Paper Group NANR 256
A Pointer Network Architecture for Context-Dependent Semantic Parsing. Investigating Multilingual Abusive Language Detection: A Cautionary Tale. Neural Network to Identify Personal Health Experience Mention in Tweets Using BioBERT Embeddings. UHH-LT at SemEval-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detecti …
A Pointer Network Architecture for Context-Dependent Semantic Parsing
| Title | A Pointer Network Architecture for Context-Dependent Semantic Parsing |
| Authors | Xuanli He, Quan Tran, Gholamreza Haffari |
| Abstract | |
| Tasks | Semantic Parsing |
| Published | 2019-04-01 |
| URL | https://www.aclweb.org/anthology/U19-1013/ |
| https://www.aclweb.org/anthology/U19-1013 | |
| PWC | https://paperswithcode.com/paper/a-pointer-network-architecture-for-context |
| Repo | |
| Framework | |
Investigating Multilingual Abusive Language Detection: A Cautionary Tale
| Title | Investigating Multilingual Abusive Language Detection: A Cautionary Tale |
| Authors | Kenneth Steimel, Daniel Dakota, Yue Chen, S K{"u}bler, ra |
| Abstract | Abusive language detection has received much attention in the last years, and recent approaches perform the task in a number of different languages. We investigate which factors have an effect on multilingual settings, focusing on the compatibility of data and annotations. In the current paper, we focus on English and German. Our findings show large differences in performance between the two languages. We find that the best performance is achieved by different classification algorithms. Sampling to address class imbalance issues is detrimental for German and beneficial for English. The only similarity that we find is that neither data set shows clear topics when we compare the results of topic modeling to the gold standard. Based on our findings, we can conclude that a multilingual optimization of classifiers is not possible even in settings where comparable data sets are used. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1132/ |
| https://www.aclweb.org/anthology/R19-1132 | |
| PWC | https://paperswithcode.com/paper/investigating-multilingual-abusive-language |
| Repo | |
| Framework | |
Neural Network to Identify Personal Health Experience Mention in Tweets Using BioBERT Embeddings
| Title | Neural Network to Identify Personal Health Experience Mention in Tweets Using BioBERT Embeddings |
| Authors | Shubham Gondane |
| Abstract | This paper describes the system developed by team ASU-NLP for the Social Media Mining for Health Applications(SMM4H) shared task 4. We extract feature embeddings from the BioBERT (Lee et al., 2019) model which has been fine-tuned on the training dataset and use that as inputs to a dense fully connected neural network. We achieve above average scores among the participant systems with the overall F1-score, accuracy, precision, recall as 0.8036, 0.8456, 0.9783, 0.6818 respectively. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3218/ |
| https://www.aclweb.org/anthology/W19-3218 | |
| PWC | https://paperswithcode.com/paper/neural-network-to-identify-personal-health |
| Repo | |
| Framework | |
UHH-LT at SemEval-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detection
| Title | UHH-LT at SemEval-2019 Task 6: Supervised vs. Unsupervised Transfer Learning for Offensive Language Detection |
| Authors | Gregor Wiedemann, Eugen Ruppert, Chris Biemann |
| Abstract | We present a neural network based approach of transfer learning for offensive language detection. For our system, we compare two types of knowledge transfer: supervised and unsupervised pre-training. Supervised pre-training of our bidirectional GRU-3-CNN architecture is performed as multi-task learning of parallel training of five different tasks. The selected tasks are supervised classification problems from public NLP resources with some overlap to offensive language such as sentiment detection, emoji classification, and aggressive language classification. Unsupervised transfer learning is performed with a thematic clustering of 40M unlabeled tweets via LDA. Based on this dataset, pre-training is performed by predicting the main topic of a tweet. Results indicate that unsupervised transfer from large datasets performs slightly better than supervised training on small {`}near target category{'} datasets. In the SemEval Task, our system ranks 14 out of 103 participants. | |
| Tasks | Multi-Task Learning, Transfer Learning |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2137/ |
| https://www.aclweb.org/anthology/S19-2137 | |
| PWC | https://paperswithcode.com/paper/uhh-lt-at-semeval-2019-task-6-supervised-vs |
| Repo | |
