Paper Group NANR 118
NLProlog: Reasoning with Weak Unification for Natural Language Question Answering. Calibration of neural network logit vectors to combat adversarial attacks. Ada-Boundary: Accelerating the DNN Training via Adaptive Boundary Batch Selection. A Fine-Grained Annotated Multi-Dialectal Arabic Corpus. Towards a Unified End-to-End Approach for Fully Unsup …
NLProlog: Reasoning with Weak Unification for Natural Language Question Answering
| Title | NLProlog: Reasoning with Weak Unification for Natural Language Question Answering |
| Authors | Leon Weber, Pasquale Minervini, Ulf Leser, Tim Rocktäschel |
| Abstract | Symbolic logic allows practitioners to build systems that perform rule-based reasoning which is interpretable and which can easily be augmented with prior knowledge. However, such systems are traditionally difficult to apply to problems involving natural language due to the large linguistic variability of language. Currently, most work in natural language processing focuses on neural networks which learn distributed representations of words and their composition, thereby performing well in the presence of large linguistic variability. We propose to reap the benefits of both approaches by applying a combination of neural networks and logic programming to natural language question answering. We propose to employ an external, non-differentiable Prolog prover which utilizes a similarity function over pretrained sentence encoders. We fine-tune these representations via Evolution Strategies with the goal of multi-hop reasoning on natural language. This allows us to create a system that can apply rule-based reasoning to natural language and induce domain-specific natural language rules from training data. We evaluate the proposed system on two different question answering tasks, showing that it complements two very strong baselines – BIDAF (Seo et al., 2016a) and FASTQA (Weissenborn et al.,2017) – and outperforms both when used in an ensemble. |
| Tasks | Question Answering |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=ByfXe2C5tm |
| https://openreview.net/pdf?id=ByfXe2C5tm | |
| PWC | https://paperswithcode.com/paper/nlprolog-reasoning-with-weak-unification-for |
| Repo | |
| Framework | |
Calibration of neural network logit vectors to combat adversarial attacks
| Title | Calibration of neural network logit vectors to combat adversarial attacks |
| Authors | Oliver Goldstein |
| Abstract | Adversarial examples remain an issue for contemporary neural networks. This paper draws on Background Check (Perello-Nieto et al., 2016), a technique in model calibration, to assist two-class neural networks in detecting adversarial examples, using the one dimensional difference between logit values as the underlying measure. This method interestingly tends to achieve the highest average recall on image sets that are generated with large perturbation vectors, which is unlike the existing literature on adversarial attacks (Cubuk et al., 2017). The proposed method does not need knowledge of the attack parameters or methods at training time, unlike a great deal of the literature that uses deep learning based methods to detect adversarial examples, such as Metzen et al. (2017), imbuing the proposed method with additional flexibility. |
| Tasks | Calibration |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=Bkxdqj0cFQ |
| https://openreview.net/pdf?id=Bkxdqj0cFQ | |
| PWC | https://paperswithcode.com/paper/calibration-of-neural-network-logit-vectors |
| Repo | |
| Framework | |
Ada-Boundary: Accelerating the DNN Training via Adaptive Boundary Batch Selection
| Title | Ada-Boundary: Accelerating the DNN Training via Adaptive Boundary Batch Selection |
| Authors | Hwanjun Song, Sundong Kim, Minseok Kim, Jae-Gil Lee |
| Abstract | Neural networks can converge faster with help from a smarter batch selection strategy. In this regard, we propose Ada-Boundary, a novel adaptive-batch selection algorithm that constructs an effective mini-batch according to the learning progress of the model.Our key idea is to present confusing samples what the true label is. Thus, the samples near the current decision boundary are considered as the most effective to expedite convergence. Taking advantage of our design, Ada-Boundary maintains its dominance in various degrees of training difficulty. We demonstrate the advantage of Ada-Boundary by extensive experiments using two convolutional neural networks for three benchmark data sets. The experiment results show that Ada-Boundary improves the training time by up to 31.7% compared with the state-of-the-art strategy and by up to 33.5% compared with the baseline strategy. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SyfXKoRqFQ |
| https://openreview.net/pdf?id=SyfXKoRqFQ | |
| PWC | https://paperswithcode.com/paper/ada-boundary-accelerating-the-dnn-training |
| Repo | |
| Framework | |
A Fine-Grained Annotated Multi-Dialectal Arabic Corpus
| Title | A Fine-Grained Annotated Multi-Dialectal Arabic Corpus |
| Authors | Anis Charfi, Wajdi Zaghouani, Syed Hassan Mehdi, Esraa Mohamed |
