Paper Group NANR 226
Semantic Matching of Documents from Heterogeneous Collections: A Simple and Transparent Method for Practical Applications. Leveraging Past References for Robust Language Grounding. Computational Syntax-Semantics Interface with Type-Theory of Acyclic Recursion for Underspecified Semantics. Text Similarity Estimation Based on Word Embeddings and Matr …
Semantic Matching of Documents from Heterogeneous Collections: A Simple and Transparent Method for Practical Applications
| Title | Semantic Matching of Documents from Heterogeneous Collections: A Simple and Transparent Method for Practical Applications |
| Authors | Mark-Christoph Mueller |
| Abstract | We present a very simple, unsupervised method for the pairwise matching of documents from heterogeneous collections. We demonstrate our method with the Concept-Project matching task, which is a binary classification task involving pairs of documents from heterogeneous collections. Although our method only employs standard resources without any domain- or task-specific modifications, it clearly outperforms the more complex system of the original authors. In addition, our method is transparent, because it provides explicit information about how a similarity score was computed, and efficient, because it is based on the aggregation of (pre-computable) word-level similarities. |
| Tasks | |
| Published | 2019-05-01 |
| URL | https://www.aclweb.org/anthology/W19-0804/ |
| https://www.aclweb.org/anthology/W19-0804 | |
| PWC | https://paperswithcode.com/paper/semantic-matching-of-documents-from-1 |
| Repo | |
| Framework | |
Leveraging Past References for Robust Language Grounding
| Title | Leveraging Past References for Robust Language Grounding |
| Authors | Subhro Roy, Michael Noseworthy, Rohan Paul, Daehyung Park, Nicholas Roy |
| Abstract | Grounding referring expressions to objects in an environment has traditionally been considered a one-off, ahistorical task. However, in realistic applications of grounding, multiple users will repeatedly refer to the same set of objects. As a result, past referring expressions for objects can provide strong signals for grounding subsequent referring expressions. We therefore reframe the grounding problem from the perspective of coreference detection and propose a neural network that detects when two expressions are referring to the same object. The network combines information from vision and past referring expressions to resolve which object is being referred to. Our experiments show that detecting referring expression coreference is an effective way to ground objects described by subtle visual properties, which standard visual grounding models have difficulty capturing. We also show the ability to detect object coreference allows the grounding model to perform well even when it encounters object categories not seen in the training data. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1040/ |
| https://www.aclweb.org/anthology/K19-1040 | |
| PWC | https://paperswithcode.com/paper/leveraging-past-references-for-robust |
| Repo | |
| Framework | |
Computational Syntax-Semantics Interface with Type-Theory of Acyclic Recursion for Underspecified Semantics
| Title | Computational Syntax-Semantics Interface with Type-Theory of Acyclic Recursion for Underspecified Semantics |
| Authors | Roussanka Loukanova |
| Abstract | |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/W19-1005/ |
| https://www.aclweb.org/anthology/W19-1005 | |
| PWC | https://paperswithcode.com/paper/computational-syntax-semantics-interface-with |
| Repo | |
| Framework | |
Text Similarity Estimation Based on Word Embeddings and Matrix Norms for Targeted Marketing
| Title | Text Similarity Estimation Based on Word Embeddings and Matrix Norms for Targeted Marketing |
| Authors | Tim vor der Br{"u}ck, Marc Pouly |
| Abstract | The prevalent way to estimate the similarity of two documents based on word embeddings is to apply the cosine similarity measure to the two centroids obtained from the embedding vectors associated with the words in each document. Motivated by an industrial application from the domain of youth marketing, where this approach produced only mediocre results, we propose an alternative way of combining the word vectors using matrix norms. The evaluation shows superior results for most of the investigated matrix norms in comparison to both the classical cosine measure and several other document similarity estimates. |
| Tasks | Word Embeddings |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-1181/ |
| https://www.aclweb.org/anthology/N19-1181 | |
| PWC | https://paperswithcode.com/paper/text-similarity-estimation-based-on-word |
| Repo | |
| Framework | |
Active Learning via Membership Query Synthesis for Semi-Supervised Sentence Classification
| Title | Active Learning via Membership Query Synthesis for Semi-Supervised Sentence Classification |
| Authors | Raphael Schumann, Ines Rehbein |
