Paper Group NANR 23
Corpus of Multimodal Interaction for Collaborative Planning. Contextualized Role Interaction for Neural Machine Translation. Building Detail-Sensitive Semantic Segmentation Networks With Polynomial Pooling. Exploring Pre-trained Language Models for Event Extraction and Generation. UaiNets: From Unsupervised to Active Deep Anomaly Detection. Summary …
Corpus of Multimodal Interaction for Collaborative Planning
| Title | Corpus of Multimodal Interaction for Collaborative Planning |
| Authors | Miltiadis Marios Katsakioris, Helen Hastie, Ioannis Konstas, Atanas Laskov |
| Abstract | As autonomous systems become more commonplace, we need a way to easily and naturally communicate to them our goals and collaboratively come up with a plan on how to achieve these goals. To this end, we conducted a Wizard of Oz study to gather data and investigate the way operators would collaboratively make plans via a conversational {`}planning assistant{'} for remote autonomous systems. We present here a corpus of 22 dialogs from expert operators, which can be used to train such a system. Data analysis shows that multimodality is key to successful interaction, measured both quantitatively and qualitatively via user feedback. | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1601/ |
| https://www.aclweb.org/anthology/W19-1601 | |
| PWC | https://paperswithcode.com/paper/corpus-of-multimodal-interaction-for |
| Repo | |
| Framework | |
Contextualized Role Interaction for Neural Machine Translation
| Title | Contextualized Role Interaction for Neural Machine Translation |
| Authors | Dirk Weissenborn, Douwe Kiela, Jason Weston, Kyunghyun Cho |
| Abstract | Word inputs tend to be represented as single continuous vectors in deep neural networks. It is left to the subsequent layers of the network to extract relevant aspects of a word’s meaning based on the context in which it appears. In this paper, we investigate whether word representations can be improved by explicitly incorporating the idea of latent roles. That is, we propose a role interaction layer (RIL) that consists of context-dependent (latent) role assignments and role-specific transformations. We evaluate the RIL on machine translation using two language pairs (En-De and En-Fi) and three datasets of varying size. We find that the proposed mechanism improves translation quality over strong baselines with limited amounts of data, but that the improvement diminishes as the size of data grows, indicating that powerful neural MT systems are capable of implicitly modeling role-word interaction by themselves. Our qualitative analysis reveals that the RIL extracts meaningful context-dependent roles and that it allows us to inspect more deeply the internal mechanisms of state-of-the-art neural machine translation systems. |
| Tasks | Machine Translation |
| Published | 2019-01-01 |
| URL | https://openreview.net/forum?id=ryx3_iAcY7 |
| https://openreview.net/pdf?id=ryx3_iAcY7 | |
| PWC | https://paperswithcode.com/paper/contextualized-role-interaction-for-neural |
| Repo | |
| Framework | |
Building Detail-Sensitive Semantic Segmentation Networks With Polynomial Pooling
| Title | Building Detail-Sensitive Semantic Segmentation Networks With Polynomial Pooling |
| Authors | Zhen Wei, Jingyi Zhang, Li Liu, Fan Zhu, Fumin Shen, Yi Zhou, Si Liu, Yao Sun, Ling Shao |
| Abstract | Semantic segmentation is an important computer vision task, which aims to allocate a semantic label to each pixel in an image. When training a segmentation model, it is common to fine-tune a classification network pre-trained on a large-scale dataset. However, as an intrinsic property of the classification model, invariance to spatial perturbation resulting from the lose of detail-sensitivity prevents segmentation networks from achieving high performance. The use of standard poolings is one of the key factors for this invariance. The most common standard poolings are max and average pooling. Max pooling can increase both the invariance to spatial perturbations and the non-linearity of the networks. Average pooling, on the other hand, is sensitive to spatial perturbations, but is a linear function. For semantic segmentation, we prefer both the preservation of detailed cues within a local feature region and non-linearity that increases a network’s functional complexity. In this work, we propose a polynomial pooling (P-pooling) function that finds an intermediate form between max and average pooling to provide an optimally balanced and self-adjusted pooling strategy for semantic segmentation. The P-pooling is differentiable and can be applied into a variety of pre-trained networks. Extensive studies on the PASCAL VOC, Cityscapes and ADE20k datasets demonstrate the superiority of P-pooling over other poolings. Experiments on various network architectures and state-of-the-art training strategies also show that models with P-pooling layers consistently outperform those directly fine-tuned using pre-trained classification models. |
| Tasks | Semantic Segmentation |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Wei_Building_Detail-Sensitive_Semantic_Segmentation_Networks_With_Polynomial_Pooling_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Wei_Building_Detail-Sensitive_Semantic_Segmentation_Networks_With_Polynomial_Pooling_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/building-detail-sensitive-semantic |