| Abstract | We present ARAP-Tweet 2.0, a corpus of 5 million dialectal Arabic tweets and 50 million words of about 3000 Twitter users from 17 Arab countries. Compared to the first version, the new corpus has significant improvements in terms of the data volume and the annotation quality. It is fully balanced with respect to dialect, gender, and three age groups: under 25 years, between 25 and 34, and 35 years and above. This paper describes the process of creating the corpus starting from gathering the dialectal phrases to find the users, to annotating their accounts and retrieving their tweets. We also report on the evaluation of the annotation quality using the inter-annotator agreement measures which were applied to the whole corpus and not just a subset. The obtained results were substantial with average Cohen{'}s Kappa values of 0.99, 0.92, and 0.88 for the annotation of gender, dialect, and age respectively. We also discuss some challenges encountered when developing this corpus.s. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1023/ |
| https://www.aclweb.org/anthology/R19-1023 | |
| PWC | https://paperswithcode.com/paper/a-fine-grained-annotated-multi-dialectal |
| Repo | |
| Framework | |
Towards a Unified End-to-End Approach for Fully Unsupervised Cross-Lingual Sentiment Analysis
| Title | Towards a Unified End-to-End Approach for Fully Unsupervised Cross-Lingual Sentiment Analysis |
| Authors | Yanlin Feng, Xiaojun Wan |
| Abstract | Sentiment analysis in low-resource languages suffers from the lack of training data. Cross-lingual sentiment analysis (CLSA) aims to improve the performance on these languages by leveraging annotated data from other languages. Recent studies have shown that CLSA can be performed in a fully unsupervised manner, without exploiting either target language supervision or cross-lingual supervision. However, these methods rely heavily on unsupervised cross-lingual word embeddings (CLWE), which has been shown to have serious drawbacks on distant language pairs (e.g. English - Japanese). In this paper, we propose an end-to-end CLSA model by leveraging unlabeled data in multiple languages and multiple domains and eliminate the need for unsupervised CLWE. Our model applies to two CLSA settings: the traditional cross-lingual in-domain setting and the more challenging cross-lingual cross-domain setting. We empirically evaluate our approach on the multilingual multi-domain Amazon review dataset. Experimental results show that our model outperforms the baselines by a large margin despite its minimal resource requirement. |
| Tasks | Sentiment Analysis, Word Embeddings |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1097/ |
| https://www.aclweb.org/anthology/K19-1097 | |
| PWC | https://paperswithcode.com/paper/towards-a-unified-end-to-end-approach-for |
| Repo | |
| Framework | |
Beyond Games: Bringing Exploration to Robots in Real-world
| Title | Beyond Games: Bringing Exploration to Robots in Real-world |
| Authors | Deepak Pathak, Dhiraj Gandhi, Abhinav Gupta |
| Abstract | Exploration has been a long standing problem in both model-based and model-free learning methods for sensorimotor control. While there has been major advances over the years, most of these successes have been demonstrated in either video games or simulation environments. This is primarily because the rewards (even the intrinsic ones) are non-differentiable since they are function of the environment (which is a black-box). In this paper, we focus on the policy optimization aspect of the intrinsic reward function. Specifically, by using a local approximation, we formulate intrinsic reward as a differentiable function so as to perform policy optimization using likelihood maximization – much like supervised learning instead of reinforcement learning. This leads to a significantly sample efficient exploration policy. Our experiments clearly show that our approach outperforms both on-policy and off-policy optimization approaches like REINFORCE and DQN respectively. But most importantly, we are able to implement an exploration policy on a robot which learns to interact with objects completely from scratch just using data collected via the differentiable exploration module. See project videos at https://doubleblindICLR.github.io/robot-exploration/ |
| Tasks | Efficient Exploration |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=SkzeJ3A9F7 |
| https://openreview.net/pdf?id=SkzeJ3A9F7 | |
| PWC | https://paperswithcode.com/paper/beyond-games-bringing-exploration-to-robots |
| Repo | |
| Framework | |
Towards Actual (Not Operational) Textual Style Transfer Auto-Evaluation
| Title | Towards Actual (Not Operational) Textual Style Transfer Auto-Evaluation |
| Authors | Richard Yuanzhe Pang |
| Abstract | Regarding the problem of automatically generating paraphrases with modified styles or attributes, the difficulty lies in the lack of parallel corpora. Numerous advances have been proposed for the generation. However, significant problems remain with the auto-evaluation of style transfer tasks. Based on the summary of Pang and Gimpel (2018) and Mir et al. (2019), style transfer evaluations rely on three metrics: post-transfer style classification accuracy, content or semantic similarity, and naturalness or fluency. We elucidate the dangerous current state of style transfer auto-evaluation research. Moreover, we propose ways to aggregate the three metrics into one evaluator. This abstract aims to bring researchers to think about the future of style transfer and style transfer evaluation research. |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Style Transfer |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-5557/ |
