Merge branch 'master' into add-kranzlein-et-al

semeval20-task11.bib

@@ -12,15 +12,15 @@ @InProceedings{Blaschke
 author = "Blaschke, Verena and
   Korniyenko, Maxim and
   Tureski, Sam",
-title = "{CyberWallE} at {SemEval}-2020 {T}ask 11: An Analysis of Feature Engineering for Ensemble Models for Propaganda Detection",
+title = "{CyberWallE} at {SemEval}-2020 {T}ask 11: {A}n Analysis of Feature Engineering for Ensemble Models for Propaganda Detection",
 pages = "",
 abstract = "This paper describes our participation in the SemEval-2020 task Detection of Propaganda Techniques in News Articles. We participate in both subtasks: Span Identification (SI) and Technique Classification (TC). We use a bi-LSTM architecture in the SI subtask and train a complex ensemble model for the TC subtask. Our architectures are built using embeddings from BERT in combination with additional lexical features and extensive label post-processing. Our systems achieve a rank of 8 out of 36 teams in the SI subtask (F1-score: 43.86\%) and 8 out of 31 teams in the TC subtask (F1-score: 57.37\%).",
 crossref = "SemEval20"
 }
 
 @InProceedings{Chauhan,
 author = "Chauhan,Aniruddha and Diddee, Harshita",
-title = "{PsuedoProp} at {SemEval}-2020 {T}ask 11:Propaganda Span Detection using BERT-CRF and Ensemble Sentence Level Classifier",
+title = "{PsuedoProp} at {SemEval}-2020 {T}ask 11: {P}ropaganda Span Detection using BERT-CRF and Ensemble Sentence Level Classifier",
 pages = "",
 abstract = "This paper presents our solution for Span Identification (SI) Task under “Task 11: Detection of Propaganda Techniques in News Articles” of SemEval 2020.This task aims to identify if a given sentence, taken from a corpus of news articles, contains a propaganda span and hence aims to identify the character level offsets of the identified propaganda element. Our solution proposes a sequential approach in which the span identification is preceded by an ensemble sentence level classifier (SLC).We only perform span identification on those samples which are flagged as propaganda samples by the SLC Model. We perform token level classification by fine-tuning BERT and use CRF to perform sequence tagging. Additionally, we present our analysis on different voting ensembles for the SLC model. Our system ranks 14th on the test set and 22nd on the development set and with an F1 score of 0.41 and 0.39 respectively.",
 crossref = "SemEval20"
@@ -30,12 +30,22 @@ @InProceedings{Dementieva
 author = "Dementieva, Daryna and
   Markov, Igor and
   Panchenko, Alexander",
-title = "SkoltechNLP at SemEval-2020 Task 11: Exploring Unsupervised Text Augmentation for Propaganda Detection",
+title = "{SkoltechNLP} at {SemEval}-2020 {T}ask 11: {E}xploring Unsupervised Text Augmentation for Propaganda Detection",
 pages = "",
 abstract = "This paper presents a solution for the Span Identification (SI) task in the ''Detection of Propaganda Techniques in News Articles'' competition at SemEval-2020. The goal of the SI task is to identify specific fragments of each article which contain the use of at least one propaganda technique. This is a binary sequence tagging task. We tested several approaches finally selecting a fine-tuned BERT model as our baseline model. Our main contribution is an investigation of several unsupervised data augmentation techniques based on distributional semantics expanding the original small training dataset as applied to this BERT-based sequence tagger. We show that, although increases in F1 score are not significant, usage of some expansion strategies can lead to discrete improvements in precision and recall.",
 crossref = "SemEval20"
 }
 
