Paper Group NANR 129
Idiap NMT System for WAT 2019 Multimodal Translation Task. Similarity Based Auxiliary Classifier for Named Entity Recognition. NLP Automation to Read Radiological Reports to Detect the Stage of Cancer Among Lung Cancer Patients. TDDiscourse: A Dataset for Discourse-Level Temporal Ordering of Events. Sentence-Level Propaganda Detection in News Artic …
Idiap NMT System for WAT 2019 Multimodal Translation Task
| Title | Idiap NMT System for WAT 2019 Multimodal Translation Task |
| Authors | Shantipriya Parida, Ond{\v{r}}ej Bojar, Petr Motlicek |
| Abstract | This paper describes the Idiap submission to WAT 2019 for the English-Hindi Multi-Modal Translation Task. We have used the state-of-the-art Transformer model and utilized the IITB English-Hindi parallel corpus as an additional data source. Among the different tracks of the multi-modal task, we have participated in the {}Text-Only{''} track for the evaluation and challenge test sets. Our submission tops in its track among the competitors in terms of both automatic and manual evaluation. Based on automatic scores, our text-only submission also outperforms systems that consider visual information in the {}multi-modal translation{''} task. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5223/ |
| https://www.aclweb.org/anthology/D19-5223 | |
| PWC | https://paperswithcode.com/paper/idiap-nmt-system-for-wat-2019-multimodal |
| Repo | |
| Framework | |
Similarity Based Auxiliary Classifier for Named Entity Recognition
| Title | Similarity Based Auxiliary Classifier for Named Entity Recognition |
| Authors | Shiyuan Xiao, Yuanxin Ouyang, Wenge Rong, Jianxin Yang, Zhang Xiong |
| Abstract | The segmentation problem is one of the fundamental challenges associated with name entity recognition (NER) tasks that aim to reduce the boundary error when detecting a sequence of entity words. A considerable number of advanced approaches have been proposed and most of them exhibit performance deterioration when entities become longer. Inspired by previous work in which a multi-task strategy is used to solve segmentation problems, we design a similarity based auxiliary classifier (SAC), which can distinguish entity words from non-entity words. Unlike conventional classifiers, SAC uses vectors to indicate tags. Therefore, SAC can calculate the similarities between words and tags, and then compute a weighted sum of the tag vectors, which can be considered a useful feature for NER tasks. Empirical results are used to verify the rationality of the SAC structure and demonstrate the SAC model{'}s potential in performance improvement against our baseline approaches. |
| Tasks | Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1105/ |
| https://www.aclweb.org/anthology/D19-1105 | |
| PWC | https://paperswithcode.com/paper/similarity-based-auxiliary-classifier-for |
| Repo | |
| Framework | |
NLP Automation to Read Radiological Reports to Detect the Stage of Cancer Among Lung Cancer Patients
| Title | NLP Automation to Read Radiological Reports to Detect the Stage of Cancer Among Lung Cancer Patients |
| Authors | Khushbu Gupta, Ratchainant Thammasudjarit, Ammarin Thakkinstian |
| Abstract | A common challenge in the healthcare industry today is physicians have access to massive amounts of healthcare data but have little time and no appropriate tools. For instance, the risk prediction model generated by logistic regression could predict the probability of diseases occurrence and thus prioritizing patients{'} waiting list for further investigations. However, many medical reports available in current clinical practice system are not yet ready for analysis using either statistics or machine learning as they are in unstructured text format. The complexity of medical information makes the annotation or validation of data very challenging and thus acts as a bottleneck to apply machine learning techniques in medical data. This study is therefore conducted to create such annotations automatically where the computer can read radiological reports for oncologists and mark the staging of lung cancer. This staging information is obtained using the rule-based method implemented using the standards of Tumor Node Metastasis (TNM) staging along with deep learning technology called Long Short Term Memory (LSTM) to extract clinical information from the Computed Tomography (CT) text report. The empirical experiment shows promising results being the accuracy of up to 85{%}. |
| Tasks | Computed Tomography (CT) |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/papers/W/W19/W19-3643/ |
| https://www.aclweb.org/anthology/W19-3643 | |
| PWC | https://paperswithcode.com/paper/nlp-automation-to-read-radiological-reports |
| Repo | |
| Framework | |
TDDiscourse: A Dataset for Discourse-Level Temporal Ordering of Events
| Title | TDDiscourse: A Dataset for Discourse-Level Temporal Ordering of Events |
| Authors | Aakanksha Naik, Luke Breitfeller, Carolyn Rose |
