlike classification with 0/1 error, collecting data adaptively to find a set with high true positive rate and low false discovery rate (FDR) is not as well understood. In this paper, we provide the first provably sample efficient adaptive algorithm for this problem. Along the way, we highlight connections between classification, combinatorial bandits, and FDR control making contributions to each. |
| Tasks | Active Learning |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9549-a-new-perspective-on-pool-based-active-classification-and-false-discovery-control |
| http://papers.nips.cc/paper/9549-a-new-perspective-on-pool-based-active-classification-and-false-discovery-control.pdf | |
| PWC | https://paperswithcode.com/paper/a-new-perspective-on-pool-based-active |
| Repo | |
| Framework | |
Johns Hopkins University Submission for WMT News Translation Task
| Title | Johns Hopkins University Submission for WMT News Translation Task |
| Authors | Kelly Marchisio, Yash Kumar Lal, Philipp Koehn |
| Abstract | We describe the work of Johns Hopkins University for the shared task of news translation organized by the Fourth Conference on Machine Translation (2019). We submitted systems for both directions of the English-German language pair. The systems combine multiple techniques {–} sampling, filtering, iterative backtranslation, and continued training {–} previously used to improve performance of neural machine translation models. At submission time, we achieve a BLEU score of 38.1 for De-En and 42.5 for En-De translation directions on newstest2019. Post-submission, the score is 38.4 for De-En and 42.8 for En-De. Various experiments conducted in the process are also described. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5329/ |
| https://www.aclweb.org/anthology/W19-5329 | |
| PWC | https://paperswithcode.com/paper/johns-hopkins-university-submission-for-wmt |
| Repo | |
| Framework | |
Normalization of Kazakh Texts
| Title | Normalization of Kazakh Texts |
| Authors | Assina Abdussaitova, Alina Amangeldiyeva |
| Abstract | Kazakh language, like other agglutinative languages, has specific difficulties on both recognition of wrong words and generation the corrections for misspelt words. The main goal of this work is to develop a better algorithm for the normalization of Kazakh texts based on traditional and Machine Learning methods, as well as the new approach which is also considered in this paper. The procedure of election among methods of normalization has been conducted in a manner of comparative analysis. The results of the comparative analysis turned up successful and are shown in details. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-2001/ |
| https://www.aclweb.org/anthology/R19-2001 | |
| PWC | https://paperswithcode.com/paper/normalization-of-kazakh-texts |
| Repo | |
| Framework | |
PROMT Systems for WMT 2019 Shared Translation Task
| Title | PROMT Systems for WMT 2019 Shared Translation Task |
| Authors | Alex Molchanov, er |
| Abstract | This paper describes the PROMT submissions for the WMT 2019 Shared News Translation Task. This year we participated in two language pairs and in three directions: English-Russian, English-German and German-English. All our submissions are Marian-based neural systems. We use significantly more data compared to the last year. We also present our improved data filtering pipeline. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5331/ |
| https://www.aclweb.org/anthology/W19-5331 | |
| PWC | https://paperswithcode.com/paper/promt-systems-for-wmt-2019-shared-translation |
| Repo | |
| Framework | |
JU-Saarland Submission to the WMT2019 English–Gujarati Translation Shared Task
| Title | JU-Saarland Submission to the WMT2019 English–Gujarati Translation Shared Task |
| Authors | Riktim Mondal, Shankha Raj Nayek, Aditya Chowdhury, Santanu Pal, Sudip Kumar Naskar, Josef van Genabith |
| Abstract | In this paper we describe our joint submission (JU-Saarland) from Jadavpur University and Saarland University in the WMT 2019 news translation shared task for English{–}Gujarati language pair within the translation task sub-track. Our baseline and primary submissions are built using Recurrent neural network (RNN) based neural machine translation (NMT) system which follows attention mechanism. Given the fact that the two languages belong to different language families and there is not enough parallel data for this language pair, building a high quality NMT system for this language pair is a difficult task. We produced synthetic data through back-translation from available monolingual data. We report the translation quality of our English{–}Gujarati and Gujarati{–}English NMT systems trained at word, byte-pair and character encoding levels where RNN at word level is considered as the baseline and used for comparison purpose. Our English{–}Gujarati system ranked in the second position in the shared task. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5332/ |
| https://www.aclweb.org/anthology/W19-5332 | |
| PWC | https://paperswithcode.com/paper/ju-saarland-submission-to-the-wmt2019-english |
| Repo | |
| Framework | |
Neural Relation Extraction for Knowledge Base Enrichment
| Title | Neural Relation Extraction for Knowledge Base Enrichment |
| Authors | Bayu Distiawan Trisedya, Gerhard Weikum, Jianzhong Qi, Rui Zhang |
