Paper Group NANR 126
On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution. Neural Coreference Resolution with Limited Lexical Context and Explicit Mention Detection for Oral French. Cross-lingual Incongruences in the Annotation of Coreference. On Sentence Representations for Propaganda Detection: From Handcrafted Features to Word Embeddings. …
On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution
| Title | On GAP Coreference Resolution Shared Task: Insights from the 3rd Place Solution |
| Authors | Artem Abzaliev |
| Abstract | This paper presents the 3rd-place-winning solution to the GAP coreference resolution shared task. The approach adopted consists of two key components: fine-tuning the BERT language representation model (Devlin et al., 2018) and the usage of external datasets during the training process. The model uses hidden states from the intermediate BERT layers instead of the last layer. The resulting system almost eliminates the difference in log loss per gender during the cross-validation, while providing high performance. |
| Tasks | Coreference Resolution |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3816/ |
| https://www.aclweb.org/anthology/W19-3816 | |
| PWC | https://paperswithcode.com/paper/on-gap-coreference-resolution-shared-task |
| Repo | |
| Framework | |
Neural Coreference Resolution with Limited Lexical Context and Explicit Mention Detection for Oral French
| Title | Neural Coreference Resolution with Limited Lexical Context and Explicit Mention Detection for Oral French |
| Authors | Lo{"\i}c Grobol |
| Abstract | We propose an end-to-end coreference resolution system obtained by adapting neural models that have recently improved the state-of-the-art on the OntoNotes benchmark to make them applicable to other paradigms for this task. We report the performances of our system on ANCOR, a corpus of transcribed oral French, for which it constitutes a new baseline with proper evaluation. |
| Tasks | Coreference Resolution |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2802/ |
| https://www.aclweb.org/anthology/W19-2802 | |
| PWC | https://paperswithcode.com/paper/neural-coreference-resolution-with-limited |
| Repo | |
| Framework | |
Cross-lingual Incongruences in the Annotation of Coreference
| Title | Cross-lingual Incongruences in the Annotation of Coreference |
| Authors | Ekaterina Lapshinova-Koltunski, Sharid Lo{'a}iciga, Christian Hardmeier, Pauline Krielke |
| Abstract | In the present paper, we deal with incongruences in English-German multilingual coreference annotation and present automated methods to discover them. More specifically, we automatically detect full coreference chains in parallel texts and analyse discrepancies in their annotations. In doing so, we wish to find out whether the discrepancies rather derive from language typological constraints, from the translation or the actual annotation process. The results of our study contribute to the referential analysis of similarities and differences across languages and support evaluation of cross-lingual coreference annotation. They are also useful for cross-lingual coreference resolution systems and contrastive linguistic studies. |
| Tasks | Coreference Resolution |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-2805/ |
| https://www.aclweb.org/anthology/W19-2805 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-incongruences-in-the-annotation |
| Repo | |
| Framework | |
On Sentence Representations for Propaganda Detection: From Handcrafted Features to Word Embeddings
| Title | On Sentence Representations for Propaganda Detection: From Handcrafted Features to Word Embeddings |
| Authors | Andr{'e} Ferreira Cruz, Gil Rocha, Henrique Lopes Cardoso |
| Abstract | Bias is ubiquitous in most online sources of natural language, from news media to social networks. Given the steady shift in news consumption behavior from traditional outlets to online sources, the automatic detection of propaganda, in which information is shaped to purposefully foster a predetermined agenda, is an increasingly crucial task. To this goal, we explore the task of sentence-level propaganda detection, and experiment with both handcrafted features and learned dense semantic representations. We also experiment with random undersampling of the majority class (non-propaganda) to curb the influence of class distribution on the system{'}s performance, leading to marked improvements on the minority class (propaganda). Our best performing system uses pre-trained ELMo word embeddings, followed by a bidirectional LSTM and an attention layer. We have submitted a 5-model ensemble of our best performing system to the NLP4IF shared task on sentence-level propaganda detection (team LIACC), achieving rank 10 among 25 participants, with 59.5 F1-score. |
