Paper Group NANR 274
Neural Network Language Modeling with Letter-based Features and Importance Sampling. YNU-HPCC at SemEval-2018 Task 12: The Argument Reasoning Comprehension Task Using a Bi-directional LSTM with Attention Model. Lyb3b at SemEval-2018 Task 12: Ensemble-based Deep Learning Models for Argument Reasoning Comprehension Task. Learning distributed event re …
Neural Network Language Modeling with Letter-based Features and Importance Sampling
| Title | Neural Network Language Modeling with Letter-based Features and Importance Sampling |
| Authors | Hainan Xu, Ke Li, Yiming Wang, Jian Wang, Shiyin Kang, Xie Chen, Daniel Povey, Sanjeev Khudanpur |
| Abstract | In this paper we describe an extension of the Kaldi software toolkit to support neural-based language modeling, intended for use in automatic speech recognition (ASR) and related tasks. We combine the use of subword features (letter n-grams) and one-hot encoding of frequent words so that the models can handle large vocabularies containing infrequent words. We propose a new objective function that allows for training of unnormalized probabilities. An importance sampling based method is supported to speed up training when the vocabulary is large. Experimental results on five corpora show that Kaldi-RNNLM rivals other recurrent neural network language model toolkits both on performance and training speed. |
| Tasks | Language Modelling, Speech Recognition |
| Published | 2018-04-15 |
| URL | https://www.cs.jhu.edu/~hxu/neural-network-language.pdf |
| https://www.cs.jhu.edu/~hxu/neural-network-language.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-language-modeling-with-letter |
| Repo | |
| Framework | |
YNU-HPCC at SemEval-2018 Task 12: The Argument Reasoning Comprehension Task Using a Bi-directional LSTM with Attention Model
| Title | YNU-HPCC at SemEval-2018 Task 12: The Argument Reasoning Comprehension Task Using a Bi-directional LSTM with Attention Model |
| Authors | Quanlei Liao, Xutao Yang, Jin Wang, Xuejie Zhang |
| Abstract | An argument is divided into two parts, the claim and the reason. To obtain a clearer conclusion, some additional explanation is required. In this task, the explanations are called warrants. This paper introduces a bi-directional long short term memory (Bi-LSTM) with an attention model to select a correct warrant from two to explain an argument. We address this question as a question-answering system. For each warrant, the model produces a probability that it is correct. Finally, the system chooses the highest correct probability as the answer. Ensemble learning is used to enhance the performance of the model. Among all of the participants, we ranked 15th on the test results. |
| Tasks | Question Answering |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1187/ |
| https://www.aclweb.org/anthology/S18-1187 | |
| PWC | https://paperswithcode.com/paper/ynu-hpcc-at-semeval-2018-task-12-the-argument |
| Repo | |
| Framework | |
Lyb3b at SemEval-2018 Task 12: Ensemble-based Deep Learning Models for Argument Reasoning Comprehension Task
| Title | Lyb3b at SemEval-2018 Task 12: Ensemble-based Deep Learning Models for Argument Reasoning Comprehension Task |
| Authors | Yongbin Li, Xiaobing Zhou |
| Abstract | Reasoning is a crucial part of natural language argumentation. In order to comprehend an argument, we have to reconstruct and analyze its reasoning. In this task, given a natural language argument with a reason and a claim, the goal is to choose the correct implicit reasoning from two options, in order to form a reasonable structure of (Reason, Warrant, Claim). Our approach is to build distributed word embedding of reason, warrant and claim respectively, meanwhile, we use a series of frameworks such as CNN model, LSTM model, GRU with attention model and biLSTM with attention model for processing word vector. Finally, ensemble mechanism is used to integrate the results of each framework to improve the final accuracy. Experiments demonstrate superior performance of ensemble mechanism compared to each separate framework. We are the 11th in official results, the final model can reach a 0.568 accuracy rate on the test dataset. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-1193/ |
| https://www.aclweb.org/anthology/S18-1193 | |
| PWC | https://paperswithcode.com/paper/lyb3b-at-semeval-2018-task-12-ensemble-based |
| Repo | |
| Framework | |
Learning distributed event representations with a multi-task approach
| Title | Learning distributed event representations with a multi-task approach |
| Authors | Xudong Hong, Asad Sayeed, Vera Demberg |
| Abstract | Human world knowledge contains information about prototypical events and their participants and locations. In this paper, we train the first models using multi-task learning that can both predict missing event participants and also perform semantic role classification based on semantic plausibility. Our best-performing model is an improvement over the previous state-of-the-art on thematic fit modelling tasks. The event embeddings learned by the model can additionally be used effectively in an event similarity task, also outperforming the state-of-the-art. |
