October 15, 2019

1978 words 10 mins read

Paper Group NANR 166

Paper Group NANR 166

CRST: a Claim Retrieval System in Twitter. ArgumenText: Searching for Arguments in Heterogeneous Sources. DeepAlignment: Unsupervised Ontology Matching with Refined Word Vectors. Using the Nunavut Hansard Data for Experiments in Morphological Analysis and Machine Translation. Interactive Instance-based Evaluation of Knowledge Base Question Answerin …

CRST: a Claim Retrieval System in Twitter

Title CRST: a Claim Retrieval System in Twitter
Authors Wenjia Ma, WenHan Chao, Zhunchen Luo, Xin Jiang
Abstract For controversial topics, collecting argumentation-containing tweets which tend to be more convincing will help researchers analyze public opinions. Meanwhile, claim is the heart of argumentation. Hence, we present the first real-time claim retrieval system CRST that retrieves tweets containing claims for a given topic from Twitter. We propose a claim-oriented ranking module which can be divided into the offline topic-independent learning to rank model and the online topic-dependent lexicon model. Our system outperforms previous claim retrieval system and argument mining system. Moreover, the claim-oriented ranking module can be easily adapted to new topics without any manual process or external information, guaranteeing the practicability of our system.
Tasks Argument Mining, Learning-To-Rank
Published 2018-08-01
URL https://www.aclweb.org/anthology/C18-2010/
PDF https://www.aclweb.org/anthology/C18-2010
PWC https://paperswithcode.com/paper/crst-a-claim-retrieval-system-in-twitter
Repo
Framework

ArgumenText: Searching for Arguments in Heterogeneous Sources

Title ArgumenText: Searching for Arguments in Heterogeneous Sources
Authors Christian Stab, Johannes Daxenberger, Chris Stahlhut, Tristan Miller, Benjamin Schiller, Christopher Tauchmann, Steffen Eger, Iryna Gurevych
Abstract Argument mining is a core technology for enabling argument search in large corpora. However, most current approaches fall short when applied to heterogeneous texts. In this paper, we present an argument retrieval system capable of retrieving sentential arguments for any given controversial topic. By analyzing the highest-ranked results extracted from Web sources, we found that our system covers 89{%} of arguments found in expert-curated lists of arguments from an online debate portal, and also identifies additional valid arguments.
Tasks Argument Mining, Information Retrieval, Question Answering
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-5005/
PDF https://www.aclweb.org/anthology/N18-5005
PWC https://paperswithcode.com/paper/argumentext-searching-for-arguments-in
Repo
Framework

DeepAlignment: Unsupervised Ontology Matching with Refined Word Vectors

Title DeepAlignment: Unsupervised Ontology Matching with Refined Word Vectors
Authors Prodromos Kolyvakis, Alex Kalousis, ros, Dimitris Kiritsis
Abstract Ontologies compartmentalize types and relations in a target domain and provide the semantic backbone needed for a plethora of practical applications. Very often different ontologies are developed independently for the same domain. Such {``}parallel{''} ontologies raise the need for a process that will establish alignments between their entities in order to unify and extend the existing knowledge. In this work, we present a novel entity alignment method which we dub DeepAlignment. DeepAlignment refines pre-trained word vectors aiming at deriving ontological entity descriptions which are tailored to the ontology matching task. The absence of explicit information relevant to the ontology matching task during the refinement process makes DeepAlignment completely unsupervised. We empirically evaluate our method using standard ontology matching benchmarks. We present significant performance improvements over the current state-of-the-art, demonstrating the advantages that representation learning techniques bring to ontology matching. |
Tasks Entity Alignment, Feature Engineering, Representation Learning
Published 2018-06-01
URL https://www.aclweb.org/anthology/N18-1072/
PDF https://www.aclweb.org/anthology/N18-1072
PWC https://paperswithcode.com/paper/deepalignment-unsupervised-ontology-matching
Repo
Framework

Using the Nunavut Hansard Data for Experiments in Morphological Analysis and Machine Translation

Title Using the Nunavut Hansard Data for Experiments in Morphological Analysis and Machine Translation
Authors Jeffrey Micher
Abstract Inuktitut is a polysynthetic language spoken in Northern Canada and is one of the official languages of the Canadian territory of Nunavut. As such, the Nunavut Legislature publishes all of its proceedings in parallel English and Inuktitut. Several parallel English-Inuktitut corpora from these proceedings have been created from these data and are publically available. The corpus used for current experiments is described. Morphological processing of one of these corpora was carried out and details about the processing are provided. Then, the processed corpus was used in morphological analysis and machine translation (MT) experiments. The morphological analysis experiments aimed to improve the coverage of morphological processing of the corpus, and compare an additional experimental condition to previously published results. The machine translation experiments made use of the additional morphologically analyzed word types in a statistical machine translation system designed to translate to and from Inuktitut morphemes. Results are reported and next steps are defined.
Tasks Machine Translation, Morphological Analysis
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4807/
PDF https://www.aclweb.org/anthology/W18-4807
PWC https://paperswithcode.com/paper/using-the-nunavut-hansard-data-for
Repo
Framework