| Repo | |
| Framework | |
Exploring Pre-trained Language Models for Event Extraction and Generation
| Title | Exploring Pre-trained Language Models for Event Extraction and Generation |
| Authors | Sen Yang, Dawei Feng, Linbo Qiao, Zhigang Kan, Dongsheng Li |
| Abstract | Traditional approaches to the task of ACE event extraction usually depend on manually annotated data, which is often laborious to create and limited in size. Therefore, in addition to the difficulty of event extraction itself, insufficient training data hinders the learning process as well. To promote event extraction, we first propose an event extraction model to overcome the roles overlap problem by separating the argument prediction in terms of roles. Moreover, to address the problem of insufficient training data, we propose a method to automatically generate labeled data by editing prototypes and screen out generated samples by ranking the quality. Experiments on the ACE2005 dataset demonstrate that our extraction model can surpass most existing extraction methods. Besides, incorporating our generation method exhibits further significant improvement. It obtains new state-of-the-art results on the event extraction task, including pushing the F1 score of trigger classification to 81.1{%}, and the F1 score of argument classification to 58.9{%}. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1522/ |
| https://www.aclweb.org/anthology/P19-1522 | |
| PWC | https://paperswithcode.com/paper/exploring-pre-trained-language-models-for |
| Repo | |
| Framework | |
UaiNets: From Unsupervised to Active Deep Anomaly Detection
| Title | UaiNets: From Unsupervised to Active Deep Anomaly Detection |
| Authors | Tiago Pimentel, Marianne Monteiro, Juliano Viana, Adriano Veloso, Nivio Ziviani |
| Abstract | This work presents a method for active anomaly detection which can be built upon existing deep learning solutions for unsupervised anomaly detection. We show that a prior needs to be assumed on what the anomalies are, in order to have performance guarantees in unsupervised anomaly detection. We argue that active anomaly detection has, in practice, the same cost of unsupervised anomaly detection but with the possibility of much better results. To solve this problem, we present a new layer that can be attached to any deep learning model designed for unsupervised anomaly detection to transform it into an active method, presenting results on both synthetic and real anomaly detection datasets. |
| Tasks | Anomaly Detection, Unsupervised Anomaly Detection |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HJex0o05F7 |
| https://openreview.net/pdf?id=HJex0o05F7 | |
| PWC | https://paperswithcode.com/paper/uainets-from-unsupervised-to-active-deep |
| Repo | |
| Framework | |
Summary Refinement through Denoising
| Title | Summary Refinement through Denoising |
| Authors | Nikola Nikolov, Aless Calmanovici, ro, Richard Hahnloser |
| Abstract | We propose a simple method for post-processing the outputs of a text summarization system in order to refine its overall quality. Our approach is to train text-to-text rewriting models to correct information redundancy errors that may arise during summarization. We train on synthetically generated noisy summaries, testing three different types of noise that introduce out-of-context information within each summary. When applied on top of extractive and abstractive summarization baselines, our summary denoising models yield metric improvements while reducing redundancy. |
| Tasks | Abstractive Text Summarization, Denoising, Text Summarization |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1097/ |
| https://www.aclweb.org/anthology/R19-1097 | |
| PWC | https://paperswithcode.com/paper/summary-refinement-through-denoising-1 |
| Repo | |
| Framework | |
Augmenting Abstract Meaning Representation for Human-Robot Dialogue
| Title | Augmenting Abstract Meaning Representation for Human-Robot Dialogue |
| Authors | Claire Bonial, Lucia Donatelli, Stephanie M. Lukin, Stephen Tratz, Ron Artstein, David Traum, Clare Voss |
| Abstract | We detail refinements made to Abstract Meaning Representation (AMR) that make the representation more suitable for supporting a situated dialogue system, where a human remotely controls a robot for purposes of search and rescue and reconnaissance. We propose 36 augmented AMRs that capture speech acts, tense and aspect, and spatial information. This linguistic information is vital for representing important distinctions, for example whether the robot has moved, is moving, or will move. We evaluate two existing AMR parsers for their performance on dialogue data. We also outline a model for graph-to-graph conversion, in which output from AMR parsers is converted into our refined AMRs. The design scheme presented here, though task-specific, is extendable for broad coverage of speech acts using AMR in future task-independent work. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3322/ |
| https://www.aclweb.org/anthology/W19-3322 | |
| PWC | https://paperswithcode.com/paper/augmenting-abstract-meaning-representation |
| Repo | |
| Framework | |
Entangled Transformer for Image Captioning
| Title | Entangled Transformer for Image Captioning |
| Authors | Guang Li, Linchao Zhu, Ping Liu, Yi Yang |