| Abstract | We study relation extraction for knowledge base (KB) enrichment. Specifically, we aim to extract entities and their relationships from sentences in the form of triples and map the elements of the extracted triples to an existing KB in an end-to-end manner. Previous studies focus on the extraction itself and rely on Named Entity Disambiguation (NED) to map triples into the KB space. This way, NED errors may cause extraction errors that affect the overall precision and recall.To address this problem, we propose an end-to-end relation extraction model for KB enrichment based on a neural encoder-decoder model. We collect high-quality training data by distant supervision with co-reference resolution and paraphrase detection. We propose an n-gram based attention model that captures multi-word entity names in a sentence. Our model employs jointly learned word and entity embeddings to support named entity disambiguation. Finally, our model uses a modified beam search and a triple classifier to help generate high-quality triples. Our model outperforms state-of-the-art baselines by 15.51{%} and 8.38{%} in terms of F1 score on two real-world datasets. |
| Tasks | Entity Disambiguation, Entity Embeddings, Relation Extraction |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1023/ |
| https://www.aclweb.org/anthology/P19-1023 | |
| PWC | https://paperswithcode.com/paper/neural-relation-extraction-for-knowledge-base |
| Repo | |
| Framework | |
Language Modeling with Graph Temporal Convolutional Networks
| Title | Language Modeling with Graph Temporal Convolutional Networks |
| Authors | Hongyin Luo, Yichen Li, Jie Fu, James Glass |
| Abstract | Recently, there have been some attempts to use non-recurrent neural models for language modeling. However, a noticeable performance gap still remains. We propose a non-recurrent neural language model, dubbed graph temporal convolutional network (GTCN), that relies on graph neural network blocks and convolution operations. While the standard recurrent neural network language models encode sentences sequentially without modeling higher-level structural information, our model regards sentences as graphs and processes input words within a message propagation framework, aiming to learn better syntactic information by inferring skip-word connections. Specifically, the graph network blocks operate in parallel and learn the underlying graph structures in sentences without any additional annotation pertaining to structure knowledge. Experiments demonstrate that the model without recurrence can achieve comparable perplexity results in language modeling tasks and successfully learn syntactic information. |
| Tasks | Language Modelling |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJlYzhR9tm |
| https://openreview.net/pdf?id=HJlYzhR9tm | |
| PWC | https://paperswithcode.com/paper/language-modeling-with-graph-temporal |
| Repo | |
| Framework | |
BOUN-ISIK Participation: An Unsupervised Approach for the Named Entity Normalization and Relation Extraction of Bacteria Biotopes
| Title | BOUN-ISIK Participation: An Unsupervised Approach for the Named Entity Normalization and Relation Extraction of Bacteria Biotopes |
| Authors | {.I}lknur Karadeniz, {"O}mer Faruk Tuna, Arzucan {"O}zg{"u}r |
| Abstract | This paper presents our participation to the Bacteria Biotope Task of the BioNLP Shared Task 2019. Our participation includes two systems for the two subtasks of the Bacteria Biotope Task: the normalization of entities (BB-norm) and the identification of the relations between the entities given a biomedical text (BB-rel). For the normalization of entities, we utilized word embeddings and syntactic re-ranking. For the relation extraction task, pre-defined rules are used. Although both approaches are unsupervised, in the sense that they do not need any labeled data, they achieved promising results. Especially, for the BB-norm task, the results have shown that the proposed method performs as good as deep learning based methods, which require labeled data. |
| Tasks | Relation Extraction, Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5722/ |
| https://www.aclweb.org/anthology/D19-5722 | |
| PWC | https://paperswithcode.com/paper/boun-isik-participation-an-unsupervised |
| Repo | |
| Framework | |
Toward a deep dialectological representation of Indo-Aryan
| Title | Toward a deep dialectological representation of Indo-Aryan |
| Authors | Chundra Cathcart |
| Abstract | This paper presents a new approach to disentangling inter-dialectal and intra-dialectal relationships within one such group, the Indo-Aryan subgroup of Indo-European. We draw upon admixture models and deep generative models to tease apart historic language contact and language-specific behavior in the overall patterns of sound change displayed by Indo-Aryan languages. We show that a {}deep{''} model of Indo-Aryan dialectology sheds some light on questions regarding inter-relationships among the Indo-Aryan languages, and performs better than a {}shallow{''} model in terms of certain qualities of the posterior distribution (e.g., entropy of posterior distributions), and outline future pathways for model development. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1411/ |
| https://www.aclweb.org/anthology/W19-1411 | |
| PWC | https://paperswithcode.com/paper/toward-a-deep-dialectological-representation |
| Repo | |
| Framework | |