| Abstract | Active learning (AL) is a technique for reducing manual annotation effort during the annotation of training data for machine learning classifiers. For NLP tasks, pool-based and stream-based sampling techniques have been used to select new instances for AL while gen erating new, artificial instances via Membership Query Synthesis was, up to know, considered to be infeasible for NLP problems. We present the first successfull attempt to use Membership Query Synthesis for generating AL queries, using Variational Autoencoders for query generation. We evaluate our approach in a text classification task and demonstrate that query synthesis shows competitive performance to pool-based AL strategies while substantially reducing annotation time |
| Tasks | Active Learning, Sentence Classification, Text Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1044/ |
| https://www.aclweb.org/anthology/K19-1044 | |
| PWC | https://paperswithcode.com/paper/active-learning-via-membership-query |
| Repo | |
| Framework | |
Cluster-Gated Convolutional Neural Network for Short Text Classification
| Title | Cluster-Gated Convolutional Neural Network for Short Text Classification |
| Authors | Haidong Zhang, Wancheng Ni, Meijing Zhao, Ziqi Lin |
| Abstract | Text classification plays a crucial role for understanding natural language in a wide range of applications. Most existing approaches mainly focus on long text classification (e.g., blogs, documents, paragraphs). However, they cannot easily be applied to short text because of its sparsity and lack of context. In this paper, we propose a new model called cluster-gated convolutional neural network (CGCNN), which jointly explores word-level clustering and text classification in an end-to-end manner. Specifically, the proposed model firstly uses a bi-directional long short-term memory to learn word representations. Then, it leverages a soft clustering method to explore their semantic relation with the cluster centers, and takes linear transformation on text representations. It develops a cluster-dependent gated convolutional layer to further control the cluster-dependent feature flows. Experimental results on five commonly used datasets show that our model outperforms state-of-the-art models. |
| Tasks | Text Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/K19-1094/ |
| https://www.aclweb.org/anthology/K19-1094 | |
| PWC | https://paperswithcode.com/paper/cluster-gated-convolutional-neural-network |
| Repo | |
| Framework | |
Investigating Capsule Network and Semantic Feature on Hyperplanes for Text Classification
| Title | Investigating Capsule Network and Semantic Feature on Hyperplanes for Text Classification |
| Authors | Chunning Du, Haifeng Sun, Jingyu Wang, Qi Qi, Jianxin Liao, Chun Wang, Bing Ma |
| Abstract | As an essential component of natural language processing, text classification relies on deep learning in recent years. Various neural networks are designed for text classification on the basis of word embedding. However, polysemy is a fundamental feature of the natural language, which brings challenges to text classification. One polysemic word contains more than one sense, while the word embedding procedure conflates different senses of a polysemic word into a single vector. Extracting the distinct representation for the specific sense could thus lead to fine-grained models with strong generalization ability. It has been demonstrated that multiple senses of a word actually reside in linear superposition within the word embedding so that specific senses can be extracted from the original word embedding. Therefore, we propose to use capsule networks to construct the vectorized representation of semantics and utilize hyperplanes to decompose each capsule to acquire the specific senses. A novel dynamic routing mechanism named {`}routing-on-hyperplane{'} will select the proper sense for the downstream classification task. Our model is evaluated on 6 different datasets, and the experimental results show that our model is capable of extracting more discriminative semantic features and yields a significant performance gain compared to other baseline methods. | |
| Tasks | Text Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1043/ |
| https://www.aclweb.org/anthology/D19-1043 | |
| PWC | https://paperswithcode.com/paper/investigating-capsule-network-and-semantic |
| Repo | |
| Framework | |
Hierarchical Attention Prototypical Networks for Few-Shot Text Classification
| Title | Hierarchical Attention Prototypical Networks for Few-Shot Text Classification |
| Authors | Shengli Sun, Qingfeng Sun, Kevin Zhou, Tengchao Lv |