| Tasks | Multi-Task Learning |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2002/ |
| https://www.aclweb.org/anthology/S18-2002 | |
| PWC | https://paperswithcode.com/paper/learning-distributed-event-representations |
| Repo | |
| Framework | |
Graph Algebraic Combinatory Categorial Grammar
| Title | Graph Algebraic Combinatory Categorial Grammar |
| Authors | Sebastian Beschke, Wolfgang Menzel |
| Abstract | This paper describes CCG/AMR, a novel grammar for semantic parsing of Abstract Meaning Representations. CCG/AMR equips Combinatory Categorial Grammar derivations with graph semantics by assigning each CCG combinator an interpretation in terms of a graph algebra. We provide an algorithm that induces a CCG/AMR from a corpus and show that it creates a compact lexicon with low ambiguity and achieves a robust coverage of 78{%} of the examined sentences under ideal conditions. We also identify several phenomena that affect any approach relying either on CCG or graph algebraic approaches for AMR parsing. This includes differences of representation between CCG and AMR, as well as non-compositional constructions that are not expressible through a monotonous construction process. To our knowledge, this paper provides the first analysis of these corpus issues. |
| Tasks | Amr Parsing, Machine Translation, Semantic Parsing |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2006/ |
| https://www.aclweb.org/anthology/S18-2006 | |
| PWC | https://paperswithcode.com/paper/graph-algebraic-combinatory-categorial |
| Repo | |
| Framework | |
GBD-NER at PARSEME Shared Task 2018: Multi-Word Expression Detection Using Bidirectional Long-Short-Term Memory Networks and Graph-Based Decoding
| Title | GBD-NER at PARSEME Shared Task 2018: Multi-Word Expression Detection Using Bidirectional Long-Short-Term Memory Networks and Graph-Based Decoding |
| Authors | Tiberiu Boros, Rux Burtica, ra |
| Abstract | This paper addresses the issue of multi-word expression (MWE) detection by employing a new decoding strategy inspired after graph-based parsing. We show that this architecture achieves state-of-the-art results with minimum feature-engineering, just by relying on lexicalized and morphological attributes. We validate our approach in a multilingual setting, using standard MWE corpora supplied in the PARSEME Shared Task. |
| Tasks | Feature Engineering |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4928/ |
| https://www.aclweb.org/anthology/W18-4928 | |
| PWC | https://paperswithcode.com/paper/gbd-ner-at-parseme-shared-task-2018-multi |
| Repo | |
| Framework | |
Quantitative Semantic Variation in the Contexts of Concrete and Abstract Words
| Title | Quantitative Semantic Variation in the Contexts of Concrete and Abstract Words |
| Authors | Daniela Naumann, Diego Frassinelli, Sabine Schulte im Walde |
| Abstract | Across disciplines, researchers are eager to gain insight into empirical features of abstract vs. concrete concepts. In this work, we provide a detailed characterisation of the distributional nature of abstract and concrete words across 16,620 English nouns, verbs and adjectives. Specifically, we investigate the following questions: (1) What is the distribution of concreteness in the contexts of concrete and abstract target words? (2) What are the differences between concrete and abstract words in terms of contextual semantic diversity? (3) How does the entropy of concrete and abstract word contexts differ? Overall, our studies show consistent differences in the distributional representation of concrete and abstract words, thus challenging existing theories of cognition and providing a more fine-grained description of their nature. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2008/ |
| https://www.aclweb.org/anthology/S18-2008 | |
| PWC | https://paperswithcode.com/paper/quantitative-semantic-variation-in-the |
| Repo | |
| Framework | |
EmoWordNet: Automatic Expansion of Emotion Lexicon Using English WordNet
| Title | EmoWordNet: Automatic Expansion of Emotion Lexicon Using English WordNet |
| Authors | Gilbert Badaro, Hussein Jundi, Hazem Hajj, Wassim El-Hajj |
| Abstract | Nowadays, social media have become a platform where people can easily express their opinions and emotions about any topic such as politics, movies, music, electronic products and many others. On the other hand, politicians, companies, and businesses are interested in analyzing automatically people{'}s opinions and emotions. In the last decade, a lot of efforts has been put into extracting sentiment polarity from texts. Recently, the focus has expanded to also cover emotion recognition from texts. In this work, we expand an existing emotion lexicon, DepecheMood, by leveraging semantic knowledge from English WordNet (EWN). We create an expanded lexicon, EmoWordNet, consisting of 67K terms aligned with EWN, almost 1.8 times the size of DepecheMood. We also evaluate EmoWordNet in an emotion recognition task using SemEval 2007 news headlines dataset and we achieve an improvement compared to the use of DepecheMood. EmoWordNet is publicly available to speed up research in the field on \url{http://oma-project.com}. |
