Paper Group NANR 169
SemEval-2018 Task 10: Capturing Discriminative Attributes. Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models. Trapping Light for Time of Flight. Automatically Generating Questions about Novel Metaphors in Literature. Decoding Strategies for Neural Referring Expression Generation. Unsupervised Detection of Metaph …
SemEval-2018 Task 10: Capturing Discriminative Attributes
| Title | SemEval-2018 Task 10: Capturing Discriminative Attributes |
| Authors | Alicia Krebs, Aless Lenci, ro, Denis Paperno |
| Abstract | This paper describes the SemEval 2018 Task 10 on Capturing Discriminative Attributes. Participants were asked to identify whether an attribute could help discriminate between two concepts. For example, a successful system should determine that {}urine{'} is a discriminating feature in the word pair {}kidney{'}, {`}bone{'}. The aim of the task is to better evaluate the capabilities of state of the art semantic models, beyond pure semantic similarity. The task attracted submissions from 21 teams, and the best system achieved a 0.75 F1 score. | |
| Tasks | Semantic Similarity, Semantic Textual Similarity, Word Sense Disambiguation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1117/ |
| https://www.aclweb.org/anthology/S18-1117 | |
| PWC | https://paperswithcode.com/paper/semeval-2018-task-10-capturing-discriminative |
| Repo | |
| Framework | |
Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models
| Title | Interpreting Word-Level Hidden State Behaviour of Character-Level LSTM Language Models |
| Authors | Avery Hiebert, Cole Peterson, Alona Fyshe, Nishant Mehta |
| Abstract | While Long Short-Term Memory networks (LSTMs) and other forms of recurrent neural network have been successfully applied to language modeling on a character level, the hidden state dynamics of these models can be difficult to interpret. We investigate the hidden states of such a model by using the HDBSCAN clustering algorithm to identify points in the text at which the hidden state is similar. Focusing on whitespace characters prior to the beginning of a word reveals interpretable clusters that offer insight into how the LSTM may combine contextual and character-level information to identify parts of speech. We also introduce a method for deriving word vectors from the hidden state representation in order to investigate the word-level knowledge of the model. These word vectors encode meaningful semantic information even for words that appear only once in the training text. |
| Tasks | Language Modelling, Word Embeddings |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5428/ |
| https://www.aclweb.org/anthology/W18-5428 | |
| PWC | https://paperswithcode.com/paper/interpreting-word-level-hidden-state |
| Repo | |
| Framework | |
Trapping Light for Time of Flight
| Title | Trapping Light for Time of Flight |
| Authors | Ruilin Xu, Mohit Gupta, Shree K. Nayar |
| Abstract | We propose a novel imaging method for near-complete, surround, 3D reconstruction of geometrically complex objects, in a single shot. The key idea is to augment a time-of-flight (ToF) based 3D sensor with a multi-mirror system, called a light-trap. The shape of the trap is chosen so that light rays entering it bounce multiple times inside the trap, thereby visiting every position inside the trap multiple times from various directions. We show via simulations that this enables light rays to reach more than 99.9% of the surface of objects placed inside the trap, even those with strong occlusions, for example, lattice-shaped objects. The ToF sensor provides the path length for each light ray, which, along with the known shape of the trap, is used to reconstruct the complete paths of all the rays. This enables performing dense, surround 3D reconstructions of objects with highly complex 3D shapes, in a single shot. We have developed a proof-of-concept hardware prototype consisting of a pulsed ToF sensor, and a light trap built with planar mirrors. We demonstrate the effectiveness of the light trap based 3D reconstruction method on a variety of objects with a broad range of geometry and reflectance properties. |
| Tasks | 3D Reconstruction |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Xu_Trapping_Light_for_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Xu_Trapping_Light_for_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/trapping-light-for-time-of-flight |
| Repo | |
| Framework | |
Automatically Generating Questions about Novel Metaphors in Literature
| Title | Automatically Generating Questions about Novel Metaphors in Literature |
| Authors | Natalie Parde, Rodney Nielsen |
| Abstract | The automatic generation of stimulating questions is crucial to the development of intelligent cognitive exercise applications. We developed an approach that generates appropriate \textit{Questioning the Author} queries based on novel metaphors in diverse syntactic relations in literature. We show that the generated questions are comparable to human-generated questions in terms of naturalness, sensibility, and depth, and score slightly higher than human-generated questions in terms of clarity. We also show that questions generated about novel metaphors are rated as cognitively deeper than questions generated about non- or conventional metaphors, providing evidence that metaphor novelty can be leveraged to promote cognitive exercise. |