Interactive Instance-based Evaluation of Knowledge Base Question Answering

Title Interactive Instance-based Evaluation of Knowledge Base Question Answering
Authors Daniil Sorokin, Iryna Gurevych
Abstract Most approaches to Knowledge Base Question Answering are based on semantic parsing. In this paper, we present a tool that aids in debugging of question answering systems that construct a structured semantic representation for the input question. Previous work has largely focused on building question answering interfaces or evaluation frameworks that unify multiple data sets. The primary objective of our system is to enable interactive debugging of model predictions on individual instances (questions) and to simplify manual error analysis. Our interactive interface helps researchers to understand the shortcomings of a particular model, qualitatively analyze the complete pipeline and compare different models. A set of sit-by sessions was used to validate our interface design.
Tasks Entity Linking, Knowledge Base Question Answering, Question Answering, Semantic Parsing
Published 2018-11-01
URL https://www.aclweb.org/anthology/D18-2020/
PDF https://www.aclweb.org/anthology/D18-2020
PWC https://paperswithcode.com/paper/interactive-instance-based-evaluation-of
Repo
Framework

Towards making NLG a voice for interpretable Machine Learning

Title Towards making NLG a voice for interpretable Machine Learning
Authors James Forrest, Somayajulu Sripada, Wei Pang, George Coghill
Abstract This paper presents a study to understand the issues related to using NLG to humanise explanations from a popular interpretable machine learning framework called LIME. Our study shows that self-reported rating of NLG explanation was higher than that for a non-NLG explanation. However, when tested for comprehension, the results were not as clear-cut showing the need for performing more studies to uncover the factors responsible for high-quality NLG explanations.
Tasks Interpretable Machine Learning, Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6522/
PDF https://www.aclweb.org/anthology/W18-6522
PWC https://paperswithcode.com/paper/towards-making-nlg-a-voice-for-interpretable
Repo
Framework

An Adaption of BIOASQ Question Answering dataset for Machine Reading systems by Manual Annotations of Answer Spans.

Title An Adaption of BIOASQ Question Answering dataset for Machine Reading systems by Manual Annotations of Answer Spans.
Authors Sanjay Kamath, Brigitte Grau, Yue Ma
Abstract BIOASQ Task B Phase B challenge focuses on extracting answers from snippets for a given question. The dataset provided by the organizers contains answers, but not all their variants. Henceforth a manual annotation was performed to extract all forms of correct answers. This article shows the impact of using all occurrences of correct answers for training on the evaluation scores which are improved significantly.
Tasks Domain Adaptation, Question Answering, Reading Comprehension
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-5309/
PDF https://www.aclweb.org/anthology/W18-5309
PWC https://paperswithcode.com/paper/an-adaption-of-bioasq-question-answering
Repo
Framework

Predicting Japanese Word Order in Double Object Constructions

Title Predicting Japanese Word Order in Double Object Constructions
Authors Masayuki Asahara, Satoshi Nambu, Shin-Ichiro Sano
Abstract This paper presents a statistical model to predict Japanese word order in the double object constructions. We employed a Bayesian linear mixed model with manually annotated predicate-argument structure data. The findings from the refined corpus analysis confirmed the effects of information status of an NP as {}givennew ordering{'} in addition to the effects of {}long-before-short{'} as a tendency of the general Japanese word order.
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2805/
PDF https://www.aclweb.org/anthology/W18-2805
PWC https://paperswithcode.com/paper/predicting-japanese-word-order-in-double
Repo
Framework

Automatic Detection of Cross-Disciplinary Knowledge Associations

Title Automatic Detection of Cross-Disciplinary Knowledge Associations
Authors Menasha Thilakaratne, Katrina Falkner, Thushari Atapattu
Abstract Detecting interesting, cross-disciplinary knowledge associations hidden in scientific publications can greatly assist scientists to formulate and validate scientifically sensible novel research hypotheses. This will also introduce new areas of research that can be successfully linked with their research discipline. Currently, this process is mostly performed manually by exploring the scientific publications, requiring a substantial amount of time and effort. Due to the exponential growth of scientific literature, it has become almost impossible for a scientist to keep track of all research advances. As a result, scientists tend to deal with fragments of the literature according to their specialisation. Consequently, important and hidden associations among these fragmented knowledge that can be linked to produce significant scientific discoveries remain unnoticed. This doctoral work aims to develop a novel knowledge discovery approach that suggests most promising research pathways by analysing the existing scientific literature.
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/P18-3007/
PDF https://www.aclweb.org/anthology/P18-3007
PWC https://paperswithcode.com/paper/automatic-detection-of-cross-disciplinary
Repo
Framework