| Tasks | Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5015/ |
| https://www.aclweb.org/anthology/D19-5015 | |
| PWC | https://paperswithcode.com/paper/on-sentence-representations-for-propaganda |
| Repo | |
| Framework | |
Controlling Over-generalization and its Effect on Adversarial Examples Detection and Generation
| Title | Controlling Over-generalization and its Effect on Adversarial Examples Detection and Generation |
| Authors | Mahdieh Abbasi, Arezoo Rajabi, Azadeh Sadat Mozafari, Rakesh B. Bobba, Christian Gagné |
| Abstract | Convolutional Neural Networks (CNNs) significantly improve the state-of-the-art for many applications, especially in computer vision. However, CNNs still suffer from a tendency to confidently classify out-distribution samples from unknown classes into pre-defined known classes. Further, they are also vulnerable to adversarial examples. We are relating these two issues through the tendency of CNNs to over-generalize for areas of the input space not covered well by the training set. We show that a CNN augmented with an extra output class can act as a simple yet effective end-to-end model for controlling over-generalization. As an appropriate training set for the extra class, we introduce two resources that are computationally efficient to obtain: a representative natural out-distribution set and interpolated in-distribution samples. To help select a representative natural out-distribution set among available ones, we propose a simple measurement to assess an out-distribution set’s fitness. We also demonstrate that training such an augmented CNN with representative out-distribution natural datasets and some interpolated samples allows it to better handle a wide range of unseen out-distribution samples and black-box adversarial examples without training it on any adversaries. Finally, we show that generation of white-box adversarial attacks using our proposed augmented CNN can become harder, as the attack algorithms have to get around the rejection regions when generating actual adversaries. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Skgge3R9FQ |
| https://openreview.net/pdf?id=Skgge3R9FQ | |
| PWC | https://paperswithcode.com/paper/controlling-over-generalization-and-its |
| Repo | |
| Framework | |
Detection of Propaganda Using Logistic Regression
| Title | Detection of Propaganda Using Logistic Regression |
| Authors | Jinfen Li, Zhihao Ye, Lu Xiao |
| Abstract | Various propaganda techniques are used to manipulate peoples perspectives in order to foster a predetermined agenda such as by the use of logical fallacies or appealing to the emotions of the audience. In this paper, we develop a Logistic Regression-based tool that automatically classifies whether a sentence is propagandistic or not. We utilize features like TF-IDF, BERT vector, sentence length, readability grade level, emotion feature, LIWC feature and emphatic content feature to help us differentiate these two categories. The linguistic and semantic features combination results in 66.16{%} of F1 score, which outperforms the baseline hugely. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5017/ |
| https://www.aclweb.org/anthology/D19-5017 | |
| PWC | https://paperswithcode.com/paper/detection-of-propaganda-using-logistic |
| Repo | |
| Framework | |
Clean-Label Backdoor Attacks
| Title | Clean-Label Backdoor Attacks |
| Authors | Alexander Turner, Dimitris Tsipras, Aleksander Madry |
| Abstract | Deep neural networks have been recently demonstrated to be vulnerable to backdoor attacks. Specifically, by altering a small set of training examples, an adversary is able to install a backdoor that can be used during inference to fully control the model’s behavior. While the attack is very powerful, it crucially relies on the adversary being able to introduce arbitrary, often clearly mislabeled, inputs to the training set and can thus be detected even by fairly rudimentary data filtering. In this paper, we introduce a new approach to executing backdoor attacks, utilizing adversarial examples and GAN-generated data. The key feature is that the resulting poisoned inputs appear to be consistent with their label and thus seem benign even upon human inspection. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJg6e2CcK7 |
| https://openreview.net/pdf?id=HJg6e2CcK7 | |
| PWC | https://paperswithcode.com/paper/clean-label-backdoor-attacks |
| Repo | |
| Framework | |
Proceedings of the 12th International Conference on Natural Language Generation
| Title | Proceedings of the 12th International Conference on Natural Language Generation |
| Authors | |
| Abstract | |
| Tasks | Text Generation |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-8600/ |