+@InProceedings{Dimov,
+author = "Dimov, Ilya and
+  Korzun, Vladislav and
+  Smurov, Ivan",
+title = "{NoPropaganda} at {SemEval}-2020 {T}ask 11: {A} Borrowed Approach to Sequence Tagging and Text Classification",
+pages = "",
+abstract = "This paper describes our contribution to SemEval-2020 Task 11: Detection Of Propaganda Techniques In News Articles. We start with simple LSTM baselines and move to an autoregressive transformer decoder to predict long continuous propaganda spans for the first subtask. We also adopt an approach from relation extraction by enveloping spans mentioned above with special tokens for the second subtask of propaganda technique classification. Our models report an F-score of 44.6% and a micro-averaged F-score of 58.2% for those tasks accordingly.",
+crossref = "SemEval20"
+}
+
 @InProceedings{Jurkiewicz,
 author = "Jurkiewicz, Dawid and
   Borchmann, {\L}ukasz and
@@ -61,7 +71,7 @@ @InProceedings{Martinkovic
 author = "Martinkovic, Matej and
   Pecar, Samuel and
   Simko, Marian",
-title = "NLFIIT at {SemEval}-2020 Task 11: Neural Network Architectures for Detection of Propaganda Techniques in News Articles",
+title = "{NLFIIT} at {SemEval}-2020 {T}ask 11: {N}eural Network Architectures for Detection of Propaganda Techniques in News Articles",
 pages = "",
 abstract = "Since propaganda became more common technique in news, it is very important to look for possibilities of its automatic detection. In this paper, we present neural model architecture submitted to the SemEval-2020 Task 11 competition: Detection of Propaganda Techniques in News Articles. We participated in both subtasks, propaganda span identification and propaganda technique classification. Our model uses recurrent Bi-LSTM layers and also takes advantage of self-attention mechanism. Our model managed to achieve score 0.405 F1 for subtask 1 and 0.553 F1 for subtask 2 resulting in 18th and 16th place in subtask 1 and subtask 2, respectively.",
 crossref = "SemEval20"
@@ -70,20 +80,30 @@ @InProceedings{Martinkovic
 @InProceedings{Paraschiv,
 author = "Paraschiv, Andrei and
   Cercel, Dumitru-Clementin",
-title = "UPB at {SemEval}-2020 Task 11: Propaganda Detection with Domain-Specific Trained BERT",
+title = "{UPB} at {SemEval}-2020 {T}ask 11: {P}ropaganda Detection with Domain-Specific Trained BERT",
 pages = "",
 abstract = "This paper describes our participation in the Semeval 2020, Task 11 - detection of propaganda techniques in news articles competition. By furthering the unsupervised pre-training of the standard BERT model, we specialize the model on propagandistic and hyperpartisan news articles, allowing it to find better representations for the two subtasks - propaganda span detection and propaganda technique classification. Our proposed system achieved in subtask SI a F1 score of 46.06\%, ranking 5th in the leaderboard and for subtask TC an overall F1 average of 54.302\% ranking 19th from 32 teams.",
 crossref = "SemEval20"
 }
 