| Tasks | Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6533/ |
| https://www.aclweb.org/anthology/W18-6533 | |
| PWC | https://paperswithcode.com/paper/automatically-generating-questions-about |
| Repo | |
| Framework | |
Decoding Strategies for Neural Referring Expression Generation
| Title | Decoding Strategies for Neural Referring Expression Generation |
| Authors | Sina Zarrie{\ss}, David Schlangen |
| Abstract | RNN-based sequence generation is now widely used in NLP and NLG (natural language generation). Most work focusses on how to train RNNs, even though also decoding is not necessarily straightforward: previous work on neural MT found seq2seq models to radically prefer short candidates, and has proposed a number of beam search heuristics to deal with this. In this work, we assess decoding strategies for referring expression generation with neural models. Here, expression length is crucial: output should neither contain too much or too little information, in order to be pragmatically adequate. We find that most beam search heuristics developed for MT do not generalize well to referring expression generation (REG), and do not generally outperform greedy decoding. We observe that beam search heuristics for termination seem to override the model{'}s knowledge of what a good stopping point is. Therefore, we also explore a recent approach called trainable decoding, which uses a small network to modify the RNN{'}s hidden state for better decoding results. We find this approach to consistently outperform greedy decoding for REG. |
| Tasks | Image Captioning, Machine Translation, Text Generation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6563/ |
| https://www.aclweb.org/anthology/W18-6563 | |
| PWC | https://paperswithcode.com/paper/decoding-strategies-for-neural-referring |
| Repo | |
| Framework | |
Unsupervised Detection of Metaphorical Adjective-Noun Pairs
| Title | Unsupervised Detection of Metaphorical Adjective-Noun Pairs |
| Authors | Malay Pramanick, Pabitra Mitra |
| Abstract | Metaphor is a popular figure of speech. Popularity of metaphors calls for their automatic identification and interpretation. Most of the unsupervised methods directed at detection of metaphors use some hand-coded knowledge. We propose an unsupervised framework for metaphor detection that does not require any hand-coded knowledge. We applied clustering on features derived from Adjective-Noun pairs for classifying them into two disjoint classes. We experimented with adjective-noun pairs of a popular dataset annotated for metaphors and obtained an accuracy of 72.87{%} with k-means clustering algorithm. |
| Tasks | Machine Translation, Word Sense Disambiguation |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0909/ |
| https://www.aclweb.org/anthology/W18-0909 | |
| PWC | https://paperswithcode.com/paper/unsupervised-detection-of-metaphorical |
| Repo | |
| Framework | |
Evaluating Grammaticality in Seq2seq Models with a Broad Coverage HPSG Grammar: A Case Study on Machine Translation
| Title | Evaluating Grammaticality in Seq2seq Models with a Broad Coverage HPSG Grammar: A Case Study on Machine Translation |
| Authors | Johnny Wei, Khiem Pham, Brendan O{'}Connor, Brian Dillon |
| Abstract | Sequence to sequence (seq2seq) models are often employed in settings where the target output is natural language. However, the syntactic properties of the language generated from these models are not well understood. We explore whether such output belongs to a formal and realistic grammar, by employing the English Resource Grammar (ERG), a broad coverage, linguistically precise HPSG-based grammar of English. From a French to English parallel corpus, we analyze the parseability and grammatical constructions occurring in output from a seq2seq translation model. Over 93{%} of the model translations are parseable, suggesting that it learns to generate conforming to a grammar. The model has trouble learning the distribution of rarer syntactic rules, and we pinpoint several constructions that differentiate translations between the references and our model. |
| Tasks | Machine Translation |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5432/ |
| https://www.aclweb.org/anthology/W18-5432 | |
| PWC | https://paperswithcode.com/paper/evaluating-grammaticality-in-seq2seq-models |
| Repo | |
| Framework | |
The NiuTrans Machine Translation System for WMT18
| Title | The NiuTrans Machine Translation System for WMT18 |
| Authors | Qiang Wang, Bei Li, Jiqiang Liu, Bojian Jiang, Zheyang Zhang, Yinqiao Li, Ye Lin, Tong Xiao, Jingbo Zhu |
| Abstract | This paper describes the submission of the NiuTrans neural machine translation system for the WMT 2018 Chinese ↔ English news translation tasks. Our baseline systems are based on the Transformer architecture. We further improve the translation performance 2.4-2.6 BLEU points from four aspects, including architectural improvements, diverse ensemble decoding, reranking, and post-processing. Among constrained submissions, we rank 2nd out of 16 submitted systems on Chinese → English task and 3rd out of 16 on English → Chinese task, respectively. |
| Tasks | Machine Translation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-6430/ |
| https://www.aclweb.org/anthology/W18-6430 | |
| PWC | https://paperswithcode.com/paper/the-niutrans-machine-translation-system-for |
| Repo | |
| Framework | |
How much should you ask? On the question structure in QA systems.