| Abstract | In image captioning, the typical attention mechanisms are arduous to identify the equivalent visual signals especially when predicting highly abstract words. This phenomenon is known as the semantic gap between vision and language. This problem can be overcome by providing semantic attributes that are homologous to language. Thanks to the inherent recurrent nature and gated operating mechanism, Recurrent Neural Network (RNN) and its variants are the dominating architectures in image captioning. However, when designing elaborate attention mechanisms to integrate visual inputs and semantic attributes, RNN-like variants become unflexible due to their complexities. In this paper, we investigate a Transformer-based sequence modeling framework, built only with attention layers and feedforward layers. To bridge the semantic gap, we introduce EnTangled Attention (ETA) that enables the Transformer to exploit semantic and visual information simultaneously. Furthermore, Gated Bilateral Controller (GBC) is proposed to guide the interactions between the multimodal information. We name our model as ETA-Transformer. Remarkably, ETA-Transformer achieves state-of-the-art performance on the MSCOCO image captioning dataset. The ablation studies validate the improvements of our proposed modules. |
| Tasks | Image Captioning |
| Published | 2019-10-01 |
| URL | http://openaccess.thecvf.com/content_ICCV_2019/html/Li_Entangled_Transformer_for_Image_Captioning_ICCV_2019_paper.html |
| http://openaccess.thecvf.com/content_ICCV_2019/papers/Li_Entangled_Transformer_for_Image_Captioning_ICCV_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/entangled-transformer-for-image-captioning |
| Repo | |
| Framework | |
How Important is a Neuron
| Title | How Important is a Neuron |
| Authors | Kedar Dhamdhere, Mukund Sundararajan, Qiqi Yan |
| Abstract | The problem of attributing a deep network’s prediction to its input/base features is well-studied (cf. Simonyan et al. (2013)). We introduce the notion of conductance to extend the notion of attribution to understanding the importance of hidden units. Informally, the conductance of a hidden unit of a deep network is the flow of attribution via this hidden unit. We can use conductance to understand the importance of a hidden unit to the prediction for a specific input, or over a set of inputs. We justify conductance in multiple ways via a qualitative comparison with other methods, via some axiomatic results, and via an empirical evaluation based on a feature selection task. The empirical evaluations are done using the Inception network over ImageNet data, and a convolutinal network over text data. In both cases, we demonstrate the effectiveness of conductance in identifying interesting insights about the internal workings of these networks. |
| Tasks | Feature Selection |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SylKoo0cKm |
| https://openreview.net/pdf?id=SylKoo0cKm | |
| PWC | https://paperswithcode.com/paper/how-important-is-a-neuron-1 |
| Repo | |
| Framework | |
Give It a Shot: Few-shot Learning to Normalize ADR Mentions in Social Media Posts
| Title | Give It a Shot: Few-shot Learning to Normalize ADR Mentions in Social Media Posts |
| Authors | Emmanouil Manousogiannis, Sepideh Mesbah, Aless Bozzon, ro, Selene Baez, Robert Jan Sips |
| Abstract | This paper describes the system that team MYTOMORROWS-TU DELFT developed for the 2019 Social Media Mining for Health Applications (SMM4H) Shared Task 3, for the end-to-end normalization of ADR tweet mentions to their corresponding MEDDRA codes. For the first two steps, we reuse a state-of-the art approach, focusing our contribution on the final entity-linking step. For that we propose a simple Few-Shot learning approach, based on pre-trained word embeddings and data from the UMLS, combined with the provided training data. Our system (relaxed F1: 0.337-0.345) outperforms the average (relaxed F1 0.2972) of the participants in this task, demonstrating the potential feasibility of few-shot learning in the context of medical text normalization. |
| Tasks | Entity Linking, Few-Shot Learning, Word Embeddings |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3219/ |
| https://www.aclweb.org/anthology/W19-3219 | |
| PWC | https://paperswithcode.com/paper/give-it-a-shot-few-shot-learning-to-normalize |
| Repo | |
| Framework | |
Perception-Aware Point-Based Value Iteration for Partially Observable Markov Decision Processes
| Title | Perception-Aware Point-Based Value Iteration for Partially Observable Markov Decision Processes |
| Authors | Mahsa Ghasemi, Ufuk Topcu |
| Abstract | Partially observable Markov decision processes (POMDPs) are a widely-used framework to model decision-making with uncertainty about the environment and under stochastic outcome. In conventional POMDP models, the observations that the agent receives originate from fixed known distribution. However, in a variety of real-world scenarios the agent has an active role in its perception by selecting which observations to receive. Due to combinatorial nature of such selection process, it is computationally intractable to integrate the perception decision with the planning decision. To prevent such expansion of the action space, we propose a greedy strategy for observation selection that aims to minimize the uncertainty in state. We develop a novel point-based value iteration algorithm that incorporates the greedy strategy to achieve near-optimal uncertainty reduction for sampled belief points. This in turn enables the solver to efficiently approximate the reachable subspace of belief simplex by essentially separating computations related to perception from planning. Lastly, we implement the proposed solver and demonstrate its performance and computational advantage in a range of robotic scenarios where the robot simultaneously performs active perception and planning. |