| Abstract | Prior work on temporal relation classification has focused extensively on event pairs in the same or adjacent sentences (local), paying scant attention to discourse-level (global) pairs. This restricts the ability of systems to learn temporal links between global pairs, since reliance on local syntactic features suffices to achieve reasonable performance on existing datasets. However, systems should be capable of incorporating cues from document-level structure to assign temporal relations. In this work, we take a first step towards discourse-level temporal ordering by creating TDDiscourse, the first dataset focusing specifically on temporal links between event pairs which are more than one sentence apart. We create TDDiscourse by augmenting TimeBank-Dense, a corpus of English news articles, manually annotating global pairs that cannot be inferred automatically from existing annotations. Our annotations double the number of temporal links in TimeBank-Dense, while possessing several desirable properties such as focusing on long-distance pairs and not being automatically inferable. We adapt and benchmark the performance of three state-of-the-art models on TDDiscourse and observe that existing systems indeed find discourse-level temporal ordering harder. |
| Tasks | Relation Classification |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5929/ |
| https://www.aclweb.org/anthology/W19-5929 | |
| PWC | https://paperswithcode.com/paper/tddiscourse-a-dataset-for-discourse-level |
| Repo | |
| Framework | |
Sentence-Level Propaganda Detection in News Articles with Transfer Learning and BERT-BiLSTM-Capsule Model
| Title | Sentence-Level Propaganda Detection in News Articles with Transfer Learning and BERT-BiLSTM-Capsule Model |
| Authors | George-Alex Vlad, ru, Mircea-Adrian Tanase, Cristian Onose, Dumitru-Clementin Cercel |
| Abstract | In recent years, the need for communication increased in online social media. Propaganda is a mechanism which was used throughout history to influence public opinion and it is gaining a new dimension with the rising interest of online social media. This paper presents our submission to NLP4IF-2019 Shared Task SLC: Sentence-level Propaganda Detection in news articles. The challenge of this task is to build a robust binary classifier able to provide corresponding propaganda labels, propaganda or non-propaganda. Our model relies on a unified neural network, which consists of several deep leaning modules, namely BERT, BiLSTM and Capsule, to solve the sentencelevel propaganda classification problem. In addition, we take a pre-training approach on a somewhat similar task (i.e., emotion classification) improving results against the cold-start model. Among the 26 participant teams in the NLP4IF-2019 Task SLC, our solution ranked 12th with an F1-score 0.5868 on the official test data. Our proposed solution indicates promising results since our system significantly exceeds the baseline approach of the organizers by 0.1521 and is slightly lower than the winning system by 0.0454. |
| Tasks | Emotion Classification, Transfer Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5022/ |
| https://www.aclweb.org/anthology/D19-5022 | |
| PWC | https://paperswithcode.com/paper/sentence-level-propaganda-detection-in-news |
| Repo | |
| Framework | |
Sentiment Aware Neural Machine Translation
| Title | Sentiment Aware Neural Machine Translation |
| Authors | Chenglei Si, Kui Wu, Ai Ti Aw, Min-Yen Kan |
| Abstract | Sentiment ambiguous lexicons refer to words where their polarity depends strongly on con- text. As such, when the context is absent, their translations or their embedded sentence ends up (incorrectly) being dependent on the training data. While neural machine translation (NMT) has achieved great progress in recent years, most systems aim to produce one single correct translation for a given source sentence. We investigate the translation variation in two sentiment scenarios. We perform experiments to study the preservation of sentiment during translation with three different methods that we propose. We conducted tests with both sentiment and non-sentiment bearing contexts to examine the effectiveness of our methods. We show that NMT can generate both positive- and negative-valent translations of a source sentence, based on a given input sentiment label. Empirical evaluations show that our valence-sensitive embedding (VSE) method significantly outperforms a sequence-to-sequence (seq2seq) baseline, both in terms of BLEU score and ambiguous word translation accuracy in test, given non-sentiment bearing contexts. |
| Tasks | Machine Translation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5227/ |
| https://www.aclweb.org/anthology/D19-5227 | |
| PWC | https://paperswithcode.com/paper/sentiment-aware-neural-machine-translation |
| Repo | |
| Framework | |
Comparative Analysis of Errors in MT Output and Computer-assisted Translation: Effect of the Human Factor
| Title | Comparative Analysis of Errors in MT Output and Computer-assisted Translation: Effect of the Human Factor |
| Authors | Irina Ovchinnikova, Daria Morozova |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-6713/ |
| https://www.aclweb.org/anthology/W19-6713 | |
| PWC | https://paperswithcode.com/paper/comparative-analysis-of-errors-in-mt-output |
| Repo | |
| Framework | |