| Abstract | Most of the current effective methods for text classification tasks are based on large-scale labeled data and a great number of parameters, but when the supervised training data are few and difficult to be collected, these models are not available. In this work, we propose a hierarchical attention prototypical networks (HAPN) for few-shot text classification. We design the feature level, word level, and instance level multi cross attention for our model to enhance the expressive ability of semantic space, so it can highlight or weaken the importance of the features, words, and instances separately. We verify the effectiveness of our model on two standard benchmark few-shot text classification datasets{—}FewRel and CSID, and achieve the state-of-the-art performance. The visualization of hierarchical attention layers illustrates that our model can capture more important features, words, and instances. In addition, our attention mechanism increases support set augmentability and accelerates convergence speed in the training stage. |
| Tasks | Text Classification |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1045/ |
| https://www.aclweb.org/anthology/D19-1045 | |
| PWC | https://paperswithcode.com/paper/hierarchical-attention-prototypical-networks |
| Repo | |
| Framework | |
Unsupervised Compositionality Prediction of Nominal Compounds
| Title | Unsupervised Compositionality Prediction of Nominal Compounds |
| Authors | Silvio Cordeiro, Aline Villavicencio, Marco Idiart, Carlos Ramisch |
| Abstract | Nominal compounds such as red wine and nut case display a continuum of compositionality, with varying contributions from the components of the compound to its semantics. This article proposes a framework for compound compositionality prediction using distributional semantic models, evaluating to what extent they capture idiomaticity compared to human judgments. For evaluation, we introduce data sets containing human judgments in three languages: English, French, and Portuguese. The results obtained reveal a high agreement between the models and human predictions, suggesting that they are able to incorporate information about idiomaticity. We also present an in-depth evaluation of various factors that can affect prediction, such as model and corpus parameters and compositionality operations. General crosslingual analyses reveal the impact of morphological variation and corpus size in the ability of the model to predict compositionality, and of a uniform combination of the components for best results. |
| Tasks | |
| Published | 2019-03-01 |
| URL | https://www.aclweb.org/anthology/J19-1001/ |
| https://www.aclweb.org/anthology/J19-1001 | |
| PWC | https://paperswithcode.com/paper/unsupervised-compositionality-prediction-of |
| Repo | |
| Framework | |
Visualizing Inferred Morphotactic Systems
| Title | Visualizing Inferred Morphotactic Systems |
| Authors | Haley Lepp, Olga Zamaraeva, Emily M. Bender |
| Abstract | We present a web-based system that facilitates the exploration of complex morphological patterns found in morphologically very rich languages. The need for better understanding of such patterns is urgent for linguistics and important for cross-linguistically applicable natural language processing. In this paper we give an overview of the system architecture and describe a sample case study on Abui [abz], a Trans-New Guinea language spoken in Indonesia. |
| Tasks | |
| Published | 2019-06-01 |
| URL | https://www.aclweb.org/anthology/N19-4022/ |
| https://www.aclweb.org/anthology/N19-4022 | |
| PWC | https://paperswithcode.com/paper/visualizing-inferred-morphotactic-systems |
| Repo | |
| Framework | |
Resolving Pronouns for a Resource-Poor Language, Malayalam Using Resource-Rich Language, Tamil.
| Title | Resolving Pronouns for a Resource-Poor Language, Malayalam Using Resource-Rich Language, Tamil. |
| Authors | Sobha Lalitha Devi |
| Abstract | In this paper we give in detail how a resource rich language can be used for resolving pronouns for a less resource language. The source language, which is resource rich language in this study, is Tamil and the resource poor language is Malayalam, both belonging to the same language family, Dravidian. The Pronominal resolution developed for Tamil uses CRFs. Our approach is to leverage the Tamil language model to test Malayalam data and the processing required for Malayalam data is detailed. The similarity at the syntactic level between the languages is exploited in identifying the features for developing the Tamil language model. The word form or the lexical item is not considered as a feature for training the CRFs. Evaluation on Malayalam Wikipedia data shows that our approach is correct and the results, though not as good as Tamil, but comparable. |
| Tasks | Language Modelling |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1072/ |
| https://www.aclweb.org/anthology/R19-1072 | |
| PWC | https://paperswithcode.com/paper/resolving-pronouns-for-a-resource-poor |
| Repo | |
| Framework | |
Detecting Anorexia in Spanish Tweets
| Title | Detecting Anorexia in Spanish Tweets |
| Authors | Pilar L{'o}pez {'U}beda, Flor Miriam Plaza del Arco, Manuel Carlos D{'\i}az Galiano, L. Alfonso Urena Lopez, Maite Martin |