| Framework | |
Using NLG for speech synthesis of mathematical sentences
| Title | Using NLG for speech synthesis of mathematical sentences |
| Authors | Aless Mazzei, ro, Michele Monticone, Cristian Bernareggi |
| Abstract | People with sight impairments can access to a mathematical expression by using its LaTeX source. However, this mechanisms have several drawbacks: (1) it assumes the knowledge of the LaTeX, (2) it is slow, since LaTeX is verbose and (3) it is error-prone since LATEX is a typographical language. In this paper we study the design of a natural language generation system for producing a mathematical sentence, i.e. a natural language sentence expressing the semantics of a mathematical expression. Moreover, we describe the main results of a first human based evaluation experiment of the system for Italian language. |
| Tasks | Speech Synthesis, Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8658/ |
| https://www.aclweb.org/anthology/W19-8658 | |
| PWC | https://paperswithcode.com/paper/using-nlg-for-speech-synthesis-of |
| Repo | |
| Framework | |
SC-LSTM: Learning Task-Specific Representations in Multi-Task Learning for Sequence Labeling
| Title | SC-LSTM: Learning Task-Specific Representations in Multi-Task Learning for Sequence Labeling |
| Authors | Peng Lu, Ting Bai, Philippe Langlais |
| Abstract | Multi-task learning (MTL) has been studied recently for sequence labeling. Typically, auxiliary tasks are selected specifically in order to improve the performance of a target task. Jointly learning multiple tasks in a way that benefit all of them simultaneously can increase the utility of MTL. In order to do so, we propose a new LSTM cell which contains both shared parameters that can learn from all tasks, and task-specific parameters that can learn task-specific information. We name it a Shared-Cell Long-Short Term Memory SC-LSTM. Experimental results on three sequence labeling benchmarks (named-entity recognition, text chunking, and part-of-speech tagging) demonstrate the effectiveness of our SC-LSTM cell. |
| Tasks | Chunking, Multi-Task Learning, Named Entity Recognition, Part-Of-Speech Tagging |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1249/ |
| https://www.aclweb.org/anthology/N19-1249 | |
| PWC | https://paperswithcode.com/paper/sc-lstm-learning-task-specific |
| Repo | |
| Framework | |
PharmaCoNER: Pharmacological Substances, Compounds and proteins Named Entity Recognition track
| Title | PharmaCoNER: Pharmacological Substances, Compounds and proteins Named Entity Recognition track |
| Authors | Aitor Gonzalez-Agirre, Montserrat Marimon, Ander Intxaurrondo, Obdulia Rabal, Marta Villegas, Martin Krallinger |
| Abstract | One of the biomedical entity types of relevance for medicine or biosciences are chemical compounds and drugs. The correct detection these entities is critical for other text mining applications building on them, such as adverse drug-reaction detection, medication-related fake news or drug-target extraction. Although a significant effort was made to detect mentions of drugs/chemicals in English texts, so far only very limited attempts were made to recognize them in medical documents in other languages. Taking into account the growing amount of medical publications and clinical records written in Spanish, we have organized the first shared task on detecting drug and chemical entities in Spanish medical documents. Additionally, we included a clinical concept-indexing sub-track asking teams to return SNOMED-CT identifiers related to drugs/chemicals for a collection of documents. For this task, named PharmaCoNER, we generated annotation guidelines together with a corpus of 1,000 manually annotated clinical case studies. A total of 22 teams participated in the sub-track 1, (77 system runs), and 7 teams in the sub-track 2 (19 system runs). Top scoring teams used sophisticated deep learning approaches yielding very competitive results with F-measures above 0.91. These results indicate that there is a real interest in promoting biomedical text mining efforts beyond English. We foresee that the PharmaCoNER annotation guidelines, corpus and participant systems will foster the development of new resources for clinical and biomedical text mining systems of Spanish medical data. |
| Tasks | Named Entity Recognition |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5701/ |
| https://www.aclweb.org/anthology/D19-5701 | |
| PWC | https://paperswithcode.com/paper/pharmaconer-pharmacological-substances |
| Repo | |
| Framework | |
Sample Size in Arabic Authorship Verification
| Title | Sample Size in Arabic Authorship Verification |