| Title | How much should you ask? On the question structure in QA systems. |
| Authors | Barbara Rychalska, Dominika Basaj, Anna Wr{'o}blewska, Przemyslaw Biecek |
| Abstract | Datasets that boosted state-of-the-art solutions for Question Answering (QA) systems prove that it is possible to ask questions in natural language manner. However, users are still used to query-like systems where they type in keywords to search for answer. In this study we validate which parts of questions are essential for obtaining valid answer. In order to conclude that, we take advantage of LIME - a framework that explains prediction by local approximation. We find that grammar and natural language is disregarded by QA. State-of-the-art model can answer properly even if {'}asked{'} only with a few words with high coefficients calculated with LIME. According to our knowledge, it is the first time that QA model is being explained by LIME. |
| Tasks | Question Answering |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-5435/ |
| https://www.aclweb.org/anthology/W18-5435 | |
| PWC | https://paperswithcode.com/paper/how-much-should-you-ask-on-the-question |
| Repo | |
| Framework | |
Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection
| Title | Geometric Constrained Joint Lane Segmentation and Lane Boundary Detection |
| Authors | Jie Zhang, Yi Xu, Bingbing Ni, Zhenyu Duan |
| Abstract | Lane detection is playing an indispensable role in advanced driver assistance systems. The existing approaches for lane detection can be categorized as lane area segmentation and lane boundary detection. Most of these methods abandon a great quantity of complementary information, such as geometric priors, when exploiting the lane area and the lane boundaries alternatively. In this paper, we establish a multiple-task learning framework to segment lane areas and detect lane boundaries simultaneously. The main contributions of the proposed frame- work are highlighted in two facets: (1) We put forward a multiple-task learning framework with mutually interlinked sub-structures between lane segmentation and lane boundary detection to improve overall performance. (2) A novel loss function is proposed with two geometric constraints considered, as assumed that the lane boundary is predicted as the outer contour of the lane area while the lane area is predicted as the area integration result within the lane boundary lines. With an end-to-end training process, these improvements extremely enhance the robustness and accuracy of our approach on several metrics. The proposed framework is evaluated on KITTI dataset, CULane dataset and RVD dataset. Compared with the state of the arts, our approach achieves the best performance on the metrics and a more robust detection in varied traffic scenes. |
| Tasks | Boundary Detection, Lane Detection |
| Published | 2018-09-01 |
| URL | http://openaccess.thecvf.com/content_ECCV_2018/html/Jie_Zhang_Geometric_Constrained_Joint_ECCV_2018_paper.html |
| http://openaccess.thecvf.com/content_ECCV_2018/papers/Jie_Zhang_Geometric_Constrained_Joint_ECCV_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/geometric-constrained-joint-lane-segmentation |
| Repo | |
| Framework | |
Same-language machine translation for local flavours/flavors
| Title | Same-language machine translation for local flavours/flavors |
| Authors | Gema Ram{'\i}rez-S{'a}nchez, Janice Campbell |
| Abstract | |
| Tasks | Machine Translation |
| Published | 2018-03-01 |
| URL | https://www.aclweb.org/anthology/W18-1908/ |
| https://www.aclweb.org/anthology/W18-1908 | |
| PWC | https://paperswithcode.com/paper/same-language-machine-translation-for-local |
| Repo | |
| Framework | |
Leveraging distributed representations and lexico-syntactic fixedness for token-level prediction of the idiomaticity of English verb-noun combinations
| Title | Leveraging distributed representations and lexico-syntactic fixedness for token-level prediction of the idiomaticity of English verb-noun combinations |
| Authors | Milton King, Paul Cook |
