Paper Group NANR 100
Quasi Bidirectional Encoder Representations from Transformers for Word Sense Disambiguation. Text Classification with Few Examples using Controlled Generalization. RTM Stacking Results for Machine Translation Performance Prediction. Augmenting a De-identification System for Swedish Clinical Text Using Open Resources and Deep Learning. ARNOR: Attent …
Quasi Bidirectional Encoder Representations from Transformers for Word Sense Disambiguation
| Title | Quasi Bidirectional Encoder Representations from Transformers for Word Sense Disambiguation |
| Authors | Michele Bevilacqua, Roberto Navigli |
| Abstract | While contextualized embeddings have produced performance breakthroughs in many Natural Language Processing (NLP) tasks, Word Sense Disambiguation (WSD) has not benefited from them yet. In this paper, we introduce QBERT, a Transformer-based architecture for contextualized embeddings which makes use of a co-attentive layer to produce more deeply bidirectional representations, better-fitting for the WSD task. As a result, we are able to train a WSD system that beats the state of the art on the concatenation of all evaluation datasets by over 3 points, also outperforming a comparable model using ELMo. |
| Tasks | Word Sense Disambiguation |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1015/ |
| https://www.aclweb.org/anthology/R19-1015 | |
| PWC | https://paperswithcode.com/paper/quasi-bidirectional-encoder-representations |
| Repo | |
| Framework | |
Text Classification with Few Examples using Controlled Generalization
| Title | Text Classification with Few Examples using Controlled Generalization |
| Authors | Abhijit Mahabal, Jason Baldridge, Burcu Karagol Ayan, Vincent Perot, Dan Roth |
| Abstract | Training data for text classification is often limited in practice, especially for applications with many output classes or involving many related classification problems. This means classifiers must generalize from limited evidence, but the manner and extent of generalization is task dependent. Current practice primarily relies on pre-trained word embeddings to map words unseen in training to similar seen ones. Unfortunately, this squishes many components of meaning into highly restricted capacity. Our alternative begins with sparse pre-trained representations derived from unlabeled parsed corpora; based on the available training data, we select features that offers the relevant generalizations. This produces task-specific semantic vectors; here, we show that a feed-forward network over these vectors is especially effective in low-data scenarios, compared to existing state-of-the-art methods. By further pairing this network with a convolutional neural network, we keep this edge in low data scenarios and remain competitive when using full training sets. |
| Tasks | Text Classification, Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1319/ |
| https://www.aclweb.org/anthology/N19-1319 | |
| PWC | https://paperswithcode.com/paper/text-classification-with-few-examples-using |
| Repo | |
| Framework | |
RTM Stacking Results for Machine Translation Performance Prediction
| Title | RTM Stacking Results for Machine Translation Performance Prediction |
| Authors | Ergun Bi{\c{c}}ici |
| Abstract | We obtain new results using referential translation machines with increased number of learning models in the set of results that are stacked to obtain a better mixture of experts prediction. We combine features extracted from the word-level predictions with the sentence- or document-level features, which significantly improve the results on the training sets but decrease the test set results. |
| Tasks | Machine Translation |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5405/ |
| https://www.aclweb.org/anthology/W19-5405 | |
| PWC | https://paperswithcode.com/paper/rtm-stacking-results-for-machine-translation |
| Repo | |
| Framework | |
Augmenting a De-identification System for Swedish Clinical Text Using Open Resources and Deep Learning
| Title | Augmenting a De-identification System for Swedish Clinical Text Using Open Resources and Deep Learning |
| Authors | Hanna Berg, Hercules Dalianis |
| Abstract | |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-6502/ |
| https://www.aclweb.org/anthology/W19-6502 | |
| PWC | https://paperswithcode.com/paper/augmenting-a-de-identification-system-for |
| Repo | |
| Framework | |
ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification
| Title | ARNOR: Attention Regularization based Noise Reduction for Distant Supervision Relation Classification |
| Authors | Wei Jia, Dai Dai, Xinyan Xiao, Hua Wu |