| Authors | Hossam Ahmed |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-7412/ |
| https://www.aclweb.org/anthology/W19-7412 | |
| PWC | https://paperswithcode.com/paper/sample-size-in-arabic-authorship-verification |
| Repo | |
| Framework | |
LDA Topic Modeling for pram=aṇa Texts: A Case Study in Sanskrit NLP Corpus Building
| Title | LDA Topic Modeling for pram=aṇa Texts: A Case Study in Sanskrit NLP Corpus Building |
| Authors | Tyler Neill |
| Abstract | |
| Tasks | |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-7505/ |
| https://www.aclweb.org/anthology/W19-7505 | |
| PWC | https://paperswithcode.com/paper/lda-topic-modeling-for-pramaa1a-texts-a-case |
| Repo | |
| Framework | |
Cross-Lingual Lemmatization and Morphology Tagging with Two-Stage Multilingual BERT Fine-Tuning
| Title | Cross-Lingual Lemmatization and Morphology Tagging with Two-Stage Multilingual BERT Fine-Tuning |
| Authors | Dan Kondratyuk |
| Abstract | We present our CHARLES-SAARLAND system for the SIGMORPHON 2019 Shared Task on Crosslinguality and Context in Morphology, in task 2, Morphological Analysis and Lemmatization in Context. We leverage the multilingual BERT model and apply several fine-tuning strategies introduced by UDify demonstrating exceptional evaluation performance on morpho-syntactic tasks. Our results show that fine-tuning multilingual BERT on the concatenation of all available treebanks allows the model to learn cross-lingual information that is able to boost lemmatization and morphology tagging accuracy over fine-tuning it purely monolingually. Unlike UDify, however, we show that when paired with additional character-level and word-level LSTM layers, a second stage of fine-tuning on each treebank individually can improve evaluation even further. Out of all submissions for this shared task, our system achieves the highest average accuracy and f1 score in morphology tagging and places second in average lemmatization accuracy. |
| Tasks | Lemmatization, Morphological Analysis |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4203/ |
| https://www.aclweb.org/anthology/W19-4203 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-lemmatization-and-morphology |
| Repo | |
| Framework | |
Investigating the Stability of Concrete Nouns in Word Embeddings
| Title | Investigating the Stability of Concrete Nouns in Word Embeddings |
| Authors | B{'e}n{'e}dicte Pierrejean, Ludovic Tanguy |
| Abstract | We know that word embeddings trained using neural-based methods (such as word2vec SGNS) are sensitive to stability problems and that across two models trained using the exact same set of parameters, the nearest neighbors of a word are likely to change. All words are not equally impacted by this internal instability and recent studies have investigated features influencing the stability of word embeddings. This stability can be seen as a clue for the reliability of the semantic representation of a word. In this work, we investigate the influence of the degree of concreteness of nouns on the stability of their semantic representation. We show that for English generic corpora, abstract words are more affected by stability problems than concrete words. We also found that to a certain extent, the difference between the degree of concreteness of a noun and its nearest neighbors can partly explain the stability or instability of its neighbors. |
| Tasks | Word Embeddings |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0510/ |
| https://www.aclweb.org/anthology/W19-0510 | |
| PWC | https://paperswithcode.com/paper/investigating-the-stability-of-concrete-nouns |
| Repo | |
| Framework | |
Convolutional Neural Networks for Financial Text Regression
| Title | Convolutional Neural Networks for Financial Text Regression |
| Authors | Ne{\c{s}}at Dereli, Murat Saraclar |
| Abstract | Forecasting financial volatility of a publicly-traded company from its annual reports has been previously defined as a text regression problem. Recent studies use a manually labeled lexicon to filter the annual reports by keeping sentiment words only. In order to remove the lexicon dependency without decreasing the performance, we replace bag-of-words model word features by word embedding vectors. Using word vectors increases the number of parameters. Considering the increase in number of parameters and excessive lengths of annual reports, a convolutional neural network model is proposed and transfer learning is applied. Experimental results show that the convolutional neural network model provides more accurate volatility predictions than lexicon based models. |
| Tasks | Transfer Learning |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2046/ |