| Abstract | Verb-noun combinations (VNCs) - e.g., blow the whistle, hit the roof, and see stars - are a common type of English idiom that are ambiguous with literal usages. In this paper we propose and evaluate models for classifying VNC usages as idiomatic or literal, based on a variety of approaches to forming distributed representations. Our results show that a model based on averaging word embeddings performs on par with, or better than, a previously-proposed approach based on skip-thoughts. Idiomatic usages of VNCs are known to exhibit lexico-syntactic fixedness. We further incorporate this information into our models, demonstrating that this rich linguistic knowledge is complementary to the information carried by distributed representations. |
| Tasks | Machine Translation, Sentence Embeddings, Word Embeddings |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2055/ |
| https://www.aclweb.org/anthology/P18-2055 | |
| PWC | https://paperswithcode.com/paper/leveraging-distributed-representations-and |
| Repo | |
| Framework | |
Using pseudo-senses for improving the extraction of synonyms from word embeddings
| Title | Using pseudo-senses for improving the extraction of synonyms from word embeddings |
| Authors | Olivier Ferret |
| Abstract | The methods proposed recently for specializing word embeddings according to a particular perspective generally rely on external knowledge. In this article, we propose Pseudofit, a new method for specializing word embeddings according to semantic similarity without any external knowledge. Pseudofit exploits the notion of pseudo-sense for building several representations for each word and uses these representations for making the initial embeddings more generic. We illustrate the interest of Pseudofit for acquiring synonyms and study several variants of Pseudofit according to this perspective. |
| Tasks | Dimensionality Reduction, Semantic Similarity, Semantic Textual Similarity, Word Embeddings, Word Sense Disambiguation |
| Published | 2018-07-01 |
| URL | https://www.aclweb.org/anthology/P18-2056/ |
| https://www.aclweb.org/anthology/P18-2056 | |
| PWC | https://paperswithcode.com/paper/using-pseudo-senses-for-improving-the |
| Repo | |
| Framework | |
Discriminator at SemEval-2018 Task 10: Minimally Supervised Discrimination
| Title | Discriminator at SemEval-2018 Task 10: Minimally Supervised Discrimination |
| Authors | Artur Kulmizev, Mostafa Abdou, Vinit Ravishankar, Malvina Nissim |
| Abstract | We participated to the SemEval-2018 shared task on capturing discriminative attributes (Task 10) with a simple system that ranked 8th amongst the 26 teams that took part in the evaluation. Our final score was 0.67, which is competitive with the winning score of 0.75, particularly given that our system is a zero-shot system that requires no training and minimal parameter optimisation. In addition to describing the submitted system, and discussing the implications of the relative success of such a system on this task, we also report on other, more complex models we experimented with. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1167/ |
| https://www.aclweb.org/anthology/S18-1167 | |
| PWC | https://paperswithcode.com/paper/discriminator-at-semeval-2018-task-10 |
| Repo | |
| Framework | |
Achieving Strong Regularization for Deep Neural Networks
| Title | Achieving Strong Regularization for Deep Neural Networks |
| Authors | Dae Hoon Park, Chiu Man Ho, Yi Chang |
| Abstract | L1 and L2 regularizers are critical tools in machine learning due to their ability to simplify solutions. However, imposing strong L1 or L2 regularization with gradient descent method easily fails, and this limits the generalization ability of the underlying neural networks. To understand this phenomenon, we investigate how and why training fails for strong regularization. Specifically, we examine how gradients change over time for different regularization strengths and provide an analysis why the gradients diminish so fast. We find that there exists a tolerance level of regularization strength, where the learning completely fails if the regularization strength goes beyond it. We propose a simple but novel method, Delayed Strong Regularization, in order to moderate the tolerance level. Experiment results show that our proposed approach indeed achieves strong regularization for both L1 and L2 regularizers and improves both accuracy and sparsity on public data sets. Our source code is published. |
| Tasks | L2 Regularization |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=Bys_NzbC- |
| https://openreview.net/pdf?id=Bys_NzbC- | |
| PWC | https://paperswithcode.com/paper/achieving-strong-regularization-for-deep |
| Repo | |
| Framework | |