| Tasks | Emotion Classification, Emotion Recognition, Recommendation Systems, Sentiment Analysis |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2009/ |
| https://www.aclweb.org/anthology/S18-2009 | |
| PWC | https://paperswithcode.com/paper/emowordnet-automatic-expansion-of-emotion |
| Repo | |
| Framework | |
Named Graphs for Semantic Representation
| Title | Named Graphs for Semantic Representation |
| Authors | Richard Crouch, Aikaterini-Lida Kalouli |
| Abstract | A position paper arguing that purely graphical representations for natural language semantics lack a fundamental degree of expressiveness, and cannot deal with even basic Boolean operations like negation or disjunction. Moving from graphs to named graphs leads to representations that stand some chance of having sufficient expressive power. Named $\mathcal{FL}_0$ graphs are of particular interest. |
| Tasks | Knowledge Graphs |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2013/ |
| https://www.aclweb.org/anthology/S18-2013 | |
| PWC | https://paperswithcode.com/paper/named-graphs-for-semantic-representation |
| Repo | |
| Framework | |
Coarse Lexical Frame Acquisition at the Syntax–Semantics Interface Using a Latent-Variable PCFG Model
| Title | Coarse Lexical Frame Acquisition at the Syntax–Semantics Interface Using a Latent-Variable PCFG Model |
| Authors | Laura Kallmeyer, Behrang QasemiZadeh, Jackie Chi Kit Cheung |
| Abstract | We present a method for unsupervised lexical frame acquisition at the syntax{–}semantics interface. Given a set of input strings derived from dependency parses, our method generates a set of clusters that resemble lexical frame structures. Our work is motivated not only by its practical applications (e.g., to build, or expand the coverage of lexical frame databases), but also to gain linguistic insight into frame structures with respect to lexical distributions in relation to grammatical structures. We model our task using a hierarchical Bayesian network and employ tools and methods from latent variable probabilistic context free grammars (L-PCFGs) for statistical inference and parameter fitting, for which we propose a new split and merge procedure. We show that our model outperforms several baselines on a portion of the Wall Street Journal sentences that we have newly annotated for evaluation purposes. |
| Tasks | Question Answering, Text Summarization |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2016/ |
| https://www.aclweb.org/anthology/S18-2016 | |
| PWC | https://paperswithcode.com/paper/coarse-lexical-frame-acquisition-at-the |
| Repo | |
| Framework | |
In-domain Context-aware Token Embeddings Improve Biomedical Named Entity Recognition
| Title | In-domain Context-aware Token Embeddings Improve Biomedical Named Entity Recognition |
| Authors | Golnar Sheikhshabbafghi, Inanc Birol, Anoop Sarkar |
| Abstract | Rapidly expanding volume of publications in the biomedical domain makes it increasingly difficult for a timely evaluation of the latest literature. That, along with a push for automated evaluation of clinical reports, present opportunities for effective natural language processing methods. In this study we target the problem of named entity recognition, where texts are processed to annotate terms that are relevant for biomedical studies. Terms of interest in the domain include gene and protein names, and cell lines and types. Here we report on a pipeline built on Embeddings from Language Models (ELMo) and a deep learning package for natural language processing (AllenNLP). We trained context-aware token embeddings on a dataset of biomedical papers using ELMo, and incorporated these embeddings in the LSTM-CRF model used by AllenNLP for named entity recognition. We show these representations improve named entity recognition for different types of biomedical named entities. We also achieve a new state of the art in gene mention detection on the BioCreative II gene mention shared task. |
| Tasks | Language Modelling, Named Entity Recognition, Question Answering, Sentiment Analysis, Word Embeddings, Word Sense Disambiguation |
| Published | 2018-10-01 |
| URL | https://www.aclweb.org/anthology/W18-5618/ |
| https://www.aclweb.org/anthology/W18-5618 | |
| PWC | https://paperswithcode.com/paper/in-domain-context-aware-token-embeddings |
| Repo | |
| Framework | |
Indigenous language technologies in Canada: Assessment, challenges, and successes
| Title | Indigenous language technologies in Canada: Assessment, challenges, and successes |
| Authors | Patrick Littell, Anna Kazantseva, Rol Kuhn, , Aidan Pine, Antti Arppe, Christopher Cox, Marie-Odile Junker |