| Abstract | Distant supervision is widely used in relation classification in order to create large-scale training data by aligning a knowledge base with an unlabeled corpus. However, it also introduces amounts of noisy labels where a contextual sentence actually does not express the labeled relation. In this paper, we propose ARNOR, a novel Attention Regularization based NOise Reduction framework for distant supervision relation classification. ARNOR assumes that a trustable relation label should be explained by the neural attention model. Specifically, our ARNOR framework iteratively learns an interpretable model and utilizes it to select trustable instances. We first introduce attention regularization to force the model to pay attention to the patterns which explain the relation labels, so as to make the model more interpretable. Then, if the learned model can clearly locate the relation patterns of a candidate instance in the training set, we will select it as a trustable instance for further training step. According to the experiments on NYT data, our ARNOR framework achieves significant improvements over state-of-the-art methods in both relation classification performance and noise reduction effect. |
| Tasks | Relation Classification |
| Published | 2019-07-01 |
| URL | https://www.aclweb.org/anthology/P19-1135/ |
| https://www.aclweb.org/anthology/P19-1135 | |
| PWC | https://paperswithcode.com/paper/arnor-attention-regularization-based-noise |
| Repo | |
| Framework | |
UniformFace: Learning Deep Equidistributed Representation for Face Recognition
| Title | UniformFace: Learning Deep Equidistributed Representation for Face Recognition |
| Authors | Yueqi Duan, Jiwen Lu, Jie Zhou |
| Abstract | In this paper, we propose a new supervision objective named uniform loss to learn deep equidistributed representations for face recognition. Most existing methods aim to learn discriminative face features, encouraging large inter-class distances and small intra-class variations. However, they ignore the distribution of faces in the holistic feature space, which may lead to severe locality and unbalance. With the prior that faces lie on a hypersphere manifold, we impose an equidistributed constraint by uniformly spreading the class centers on the manifold, so that the minimum distance between class centers can be maximized through complete exploitation of the feature space. To this end, we consider the class centers as like charges on the surface of hypersphere with inter-class repulsion, and minimize the total electric potential energy as the uniform loss. Extensive experimental results on the MegaFace Challenge I, IARPA Janus Benchmark A (IJB-A), Youtube Faces (YTF) and Labeled Faces in the Wild (LFW) datasets show the effectiveness of the proposed uniform loss. |
| Tasks | Face Recognition |
| Published | 2019-06-01 |
| URL | http://openaccess.thecvf.com/content_CVPR_2019/html/Duan_UniformFace_Learning_Deep_Equidistributed_Representation_for_Face_Recognition_CVPR_2019_paper.html |
| http://openaccess.thecvf.com/content_CVPR_2019/papers/Duan_UniformFace_Learning_Deep_Equidistributed_Representation_for_Face_Recognition_CVPR_2019_paper.pdf | |
| PWC | https://paperswithcode.com/paper/uniformface-learning-deep-equidistributed |
| Repo | |
| Framework | |
CiTIUS-COLE at SemEval-2019 Task 5: Combining Linguistic Features to Identify Hate Speech Against Immigrants and Women on Multilingual Tweets
| Title | CiTIUS-COLE at SemEval-2019 Task 5: Combining Linguistic Features to Identify Hate Speech Against Immigrants and Women on Multilingual Tweets |
| Authors | Sattam Almatarneh, Pablo Gamallo, Francisco J. Ribadas Pena |
| Abstract | This article describes the strategy submitted by the CiTIUS-COLE team to SemEval 2019 Task 5, a task which consists of binary classi- fication where the system predicting whether a tweet in English or in Spanish is hateful against women or immigrants or not. The proposed strategy relies on combining linguis- tic features to improve the classifier{'}s perfor- mance. More precisely, the method combines textual and lexical features, embedding words with the bag of words in Term Frequency- Inverse Document Frequency (TF-IDF) repre- sentation. The system performance reaches about 81{%} F1 when it is applied to the training dataset, but its F1 drops to 36{%} on the official test dataset for the English and 64{%} for the Spanish language concerning the hate speech class |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/S19-2068/ |
| https://www.aclweb.org/anthology/S19-2068 | |
| PWC | https://paperswithcode.com/paper/citius-cole-at-semeval-2019-task-5-combining |
| Repo | |
| Framework | |
Relation Module for Non-Answerable Predictions on Reading Comprehension
| Title | Relation Module for Non-Answerable Predictions on Reading Comprehension |
| Authors | Kevin Huang, Yun Tang, Jing Huang, Xiaodong He, Bowen Zhou |