Deep neural model with enhanced embeddings for pharmaceutical and chemical entities recognition in Spanish clinical text
| Title | Deep neural model with enhanced embeddings for pharmaceutical and chemical entities recognition in Spanish clinical text |
| Authors | Renzo Rivera, Paloma Mart{'\i}nez |
| Abstract | In this work, we introduce a Deep Learning architecture for pharmaceutical and chemical Named Entity Recognition in Spanish clinical cases texts. We propose a hybrid model approach based on two Bidirectional Long Short-Term Memory (Bi-LSTM) network and Conditional Random Field (CRF) network using character, word, concept and sense embeddings to deal with the extraction of semantic, syntactic and morphological features. The approach was evaluated on the PharmaCoNER Corpus obtaining an F-measure of 85.24{%} for subtask 1 and 49.36{%} for subtask2. These results prove that deep learning methods with specific domain embedding representations can outperform the state-of-the-art approaches. |
| Tasks | Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5707/ |
| https://www.aclweb.org/anthology/D19-5707 | |
| PWC | https://paperswithcode.com/paper/deep-neural-model-with-enhanced-embeddings |
| Repo | |
| Framework | |
A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models
| Title | A Neural Pipeline Approach for the PharmaCoNER Shared Task using Contextual Exhaustive Models |
| Authors | Mohammad Golam Sohrab, Minh Thang Pham, Makoto Miwa, Hiroya Takamura |
| Abstract | We present a neural pipeline approach that performs named entity recognition (NER) and concept indexing (CI), which links them to concept unique identifiers (CUIs) in a knowledge base, for the PharmaCoNER shared task on pharmaceutical drugs and chemical entities. We proposed a neural NER model that captures the surrounding semantic information of a given sequence by capturing the forward- and backward-context of bidirectional LSTM (Bi-LSTM) output of a target span using contextual span representation-based exhaustive approach. The NER model enumerates all possible spans as potential entity mentions and classify them into entity types or no entity with deep neural networks. For representing span, we compare several different neural network architectures and their ensembling for the NER model. We then perform dictionary matching for CI and, if there is no matching, we further compute similarity scores between a mention and CUIs using entity embeddings to assign the CUI with the highest score to the mention. We evaluate our approach on the two sub-tasks in the shared task. Among the five submitted runs, the best run for each sub-task achieved the F-score of 86.76{%} on Sub-task 1 (NER) and the F-score of 79.97{%} (strict) on Sub-task 2 (CI). |
| Tasks | Entity Embeddings, Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5708/ |
| https://www.aclweb.org/anthology/D19-5708 | |
| PWC | https://paperswithcode.com/paper/a-neural-pipeline-approach-for-the |
| Repo | |
| Framework | |
Context-Aware Feature and Label Fusion for Facial Action Unit Intensity Estimation With Partially Labeled Data
| Title | Context-Aware Feature and Label Fusion for Facial Action Unit Intensity Estimation With Partially Labeled Data |
| Authors | Yong Zhang, Haiyong Jiang, Baoyuan Wu, Yanbo Fan, Qiang Ji |
| Abstract | Facial action unit (AU) intensity estimation is a fundamental task for facial behaviour analysis. Most previous methods use a whole face image as input for intensity prediction. Considering that AUs are defined according to their corresponding local appearance, a few patch-based methods utilize image features of local patches. However, fusion of local features is always performed via straightforward feature concatenation or summation. Besides, these methods require fully annotated databases for model learning, which is expensive to acquire. In this paper, we propose a novel weakly supervised patch-based deep model on basis of two types of attention mechanisms for joint intensity estimation of multiple AUs. The model consists of a feature fusion module and a label fusion module. And we augment attention mechanisms of these two modules with a learnable task-related context, as one patch may play different roles in analyzing different AUs and each AU has its own temporal evolution rule. The context-aware feature fusion module is used to capture spatial relationships among local patches while the context-aware label fusion module is used to capture the temporal dynamics of AUs. The latter enables the model to be trained on a partially annotated database. Experimental evaluations on two benchmark expression databases demonstrate the superior performance of the proposed method. |
| Tasks | |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Zhang_Context-Aware_Feature_and_Label_Fusion_for_Facial_Action_Unit_Intensity_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Zhang_Context-Aware_Feature_and_Label_Fusion_for_Facial_Action_Unit_Intensity_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/context-aware-feature-and-label-fusion-for |
| Repo | |
| Framework | |
Transfer Learning in Biomedical Named Entity Recognition: An Evaluation of BERT in the PharmaCoNER task