| Abstract | In this article, we discuss which text, speech, and image technologies have been developed, and would be feasible to develop, for the approximately 60 Indigenous languages spoken in Canada. In particular, we concentrate on technologies that may be feasible to develop for most or all of these languages, not just those that may be feasible for the few most-resourced of these. We assess past achievements and consider future horizons for Indigenous language transliteration, text prediction, spell-checking, approximate search, machine translation, speech recognition, speaker diarization, speech synthesis, optical character recognition, and computer-aided language learning. |
| Tasks | Machine Translation, Optical Character Recognition, Speaker Diarization, Speech Recognition, Speech Synthesis, Transliteration |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/C18-1222/ |
| https://www.aclweb.org/anthology/C18-1222 | |
| PWC | https://paperswithcode.com/paper/indigenous-language-technologies-in-canada |
| Repo | |
| Framework | |
Putting Semantics into Semantic Roles
| Title | Putting Semantics into Semantic Roles |
| Authors | James Allen, Choh Man Teng |
| Abstract | While there have been many proposals for theories of semantic roles over the years, these models are mostly justified by intuition and the only evaluation methods have been inter-annotator agreement. We explore three different ideas for providing more rigorous theories of semantic roles. These ideas give rise to more objective criteria for designing role sets, and lend themselves to some experimental evaluation. We illustrate the discussion by examining the semantic roles in TRIPS. |
| Tasks | |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2028/ |
| https://www.aclweb.org/anthology/S18-2028 | |
| PWC | https://paperswithcode.com/paper/putting-semantics-into-semantic-roles |
| Repo | |
| Framework | |
Pose Transferrable Person Re-Identification
| Title | Pose Transferrable Person Re-Identification |
| Authors | Jinxian Liu, Bingbing Ni, Yichao Yan, Peng Zhou, Shuo Cheng, Jianguo Hu |
| Abstract | Person re-identification (ReID) is an important task in the field of intelligent security. A key challenge is how to capture human pose variations, while existing benchmarks (i.e., Market1501, DukeMTMC-reID, CUHK03, etc.) do NOT provide sufficient pose coverage to train a robust ReID system. To address this issue, we propose a pose-transferrable person ReID framework which utilizes pose-transferred sample augmentations (i.e., with ID supervision) to enhance ReID model training. On one hand, novel training samples with rich pose variations are generated via transferring pose instances from MARS dataset, and they are added into the target dataset to facilitate robust training. On the other hand, in addition to the conventional discriminator of GAN (i.e., to distinguish between REAL/FAKE samples), we propose a novel guider sub-network which encourages the generated sample (i.e., with novel pose) towards better satisfying the ReID loss (i.e., cross-entropy ReID loss, triplet ReID loss). In the meantime, an alternative optimization procedure is proposed to train the proposed Generator-Guider-Discriminator network. Experimental results on Market-1501, DukeMTMC-reID and CUHK03 show that our method achieves great performance improvement, and outperforms most state-of-the-art methods without elaborate designing the ReID model. |
| Tasks | Person Re-Identification |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Liu_Pose_Transferrable_Person_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Pose_Transferrable_Person_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/pose-transferrable-person-re-identification |
| Repo | |
| Framework | |
Solving Feature Sparseness in Text Classification using Core-Periphery Decomposition
| Title | Solving Feature Sparseness in Text Classification using Core-Periphery Decomposition |
| Authors | Xia Cui, Sadamori Kojaku, Naoki Masuda, Danushka Bollegala |
| Abstract | Feature sparseness is a problem common to cross-domain and short-text classification tasks. To overcome this feature sparseness problem, we propose a novel method based on graph decomposition to find candidate features for expanding feature vectors. Specifically, we first create a feature-relatedness graph, which is subsequently decomposed into core-periphery (CP) pairs and use the peripheries as the expansion candidates of the cores. We expand both training and test instances using the computed related features and use them to train a text classifier. We observe that prioritising features that are common to both training and test instances as cores during the CP decomposition to further improve the accuracy of text classification. We evaluate the proposed CP-decomposition-based feature expansion method on benchmark datasets for cross-domain sentiment classification and short-text classification. Our experimental results show that the proposed method consistently outperforms all baselines on short-text classification tasks, and perform competitively with pivot-based cross-domain sentiment classification methods. |
| Tasks | Domain Adaptation, Sentiment Analysis, Text Classification |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/S18-2030/ |
| https://www.aclweb.org/anthology/S18-2030 | |
| PWC | https://paperswithcode.com/paper/solving-feature-sparseness-in-text |
| Repo | |
| Framework | |