| Abstract | Machine reading comprehension (MRC) has attracted significant amounts of research attention recently, due to an increase of challenging reading comprehension datasets. In this paper, we aim to improve a MRC model{'}s ability to determine whether a question has an answer in a given context (e.g. the recently proposed SQuAD 2.0 task). The relation module consists of both semantic extraction and relational information. We first extract high level semantics as objects from both question and context with multi-head self-attentive pooling. These semantic objects are then passed to a relation network, which generates relationship scores for each object pair in a sentence. These scores are used to determine whether a question is non-answerable. We test the relation module on the SQuAD 2.0 dataset using both the BiDAF and BERT models as baseline readers. We obtain 1.8{%} gain of F1 accuracy on top of the BiDAF reader, and 1.0{%} on top of the BERT base model. These results show the effectiveness of our relation module on MRC. |
| Tasks | Machine Reading Comprehension, Reading Comprehension |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1070/ |
| https://www.aclweb.org/anthology/K19-1070 | |
| PWC | https://paperswithcode.com/paper/relation-module-for-non-answerable |
| Repo | |
| Framework | |
NJU Submissions for the WMT19 Quality Estimation Shared Task
| Title | NJU Submissions for the WMT19 Quality Estimation Shared Task |
| Authors | Hou Qi |
| Abstract | In this paper, we describe the submissions of the team from Nanjing University for the WMT19 sentence-level Quality Estimation (QE) shared task on English-German language pair. We develop two approaches based on a two-stage neural QE model consisting of a feature extractor and a quality estimator. More specifically, one of the proposed approaches employs the translation knowledge between the two languages from two different translation directions; while the other one employs extra monolingual knowledge from both source and target sides, obtained by pre-training deep self-attention networks. To efficiently train these two-stage models, a joint learning training method is applied. Experiments show that the ensemble model of the above two models achieves the best results on the benchmark dataset of the WMT17 sentence-level QE shared task and obtains competitive results in WMT19, ranking 3rd out of 10 submissions. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5409/ |
| https://www.aclweb.org/anthology/W19-5409 | |
| PWC | https://paperswithcode.com/paper/nju-submissions-for-the-wmt19-quality |
| Repo | |
| Framework | |
A Scalable Method for Quantifying the Role of Pitch in Conversational Turn-Taking
| Title | A Scalable Method for Quantifying the Role of Pitch in Conversational Turn-Taking |
| Authors | Kornel Laskowski, Marcin Wlodarczak, Mattias Heldner |
| Abstract | Pitch has long been held as an important signalling channel when planning and deploying speech in conversation, and myriad studies have been undertaken to determine the extent to which it actually plays this role. Unfortunately, these studies have required considerable human investment in data preparation and analysis, and have therefore often been limited to a handful of specific conversational contexts. The current article proposes a framework which addresses these limitations, by enabling a scalable, quantitative characterization of the role of pitch throughout an entire conversation, requiring only the raw signal and speech activity references. The framework is evaluated on the Switchboard dialogue corpus. Experiments indicate that pitch trajectories of both parties are predictive of their incipient speech activity; that pitch should be expressed on a logarithmic scale and Z-normalized, as well as accompanied by a binary voicing variable; and that only the most recent 400 ms of the pitch trajectory are useful in incipient speech activity prediction. |
| Tasks | Activity Prediction |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/W19-5934/ |
| https://www.aclweb.org/anthology/W19-5934 | |
| PWC | https://paperswithcode.com/paper/a-scalable-method-for-quantifying-the-role-of |
| Repo | |
| Framework | |
Adaptive Sample-space & Adaptive Probability coding: a neural-network based approach for compression
| Title | Adaptive Sample-space & Adaptive Probability coding: a neural-network based approach for compression |
| Authors | Ken Nakanishi, Shin-ichi Maeda, Takeru Miyato, Masanori Koyama |
| Abstract | We propose Adaptive Sample-space & Adaptive Probability (ASAP) coding, an efficient neural-network based method for lossy data compression. Our ASAP coding distinguishes itself from the conventional method based on adaptive arithmetic coding in that it models the probability distribution for the quantization process in such a way that one can conduct back-propagation for the quantization width that determines the support of the distribution. Our ASAP also trains the model with a novel, hyper-parameter free multiplicative loss for the rate-distortion tradeoff. With our ASAP encoder, we are able to compress the image files in the Kodak dataset to as low as one fifth the size of the JPEG-compressed image without compromising their visual quality, and achieved the state-of-the-art result in terms of MS-SSIM based rate-distortion tradeoff. |
| Tasks | Quantization |