| Title | Transfer Learning in Biomedical Named Entity Recognition: An Evaluation of BERT in the PharmaCoNER task |
| Authors | Cong Sun, Zhihao Yang |
| Abstract | To date, a large amount of biomedical content has been published in non-English texts, especially for clinical documents. Therefore, it is of considerable significance to conduct Natural Language Processing (NLP) research in non-English literature. PharmaCoNER is the first Named Entity Recognition (NER) task to recognize chemical and protein entities from Spanish biomedical texts. Since there have been abundant resources in the NLP field, how to exploit these existing resources to a new task to obtain competitive performance is a meaningful study. Inspired by the success of transfer learning with language models, we introduce the BERT benchmark to facilitate the research of PharmaCoNER task. In this paper, we evaluate two baselines based on Multilingual BERT and BioBERT on the PharmaCoNER corpus. Experimental results show that transferring the knowledge learned from source large-scale datasets to the target domain offers an effective solution for the PharmaCoNER task. |
| Tasks | Named Entity Recognition, Transfer Learning |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5715/ |
| https://www.aclweb.org/anthology/D19-5715 | |
| PWC | https://paperswithcode.com/paper/transfer-learning-in-biomedical-named-entity |
| Repo | |
| Framework | |
Easy First Relation Extraction with Information Redundancy
| Title | Easy First Relation Extraction with Information Redundancy |
| Authors | Shuai Ma, Gang Wang, Yansong Feng, Jinpeng Huai |
| Abstract | Many existing relation extraction (RE) models make decisions globally using integer linear programming (ILP). However, it is nontrivial to make use of integer linear programming as a blackbox solver for RE. Its cost of time and memory may become unacceptable with the increase of data scale, and redundant information needs to be encoded cautiously for ILP. In this paper, we propose an easy first approach for relation extraction with information redundancies, embedded in the results produced by local sentence level extractors, during which conflict decisions are resolved with domain and uniqueness constraints. Information redundancies are leveraged to support both easy first collective inference for easy decisions in the first stage and ILP for hard decisions in a subsequent stage. Experimental study shows that our approach improves the efficiency and accuracy of RE, and outperforms both ILP and neural network-based methods. |
| Tasks | Relation Extraction |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1398/ |
| https://www.aclweb.org/anthology/D19-1398 | |
| PWC | https://paperswithcode.com/paper/easy-first-relation-extraction-with |
| Repo | |
| Framework | |
Learning Word Embeddings without Context Vectors
| Title | Learning Word Embeddings without Context Vectors |
| Authors | Alexey Zobnin, Evgenia Elistratova |
| Abstract | Most word embedding algorithms such as word2vec or fastText construct two sort of vectors: for words and for contexts. Naive use of vectors of only one sort leads to poor results. We suggest using indefinite inner product in skip-gram negative sampling algorithm. This allows us to use only one sort of vectors without loss of quality. Our {``}context-free{''} cf algorithm performs on par with SGNS on word similarity datasets | |
| Tasks | Learning Word Embeddings, Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4329/ |
| https://www.aclweb.org/anthology/W19-4329 | |
| PWC | https://paperswithcode.com/paper/learning-word-embeddings-without-context |
| Repo | |
| Framework | |
ParaDis and D'emonette: From Theory to Resources for Derivational Paradigms
| Title | ParaDis and D'emonette: From Theory to Resources for Derivational Paradigms |
| Authors | Fiammetta Namer, Nabil Hathout |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8502/ |
| https://www.aclweb.org/anthology/W19-8502 | |
| PWC | https://paperswithcode.com/paper/paradis-and-demonette-from-theory-to |
| Repo | |
| Framework | |
Personality Traits Recognition in Literary Texts
| Title | Personality Traits Recognition in Literary Texts |
| Authors | Daniele Pizzolli, Carlo Strapparava |
| Abstract | Interesting stories often are built around interesting characters. Finding and detailing what makes an interesting character is a real challenge, but certainly a significant cue is the character personality traits. Our exploratory work tests the adaptability of the current personality traits theories to literal characters, focusing on the analysis of utterances in theatre scripts. And, at the opposite, we try to find significant traits for interesting characters. The preliminary results demonstrate that our approach is reasonable. Using machine learning for gaining insight into the personality traits of fictional characters can make sense. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3411/ |
| https://www.aclweb.org/anthology/W19-3411 | |
| PWC | https://paperswithcode.com/paper/personality-traits-recognition-in-literary |
| Repo | |
| Framework | |