+@InProceedings{Patil,
+author = "Patil, Rajaswa and
+  Singh, Somesh and
+  Agarwal, Swati",
+title = "{BPGC} at {SemEval}-2020 {T}ask 11: {P}ropaganda Detection in News Articles with Multi-Granularity Knowledge Sharing and Linguistic Features based Ensemble Learning",
+pages = "",
+abstract = "Propaganda spreads the ideology and beliefs of like-minded people, brainwashing their audiences, and sometimes leading to violence. SemEval 2020 Task-11 aims to design automated systems for news propaganda detection. Task-11 consists of two sub-tasks, namely, Span Identification - given any news article, the system tags those specific fragments which contain at least one propaganda technique; and Technique Classification - correctly classify a given propagandist statement amongst 14 propaganda techniques. For sub-task 1, we use contextual embeddings extracted from pre-trained transformer models to represent the text data at various granularities and propose a multi-granularity knowledge sharing approach. For sub-task 2, we use an ensemble of BERT and logistic regression classifiers with linguistic features. Our results reveal that the linguistic features are the strong indicators for covering minority classes in a highly imbalanced dataset.",
+crossref = "SemEval20"
+}
+
 @InProceedings{Raj,
 author = "Raj, Mayank and
 Jaiswal, Ajay and R.R, Rohit and
 Gupta, Ankita and
 Sahoo, Sudeep and
 Srivastava,Vertika and
 Yeon Hyang ,Kim ",
-title = "Solomon at {SemEval}-2020 {T}ask 11: Novel Ensemble Architechture for Fine-Tuned Propoganda Detection in News Articles",
+title = "Solomon at {SemEval}-2020 {T}ask 11: {N}ovel Ensemble Architechture for Fine-Tuned Propoganda Detection in News Articles",
 pages = "",
 abstract = "This paper describes our system (Solomon) details and results of participation in the SemEval 2020 Task 11 ”Detection of Propaganda Techniques in News Articles”. We participated in Task ”Technique Classification” (TC) which is a multi-class classification task. To address the TC task, we used RoBERTa based transformer architecture for fine-tuning on the propaganda dataset. The predictions of RoBERTa were further fine-tuned by class-dependent-minority-class classifiers. A special classifier, which employs dynamically adapted Least Common Sub-sequence algorithm, is used to adapt to the intricacies of repetition class. Compared to the other participating systems,our submission is ranked 4th on the leaderboard.",
 crossref = "SemEval20"
@@ -93,7 +113,7 @@ @InProceedings{Verma
 author = "Verma, Ekansh  and
         Motupalli, Vinodh and
         Chakraborty, Souradip",
-title = "{Transformers} at {SemEval}-2020 {T}ask 11: Propaganda Fragment Detection using Diversified BERT Architectures based Ensemble Learning",
+title = "{Transformers} at {SemEval}-2020 {T}ask 11: {P}ropaganda Fragment Detection using Diversified BERT Architectures based Ensemble Learning",
 pages = "",
 abstract = "In this paper, we present our approach for the ’Detection of Propaganda Techniques in NewsArticles’ task as a part of the 2020 edition of International Workshop on Semantic Evaluation.The specific objective of this task is to identify and extract the text segments in which propagandatechniques are used.  We propose a multi-system deep learning framework that can be used toidentify the presence of propaganda fragments in a news article and also deep dive into the diverseenhancements of BERT architecture which are part of the final solution. Our proposed final modelgave an F1-score of 0.48 on the test dataset.",
 crossref = "SemEval20"
@@ -106,7 +126,7 @@ @InProceedings{DaSanMartinoSemeval20task11
   Wachsmuth, Henning and
   Petrov, Rostislav and
   Nakov, Preslav",
-title = "{SemEval}-2020 Task 11: Detection of Propaganda Techniques in News Articles",
+title = "{SemEval}-2020 Task 11: {D}etection of Propaganda Techniques in News Articles",
 pages = "",
 abstract = "We describe the outcome of the SemEval 2020 Task 11 on the detection of propaganda in news articles. We present two tasks. In the first task, systems are asked to identify specific text spans in a free text where propaganda is being applied. In the second task, systems are asked to identify the propaganda technique being applied in a text span. We describe the construction of the evaluation framework (dataset and evaluation metrics) as well as the approaches explored by the different participants. ",
 crossref = "SemEval20"
@@ -134,16 +154,6 @@ @InProceedings{EMNLP19DaSanMartino
 month = "November",
 }
 
-@InProceedings{Patil,
-author = "Patil, Rajaswa and
-  Singh, Somesh and
-  Agarwal, Swati",
-title = "{BPGC} at {SemEval}-2020 {T}ask 11: Propaganda Detection in News Articles with Multi-Granularity Knowledge Sharing and Linguistic Features based Ensemble Learning",
-pages = "",
-abstract = "Propaganda spreads the ideology and beliefs of like-minded people, brainwashing their audiences, and sometimes leading to violence. SemEval 2020 Task-11 aims to design automated systems for news propaganda detection. Task-11 consists of two sub-tasks, namely, Span Identification - given any news article, the system tags those specific fragments which contain at least one propaganda technique; and Technique Classification - correctly classify a given propagandist statement amongst 14 propaganda techniques. For sub-task 1, we use contextual embeddings extracted from pre-trained transformer models to represent the text data at various granularities and propose a multi-granularity knowledge sharing approach. For sub-task 2, we use an ensemble of BERT and logistic regression classifiers with linguistic features. Our results reveal that the linguistic features are the strong indicators for covering minority classes in a highly imbalanced dataset.",
-crossref = "SemEval20"
-}
-
 @InProceedings{Kranzlein,
 author = "Kranzlein, Michael and
   Behzad, Shabnam and
@@ -153,3 +163,4 @@ @InProceedings{Kranzlein
 abstract = "This paper presents our systems for SemEval 2020 Shared Task 11: Detection of Propaganda Techniques in News Articles. We participate in both the span identification and technique classification subtasks and report on experiments using different BERT-based models along with handcrafted features. Out models perform well above the baseline for both tasks, and we contribute ablation studies and discussion of our results to dissect the effectiveness of different features and techniques with the goal of aiding future studies in propaganda detection.",
 crossref = "SemEval20"
 }
+