| https://www.aclweb.org/anthology/D19-5557 | |
| PWC | https://paperswithcode.com/paper/towards-actual-not-operational-textual-style |
| Repo | |
| Framework | |
LasigeBioTM at MEDIQA 2019: Biomedical Question Answering using Bidirectional Transformers and Named Entity Recognition
| Title | LasigeBioTM at MEDIQA 2019: Biomedical Question Answering using Bidirectional Transformers and Named Entity Recognition |
| Authors | Andre Lamurias, Francisco M Couto |
| Abstract | Biomedical Question Answering (QA) aims at providing automated answers to user questions, regarding a variety of biomedical topics. For example, these questions may ask for related to diseases, drugs, symptoms, or medical procedures. Automated biomedical QA systems could improve the retrieval of information necessary to answer these questions. The MEDIQA challenge consisted of three tasks concerning various aspects of biomedical QA. This challenge aimed at advancing approaches to Natural Language Inference (NLI) and Recognizing Question Entailment (RQE), which would then result in enhanced approaches to biomedical QA. Our approach explored a common Transformer-based architecture that could be applied to each task. This approach shared the same pre-trained weights, but which were then fine-tuned for each task using the provided training data. Furthermore, we augmented the training data with external datasets and enriched the question and answer texts using MER, a named entity recognition tool. Our approach obtained high levels of accuracy, in particular on the NLI task, which classified pairs of text according to their relation. For the QA task, we obtained higher Spearman{'}s rank correlation values using the entities recognized by MER. |
| Tasks | Named Entity Recognition, Natural Language Inference, Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5057/ |
| https://www.aclweb.org/anthology/W19-5057 | |
| PWC | https://paperswithcode.com/paper/lasigebiotm-at-mediqa-2019-biomedical |
| Repo | |
| Framework | |
Measuring the Value of Linguistics: A Case Study from St. Lawrence Island Yupik
| Title | Measuring the Value of Linguistics: A Case Study from St. Lawrence Island Yupik |
| Authors | Emily Chen |
| Abstract | The adaptation of neural approaches to NLP is a landmark achievement that has called into question the utility of linguistics in the development of computational systems. This research proposal consequently explores this question in the context of a neural morphological analyzer for a polysynthetic language, St. Lawrence Island Yupik. It asks whether incorporating elements of Yupik linguistics into the implementation of the analyzer can improve performance, both in low-resource settings and in high-resource settings, where rich quantities of data are readily available. |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2004/ |
| https://www.aclweb.org/anthology/P19-2004 | |
| PWC | https://paperswithcode.com/paper/measuring-the-value-of-linguistics-a-case |
| Repo | |
| Framework | |
Towards Turkish Abstract Meaning Representation
| Title | Towards Turkish Abstract Meaning Representation |
| Authors | Zahra Azin, G{"u}l{\c{s}}en Eryi{\u{g}}it |
| Abstract | Using rooted, directed and labeled graphs, Abstract Meaning Representation (AMR) abstracts away from syntactic features such as word order and does not annotate every constituent in a sentence. AMR has been specified for English and was not supposed to be an Interlingua. However, several studies strived to overcome divergences in the annotations between English AMRs and those of their target languages by refining the annotation specification. Following this line of research, we have started to build the first Turkish AMR corpus by hand-annotating 100 sentences of the Turkish translation of the novel {``}The Little Prince{''} and comparing the results with the English AMRs available for the same corpus. The next step is to prepare the Turkish AMR annotation specification for training future annotators. | |
| Tasks | |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-2006/ |
| https://www.aclweb.org/anthology/P19-2006 | |
| PWC | https://paperswithcode.com/paper/towards-turkish-abstract-meaning |
| Repo | |
| Framework | |
DUT-NLP at MEDIQA 2019: An Adversarial Multi-Task Network to Jointly Model Recognizing Question Entailment and Question Answering
| Title | DUT-NLP at MEDIQA 2019: An Adversarial Multi-Task Network to Jointly Model Recognizing Question Entailment and Question Answering |
| Authors | Huiwei Zhou, Xuefei Li, Weihong Yao, Chengkun Lang, Shixian Ning |
| Abstract | In this paper, we propose a novel model called Adversarial Multi-Task Network (AMTN) for jointly modeling Recognizing Question Entailment (RQE) and medical Question Answering (QA) tasks. AMTN utilizes a pre-trained BioBERT model and an Interactive Transformer to learn the shared semantic representations across different task through parameter sharing mechanism. Meanwhile, an adversarial training strategy is introduced to separate the private features of each task from the shared representations. Experiments on BioNLP 2019 RQE and QA Shared Task datasets show that our model benefits from the shared representations of both tasks provided by multi-task learning and adversarial training, and obtains significant improvements upon the single-task models. |
| Tasks | Multi-Task Learning, Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5046/ |