| https://www.aclweb.org/anthology/W19-8600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-12th-international-4 |
| Repo | |
| Framework | |
Shifting More Attention to Video Salient Object Detection
| Title | Shifting More Attention to Video Salient Object Detection |
| Authors | Deng-Ping Fan, Wenguan Wang, Ming-Ming Cheng, Jianbing Shen |
| Abstract | The last decade has witnessed a growing interest in video salient object detection (VSOD). However, the research community long-term lacked a well-established VSOD dataset representative of real dynamic scenes with high-quality annotations. To address this issue, we elaborately collected a visual-attention-consistent Densely Annotated VSOD (DAVSOD) dataset, which contains 226 videos with 23,938 frames that cover diverse realistic-scenes, objects, instances and motions. With corresponding real human eye-fixation data, we obtain precise ground-truths. This is the first work that explicitly emphasizes the challenge of saliency shift, i.e., the video salient object(s) may dynamically change. To further contribute the community a complete benchmark, we systematically assess 17 representative VSOD algorithms over seven existing VSOD datasets and our DAVSOD with totally 84K frames (largest-scale). Utilizing three famous metrics, we then present a comprehensive and insightful performance analysis. Furthermore, we propose a baseline model. It is equipped with a saliency shift- aware convLSTM, which can efficiently capture video saliency dynamics through learning human attention-shift behavior. Extensive experiments open up promising future directions for model development and comparison. |
| Tasks | Object Detection, Salient Object Detection, Video Salient Object Detection |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Fan_Shifting_More_Attention_to_Video_Salient_Object_Detection_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Fan_Shifting_More_Attention_to_Video_Salient_Object_Detection_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/shifting-more-attention-to-video-salient |
| Repo | |
| Framework | |
The Impact of Spelling Correction and Task Context on Short Answer Assessment for Intelligent Tutoring Systems
| Title | The Impact of Spelling Correction and Task Context on Short Answer Assessment for Intelligent Tutoring Systems |
| Authors | Ramon Ziai, Florian Nuxoll, Kordula De Kuthy, Bj{"o}rn Rudzewitz, Detmar Meurers |
| Abstract | |
| Tasks | Spelling Correction |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6310/ |
| https://www.aclweb.org/anthology/W19-6310 | |
| PWC | https://paperswithcode.com/paper/the-impact-of-spelling-correction-and-task |
| Repo | |
| Framework | |
Synthetic Propaganda Embeddings To Train A Linear Projection
| Title | Synthetic Propaganda Embeddings To Train A Linear Projection |
| Authors | Adam Ek, Mehdi Ghanimifard |
| Abstract | This paper presents a method of detecting fine-grained categories of propaganda in text. Given a sentence, our method aims to identify a span of words and predict the type of propaganda used. To detect propaganda, we explore a method for extracting features of propaganda from contextualized embeddings without fine-tuning the large parameters of the base model. We show that by generating synthetic embeddings we can train a linear function with ReLU activation to extract useful labeled embeddings from an embedding space generated by a general-purpose language model. We also introduce an inference technique to detect continuous spans in sequences of propaganda tokens in sentences. A result of the ensemble model is submitted to the first shared task in fine-grained propaganda detection at NLP4IF as Team Stalin. In this paper, we provide additional analysis regarding our method of detecting spans of propaganda with synthetically generated representations. |
| Tasks | Language Modelling |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5023/ |
| https://www.aclweb.org/anthology/D19-5023 | |
| PWC | https://paperswithcode.com/paper/synthetic-propaganda-embeddings-to-train-a |
| Repo | |
| Framework | |
Generating Natural Anagrams: Towards Language Generation Under Hard Combinatorial Constraints
| Title | Generating Natural Anagrams: Towards Language Generation Under Hard Combinatorial Constraints |
| Authors | Masaaki Nishino, Sho Takase, Tsutomu Hirao, Masaaki Nagata |
| Abstract | An anagram is a sentence or a phrase that is made by permutating the characters of an input sentence or a phrase. For example, {}Trims cash{''} is an anagram of {}Christmas{''}. Existing automatic anagram generation methods can find possible combinations of words form an anagram. However, they do not pay much attention to the naturalness of the generated anagrams. In this paper, we show that simple depth-first search can yield natural anagrams when it is combined with modern neural language models. Human evaluation results show that the proposed method can generate significantly more natural anagrams than baseline methods. |