| Published | 2019-05-01 |
| URL | https://openreview.net/forum?id=HkzNXhC9KQ |
| https://openreview.net/pdf?id=HkzNXhC9KQ | |
| PWC | https://paperswithcode.com/paper/adaptive-sample-space-adaptive-probability |
| Repo | |
| Framework | |
YiSi - a Unified Semantic MT Quality Evaluation and Estimation Metric for Languages with Different Levels of Available Resources
| Title | YiSi - a Unified Semantic MT Quality Evaluation and Estimation Metric for Languages with Different Levels of Available Resources |
| Authors | Chi-kiu Lo |
| Abstract | We present YiSi, a unified automatic semantic machine translation quality evaluation and estimation metric for languages with different levels of available resources. Underneath the interface with different language resources settings, YiSi uses the same representation for the two sentences in assessment. Besides, we show significant improvement in the correlation of YiSi-1{'}s scores with human judgment is made by using contextual embeddings in multilingual BERT{–}Bidirectional Encoder Representations from Transformers to evaluate lexical semantic similarity. YiSi is open source and publicly available. |
| Tasks | Machine Translation, Semantic Similarity, Semantic Textual Similarity |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-5358/ |
| https://www.aclweb.org/anthology/W19-5358 | |
| PWC | https://paperswithcode.com/paper/yisi-a-unified-semantic-mt-quality-evaluation |
| Repo | |
| Framework | |
Porting Multilingual Morphological Resources to OntoLex-Lemon
| Title | Porting Multilingual Morphological Resources to OntoLex-Lemon |
| Authors | Thierry Declerck, Stefania Racioppa |
| Abstract | We describe work consisting in porting various morphological resources to the OntoLex-Lemon model. A main objective of this work is to offer a uniform representation of different morphological data sets in order to be able to compare and interlink multilingual resources and to cross-check and interlink or merge the content of morphological resources of one and the same language. The results of our work will be published on the Linguistic Linked Open Data cloud. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1027/ |
| https://www.aclweb.org/anthology/R19-1027 | |
| PWC | https://paperswithcode.com/paper/porting-multilingual-morphological-resources |
| Repo | |
| Framework | |
Redcoat: A Collaborative Annotation Tool for Hierarchical Entity Typing
| Title | Redcoat: A Collaborative Annotation Tool for Hierarchical Entity Typing |
| Authors | Michael Stewart, Wei Liu, Rachel Cardell-Oliver |
| Abstract | We introduce Redcoat, a web-based annotation tool that supports collaborative hierarchical entity typing. As an annotation tool, Redcoat also facilitates knowledge elicitation by allowing the creation and continuous refinement of concept hierarchies during annotation. It aims to minimise not only annotation time but the time it takes for project creators to set up and distribute projects to annotators. Projects created using the web-based interface can be rapidly distributed to a list of email addresses. Redcoat handles the propagation of documents amongst annotators and automatically scales the annotation workload depending on the number of active annotators. In this paper we discuss these key features and outline Redcoat{'}s system architecture. We also highlight Redcoat{'}s unique benefits over existing annotation tools via a qualitative comparison. |
| Tasks | Entity Typing |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-3033/ |
| https://www.aclweb.org/anthology/D19-3033 | |
| PWC | https://paperswithcode.com/paper/redcoat-a-collaborative-annotation-tool-for |
| Repo | |
| Framework | |
Grammatical-Error-Aware Incorrect Example Retrieval System for Learners of Japanese as a Second Language
| Title | Grammatical-Error-Aware Incorrect Example Retrieval System for Learners of Japanese as a Second Language |
| Authors | Mio Arai, Masahiro Kaneko, Mamoru Komachi |
| Abstract | Existing example retrieval systems do not include grammatically incorrect examples or present only a few examples, if any. Even if a retrieval system has a wide coverage of incorrect examples along with the correct counterpart, learners need to know whether their query includes errors or not. Considering the usability of retrieving incorrect examples, our proposed method uses a large-scale corpus and presents correct expressions along with incorrect expressions using a grammatical error detection system so that the learner do not need to be aware of how to search for the examples. Intrinsic and extrinsic evaluations indicate that our method improves accuracy of example sentence retrieval and quality of learner{'}s writing. |
| Tasks | Grammatical Error Detection |
| Published | 2019-08-01 |
| URL | https://www.aclweb.org/anthology/W19-4431/ |
| https://www.aclweb.org/anthology/W19-4431 | |
| PWC | https://paperswithcode.com/paper/grammatical-error-aware-incorrect-example |
| Repo | |
| Framework | |