| https://www.aclweb.org/anthology/P19-2046 | |
| PWC | https://paperswithcode.com/paper/convolutional-neural-networks-for-financial |
| Repo | |
| Framework | |
eventAI at SemEval-2019 Task 7: Rumor Detection on Social Media by Exploiting Content, User Credibility and Propagation Information
| Title | eventAI at SemEval-2019 Task 7: Rumor Detection on Social Media by Exploiting Content, User Credibility and Propagation Information |
| Authors | Quanzhi Li, Qiong Zhang, Luo Si |
| Abstract | This paper describes our system for SemEval 2019 RumorEval: Determining rumor veracity and support for rumors (SemEval 2019 Task 7). This track has two tasks: Task A is to determine a user{'}s stance towards the source rumor, and Task B is to detect the veracity of the rumor: true, false or unverified. For stance classification, a neural network model with language features is utilized. For rumor verification, our approach exploits information from different dimensions: rumor content, source credibility, user credibility, user stance, event propagation path, etc. We use an ensemble approach in both tasks, which includes neural network models as well as the traditional classification algorithms. Our system is ranked 1st place in the rumor verification task by both the macro F1 measure and the RMSE measure. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2148/ |
| https://www.aclweb.org/anthology/S19-2148 | |
| PWC | https://paperswithcode.com/paper/eventai-at-semeval-2019-task-7-rumor |
| Repo | |
| Framework | |
Variance Reduction in Bipartite Experiments through Correlation Clustering
| Title | Variance Reduction in Bipartite Experiments through Correlation Clustering |
| Authors | Jean Pouget-Abadie, Kevin Aydin, Warren Schudy, Kay Brodersen, Vahab Mirrokni |
| Abstract | Causal inference in randomized experiments typically assumes that the units of randomization and the units of analysis are one and the same. In some applications, however, these two roles are played by distinct entities linked by a bipartite graph. The key challenge in such bipartite settings is how to avoid interference bias, which would typically arise if we simply randomized the treatment at the level of analysis units. One effective way of minimizing interference bias in standard experiments is through cluster randomization, but this design has not been studied in the bipartite setting where conventional clustering schemes can lead to poorly powered experiments. This paper introduces a novel clustering objective and a corresponding algorithm that partitions a bipartite graph so as to maximize the statistical power of a bipartite experiment on that graph. Whereas previous work relied on balanced partitioning, our formulation suggests the use of a correlation clustering objective. We use a publicly-available graph of Amazon user-item reviews to validate our solution and illustrate how it substantially increases the statistical power in bipartite experiments. |
| Tasks | Causal Inference |
| Published | 2019-12-01 |
| URL | http://papers.nips.cc/paper/9486-variance-reduction-in-bipartite-experiments-through-correlation-clustering |
| http://papers.nips.cc/paper/9486-variance-reduction-in-bipartite-experiments-through-correlation-clustering.pdf | |
| PWC | https://paperswithcode.com/paper/variance-reduction-in-bipartite-experiments |
| Repo | |
| Framework | |
What Influences the Features of Post-editese? A Preliminary Study
| Title | What Influences the Features of Post-editese? A Preliminary Study |
| Authors | Sheila Castilho, Nat{'a}lia Resende, Ruslan Mitkov |
| Abstract | While a number of studies have shown evidence of translationese phenomena, that is, statistical differences between original texts and translated texts (Gellerstam, 1986), results of studies searching for translationese features in postedited texts (what has been called {''}posteditese{''} (Daems et al., 2017)) have presented mixed results. This paper reports a preliminary study aimed at identifying the presence of post-editese features in machine-translated post-edited texts and at understanding how they differ from translationese features. We test the influence of factors such as post-editing (PE) levels (full vs. light), translation proficiency (professionals vs. students) and text domain (news vs. literary). Results show evidence of post-editese features, especially in light PE texts and in certain domains. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-8703/ |
| https://www.aclweb.org/anthology/W19-8703 | |
| PWC | https://paperswithcode.com/paper/what-influences-the-features-of-post-editese |
| Repo | |
| Framework | |