| https://www.aclweb.org/anthology/W19-5046 | |
| PWC | https://paperswithcode.com/paper/dut-nlp-at-mediqa-2019-an-adversarial-multi |
| Repo | |
| Framework | |
DUT-BIM at MEDIQA 2019: Utilizing Transformer Network and Medical Domain-Specific Contextualized Representations for Question Answering
| Title | DUT-BIM at MEDIQA 2019: Utilizing Transformer Network and Medical Domain-Specific Contextualized Representations for Question Answering |
| Authors | Huiwei Zhou, Bizun Lei, Zhe Liu, Zhuang Liu |
| Abstract | In medical domain, given a medical question, it is difficult to manually select the most relevant information from a large number of search results. BioNLP 2019 proposes Question Answering (QA) task, which encourages the use of text mining technology to automatically judge whether a search result is an answer to the medical question. The main challenge of QA task is how to mine the semantic relation between question and answer. We propose BioBERT Transformer model to tackle this challenge, which applies Transformers to extract semantic relation between different words in questions and answers. Furthermore, BioBERT is utilized to encode medical domain-specific contextualized word representations. Our method has reached the accuracy of 76.24{%} and spearman of 17.12{%} on the BioNLP 2019 QA task. |
| Tasks | Question Answering |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5047/ |
| https://www.aclweb.org/anthology/W19-5047 | |
| PWC | https://paperswithcode.com/paper/dut-bim-at-mediqa-2019-utilizing-transformer |
| Repo | |
| Framework | |
Proceedings of the 2019 Workshop on Widening NLP
| Title | Proceedings of the 2019 Workshop on Widening NLP |
| Authors | |
| Abstract | |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-3600/ |
| https://www.aclweb.org/anthology/W19-3600 | |
| PWC | https://paperswithcode.com/paper/proceedings-of-the-2019-workshop-on-widening |
| Repo | |
| Framework | |
Convolutional Recurrent Network for Road Boundary Extraction
| Title | Convolutional Recurrent Network for Road Boundary Extraction |
| Authors | Justin Liang, Namdar Homayounfar, Wei-Chiu Ma, Shenlong Wang, Raquel Urtasun |
| Abstract | Creating high definition maps that contain precise information of static elements of the scene is of utmost importance for enabling self driving cars to drive safely. In this paper, we tackle the problem of drivable road boundary extraction from LiDAR and camera imagery. Towards this goal, we design a structured model where a fully convolutional network obtains deep features encoding the location and direction of road boundaries and then, a convolutional recurrent network outputs a polyline representation for each one of them. Importantly, our method is fully automatic and does not require a user in the loop. We showcase the effectiveness of our method on a large North American city where we obtain perfect topology of road boundaries 99.3% of the time at a high precision and recall. |
| Tasks | Self-Driving Cars |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Liang_Convolutional_Recurrent_Network_for_Road_Boundary_Extraction_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Liang_Convolutional_Recurrent_Network_for_Road_Boundary_Extraction_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/convolutional-recurrent-network-for-road |
| Repo | |
| Framework | |
A Self-Supervised Method for Mapping Human Instructions to Robot Policies
| Title | A Self-Supervised Method for Mapping Human Instructions to Robot Policies |
| Authors | Hsin-Wei Yu, Po-Yu Wu, Chih-An Tsao, You-An Shen, Shih-Hsuan Lin, Zhang-Wei Hong, Yi-Hsiang Chang, Chun-Yi Lee |
| Abstract | In this paper, we propose a modular approach which separates the instruction-to-action mapping procedure into two separate stages. The two stages are bridged via an intermediate representation called a goal, which stands for the result after a robot performs a specific task. The first stage maps an input instruction to a goal, while the second stage maps the goal to an appropriate policy selected from a set of robot policies. The policy is selected with an aim to guide the robot to reach the goal as close as possible. We implement the above two stages as a framework consisting of two distinct modules: an instruction-goal mapping module and a goal-policy mapping module. Given a human instruction in the evaluation phase, the instruction-goal mapping module first translates the instruction to a robot-interpretable goal. Once a goal is derived by the instruction-goal mapping module, the goal-policy mapping module then follows up to search through the goal-policy pairs to look for policy to be mapped by the instruction. Our experimental results show that the proposed method is able to learn an effective instruction-to-action mapping procedure in an environment with a given instruction set more efficiently than the baselines. In addition to the impressive data-efficiency, the results also show that our method can be adapted to a new instruction set and a new robot action space much faster than the baselines. The evidence suggests that our modular approach does lead to better adaptability and efficiency. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=BkgiM20cYX |
| https://openreview.net/pdf?id=BkgiM20cYX | |
| PWC | https://paperswithcode.com/paper/a-self-supervised-method-for-mapping-human |
| Repo | |
| Framework | |