| Tasks | Decision Making |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=S1lTg3RcFm |
| https://openreview.net/pdf?id=S1lTg3RcFm | |
| PWC | https://paperswithcode.com/paper/perception-aware-point-based-value-iteration |
| Repo | |
| Framework | |
Revisiting the Role of Feature Engineering for Compound Type Identification in Sanskrit
| Title | Revisiting the Role of Feature Engineering for Compound Type Identification in Sanskrit |
| Authors | S, Jivnesh han, Amrith Krishna, Pawan Goyal, Laxmidhar Behera |
| Abstract | |
| Tasks | Feature Engineering |
| Published | 2019-10-01 |
| URL | https://www.aclweb.org/anthology/W19-7503/ |
| https://www.aclweb.org/anthology/W19-7503 | |
| PWC | https://paperswithcode.com/paper/revisiting-the-role-of-feature-engineering |
| Repo | |
| Framework | |
Cross-Lingual Word Embeddings and the Structure of the Human Bilingual Lexicon
| Title | Cross-Lingual Word Embeddings and the Structure of the Human Bilingual Lexicon |
| Authors | Paola Merlo, Maria Andueza Rodriguez |
| Abstract | Research on the bilingual lexicon has uncovered fascinating interactions between the lexicons of the native language and of the second language in bilingual speakers. In particular, it has been found that the lexicon of the underlying native language affects the organisation of the second language. In the spirit of interpreting current distributed representations, this paper investigates two models of cross-lingual word embeddings, comparing them to the shared-translation effect and the cross-lingual coactivation effects of false and true friends (cognates) found in humans. We find that the similarity structure of the cross-lingual word embeddings space yields the same effects as the human bilingual lexicon. |
| Tasks | Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1011/ |
| https://www.aclweb.org/anthology/K19-1011 | |
| PWC | https://paperswithcode.com/paper/cross-lingual-word-embeddings-and-the |
| Repo | |
| Framework | |
Learning Conceptual Spaces with Disentangled Facets
| Title | Learning Conceptual Spaces with Disentangled Facets |
| Authors | Rana Alshaikh, Zied Bouraoui, Steven Schockaert |
| Abstract | Conceptual spaces are geometric representations of meaning that were proposed by G ̈ardenfors (2000). They share many similarities with the vector space embeddings that are commonly used in natural language processing. However, rather than representing entities in a single vector space, conceptual spaces are usually decomposed into several facets, each of which is then modelled as a relatively low dimensional vector space. Unfortunately, the problem of learning such conceptual spaces has thus far only received limited attention. To address this gap, we analyze how, and to what extent, a given vector space embedding can be decomposed into meaningful facets in an unsupervised fashion. While this problem is highly challenging, we show that useful facets can be discovered by relying on word embeddings to group semantically related features. |
| Tasks | Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1013/ |
| https://www.aclweb.org/anthology/K19-1013 | |
| PWC | https://paperswithcode.com/paper/learning-conceptual-spaces-with-disentangled |
| Repo | |
| Framework | |
Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data
| Title | Cost-Sensitive BERT for Generalisable Sentence Classification on Imbalanced Data |
| Authors | Harish Tayyar Madabushi, Elena Kochkina, Michael Castelle |
| Abstract | The automatic identification of propaganda has gained significance in recent years due to technological and social changes in the way news is generated and consumed. That this task can be addressed effectively using BERT, a powerful new architecture which can be fine-tuned for text classification tasks, is not surprising. However, propaganda detection, like other tasks that deal with news documents and other forms of decontextualized social communication (e.g. sentiment analysis), inherently deals with data whose categories are simultaneously imbalanced and dissimilar. We show that BERT, while capable of handling imbalanced classes with no additional data augmentation, does not generalise well when the training and test data are sufficiently dissimilar (as is often the case with news sources, whose topics evolve over time). We show how to address this problem by providing a statistical measure of similarity between datasets and a method of incorporating cost-weighting into BERT when the training and test sets are dissimilar. We test these methods on the Propaganda Techniques Corpus (PTC) and achieve the second highest score on sentence-level propaganda classification. |
| Tasks | Data Augmentation, Sentence Classification, Sentiment Analysis, Text Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5018/ |
| https://www.aclweb.org/anthology/D19-5018 | |
| PWC | https://paperswithcode.com/paper/cost-sensitive-bert-for-generalisable |
| Repo | |
| Framework | |