| Abstract | Mental health is one of the main concerns of today{'}s society. Early detection of symptoms can greatly help people with mental disorders. People are using social networks more and more to express emotions, sentiments and mental states. Thus, the treatment of this information using NLP technologies can be applied to the automatic detection of mental problems such as eating disorders. However, the first step to solving the problem should be to provide a corpus in order to evaluate our systems. In this paper, we specifically focus on detecting anorexia messages on Twitter. Firstly, we have generated a new corpus of tweets extracted from different accounts including anorexia and non-anorexia messages in Spanish. The corpus is called SAD: Spanish Anorexia Detection corpus. In order to validate the effectiveness of the SAD corpus, we also propose several machine learning approaches for automatically detecting anorexia symptoms in the corpus. The good results obtained show that the application of textual classification methods is a promising option for developing this kind of system demonstrating that these tools could be used by professionals to help in the early detection of mental problems. |
| Tasks | |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1077/ |
| https://www.aclweb.org/anthology/R19-1077 | |
| PWC | https://paperswithcode.com/paper/detecting-anorexia-in-spanish-tweets |
| Repo | |
| Framework | |
A Label Informative Wide & Deep Classifier for Patents and Papers
| Title | A Label Informative Wide & Deep Classifier for Patents and Papers |
| Authors | Muyao Niu, Jie Cai |
| Abstract | In this paper, we provide a simple and effective baseline for classifying both patents and papers to the well-established Cooperative Patent Classification (CPC). We propose a label-informative classifier based on the Wide {&} Deep structure, where the Wide part encodes string-level similarities between texts and labels, and the Deep part captures semantic-level similarities via non-linear transformations. Our model trains on millions of patents, and transfers to papers by developing distant-supervised training set and domain-specific features. Extensive experiments show that our model achieves comparable performance to the state-of-the-art model used in industry on both patents and papers. The output of this work should facilitate the searching, granting and filing of innovative ideas for patent examiners, attorneys and researchers. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1344/ |
| https://www.aclweb.org/anthology/D19-1344 | |
| PWC | https://paperswithcode.com/paper/a-label-informative-wide-textbackslash-deep |
| Repo | |
| Framework | |
Jointly Learning Author and Annotated Character N-gram Embeddings: A Case Study in Literary Text
| Title | Jointly Learning Author and Annotated Character N-gram Embeddings: A Case Study in Literary Text |
| Authors | Suraj Maharjan, Deepthi Mave, Prasha Shrestha, Manuel Montes, Fabio A. Gonz{'a}lez, Thamar Solorio |
| Abstract | An author{'}s way of presenting a story through his/her writing style has a great impact on whether the story will be liked by readers or not. In this paper, we learn representations for authors of literary texts together with representations for character n-grams annotated with their functional roles. We train a neural character n-gram based language model using an external corpus of literary texts and transfer learned representations for use in downstream tasks. We show that augmenting the knowledge from external works of authors produces results competitive with other style-based methods for book likability prediction, genre classification, and authorship attribution. |
| Tasks | Language Modelling |
| Published | 2019-09-01 |
| URL | https://www.aclweb.org/anthology/R19-1080/ |
| https://www.aclweb.org/anthology/R19-1080 | |
| PWC | https://paperswithcode.com/paper/jointly-learning-author-and-annotated |
| Repo | |
| Framework | |
Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval
| Title | Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval |
| Authors | Zeynep Akkalyoncu Yilmaz, Wei Yang, Haotian Zhang, Jimmy Lin |
| Abstract | This paper applies BERT to ad hoc document retrieval on news articles, which requires addressing two challenges: relevance judgments in existing test collections are typically provided only at the document level, and documents often exceed the length that BERT was designed to handle. Our solution is to aggregate sentence-level evidence to rank documents. Furthermore, we are able to leverage passage-level relevance judgments fortuitously available in other domains to fine-tune BERT models that are able to capture cross-domain notions of relevance, and can be directly used for ranking news articles. Our simple neural ranking models achieve state-of-the-art effectiveness on three standard test collections. |
| Tasks | |
| Published | 2019-11-01 |
| URL | https://www.aclweb.org/anthology/D19-1352/ |
| https://www.aclweb.org/anthology/D19-1352 | |
| PWC | https://paperswithcode.com/paper/cross-domain-modeling-of-sentence-level |
| Repo | |
| Framework | |