| Tasks | Text Generation |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1674/ |
| https://www.aclweb.org/anthology/D19-1674 | |
| PWC | https://paperswithcode.com/paper/generating-natural-anagrams-towards-language |
| Repo | |
| Framework | |
Offence in Dialogues: A Corpus-Based Study
| Title | Offence in Dialogues: A Corpus-Based Study |
| Authors | Johannes Sch{"a}fer, Ben Burtenshaw |
| Abstract | In recent years an increasing number of analyses of offensive language has been published, however, dealing mainly with the automatic detection and classification of isolated instances. In this paper we aim to understand the impact of offensive messages in online conversations diachronically, and in particular the change in offensiveness of dialogue turns. In turn, we aim to measure the progression of offence level as well as its direction - For example, whether a conversation is escalating or declining in offence. We present our method of extracting linear dialogues from tree-structured conversations in social media data and make our code publicly available. Furthermore, we discuss methods to analyse this dataset through changes in discourse offensiveness. Our paper includes two main contributions; first, using a neural network to measure the level of offensiveness in conversations; and second, the analysis of conversations around offensive comments using decoupling functions. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1125/ |
| https://www.aclweb.org/anthology/R19-1125 | |
| PWC | https://paperswithcode.com/paper/offence-in-dialogues-a-corpus-based-study |
| Repo | |
| Framework | |
GKR: Bridging the Gap between Symbolic/structural and Distributional Meaning Representations
| Title | GKR: Bridging the Gap between Symbolic/structural and Distributional Meaning Representations |
| Authors | Aikaterini-Lida Kalouli, Richard Crouch, Valeria de Paiva |
| Abstract | Three broad approaches have been attempted to combine distributional and structural/symbolic aspects to construct meaning representations: a) injecting linguistic features into distributional representations, b) injecting distributional features into symbolic representations or c) combining structural and distributional features in the final representation. This work focuses on an example of the third and less studied approach: it extends the Graphical Knowledge Representation (GKR) to include distributional features and proposes a division of semantic labour between the distributional and structural/symbolic features. We propose two extensions of GKR that clearly show this division and empirically test one of the proposals on an NLI dataset with hard compositional pairs. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3305/ |
| https://www.aclweb.org/anthology/W19-3305 | |
| PWC | https://paperswithcode.com/paper/gkr-bridging-the-gap-between |
| Repo | |
| Framework | |
Soft Labels for Ordinal Regression
| Title | Soft Labels for Ordinal Regression |
| Authors | Raul Diaz, Amit Marathe |
| Abstract | Ordinal regression attempts to solve classification problems in which categories are not independent, but rather follow a natural order. It is crucial to classify each class correctly while learning adequate interclass ordinal relationships. We present a simple and effective method that constrains these relationships among categories by seamlessly incorporating metric penalties into ground truth label representations. This encoding allows deep neural networks to automatically learn intraclass and interclass relationships without any explicit modification of the network architecture. Our method converts data labels into soft probability distributions that pair well with common categorical loss functions such as cross-entropy. We show that this approach is effective by using off-the-shelf classification and segmentation networks in four wildly different scenarios: image quality ranking, age estimation, horizon line regression, and monocular depth estimation. We demonstrate that our general-purpose method is very competitive with respect to specialized approaches, and adapts well to a variety of different network architectures and metrics. |
| Tasks | Age Estimation, Depth Estimation, Monocular Depth Estimation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Diaz_Soft_Labels_for_Ordinal_Regression_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Diaz_Soft_Labels_for_Ordinal_Regression_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/soft-labels-for-ordinal-regression |
| Repo | |
| Framework | |