Designing and testing the messages produced by a virtual dietitian

Title Designing and testing the messages produced by a virtual dietitian
Authors Luca Anselma, Aless Mazzei, ro
Abstract This paper presents a project about the automatic generation of persuasive messages in the context of the diet management. In the first part of the paper we introduce the basic mechanisms related to data interpretation and content selection for a numerical data-to-text generation architecture. In the second part of the paper we discuss a number of factors influencing the design of the messages. In particular, we consider the design of the aggregation procedure. Finally, we present the results of a human-based evaluation concerning this design factor.
Tasks Data-to-Text Generation, Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6531/
PDF https://www.aclweb.org/anthology/W18-6531
PWC https://paperswithcode.com/paper/designing-and-testing-the-messages-produced
Repo
Framework

Frustratingly Easy Model Ensemble for Abstractive Summarization

Title Frustratingly Easy Model Ensemble for Abstractive Summarization
Authors Hayato Kobayashi
Abstract Ensemble methods, which combine multiple models at decoding time, are now widely known to be effective for text-generation tasks. However, they generally increase computational costs, and thus, there have been many studies on compressing or distilling ensemble models. In this paper, we propose an alternative, simple but effective unsupervised ensemble method, \textit{post-ensemble}, that combines multiple models by selecting a majority-like output in post-processing. We theoretically prove that our method is closely related to kernel density estimation based on the von Mises-Fisher kernel. Experimental results on a news-headline-generation task show that the proposed method performs better than the current ensemble methods.
Tasks Abstractive Text Summarization, Density Estimation, Model Compression, Question Answering, Text Generation
Published 2018-10-01
URL https://www.aclweb.org/anthology/D18-1449/
PDF https://www.aclweb.org/anthology/D18-1449
PWC https://paperswithcode.com/paper/frustratingly-easy-model-ensemble-for
Repo
Framework

Enhancement of Encoder and Attention Using Target Monolingual Corpora in Neural Machine Translation

Title Enhancement of Encoder and Attention Using Target Monolingual Corpora in Neural Machine Translation
Authors Kenji Imamura, Atsushi Fujita, Eiichiro Sumita
Abstract A large-scale parallel corpus is required to train encoder-decoder neural machine translation. The method of using synthetic parallel texts, in which target monolingual corpora are automatically translated into source sentences, is effective in improving the decoder, but is unreliable for enhancing the encoder. In this paper, we propose a method that enhances the encoder and attention using target monolingual corpora by generating multiple source sentences via sampling. By using multiple source sentences, diversity close to that of humans is achieved. Our experimental results show that the translation quality is improved by increasing the number of synthetic source sentences for each given target sentence, and quality close to that using a manually created parallel corpus was achieved.
Tasks Language Modelling, Machine Translation
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-2707/
PDF https://www.aclweb.org/anthology/W18-2707
PWC https://paperswithcode.com/paper/enhancement-of-encoder-and-attention-using
Repo
Framework

Technology Showcase and Presentations

Title Technology Showcase and Presentations
Authors Jennifer DeCamp
Abstract
Tasks
Published 2018-03-01
URL https://www.aclweb.org/anthology/W18-1904/
PDF https://www.aclweb.org/anthology/W18-1904
PWC https://paperswithcode.com/paper/technology-showcase-and-presentations
Repo
Framework

A Master-Apprentice Approach to Automatic Creation of Culturally Satirical Movie Titles

Title A Master-Apprentice Approach to Automatic Creation of Culturally Satirical Movie Titles
Authors Khalid Alnajjar, Mika H{"a}m{"a}l{"a}inen
Abstract Satire has played a role in indirectly expressing critique towards an authority or a person from time immemorial. We present an autonomously creative master-apprentice approach consisting of a genetic algorithm and an NMT model to produce humorous and culturally apt satire out of movie titles automatically. Furthermore, we evaluate the approach in terms of its creativity and its output. We provide a solid definition for creativity to maximize the objectiveness of the evaluation.
Tasks Text Generation
Published 2018-11-01
URL https://www.aclweb.org/anthology/W18-6534/
PDF https://www.aclweb.org/anthology/W18-6534
PWC https://paperswithcode.com/paper/a-master-apprentice-approach-to-automatic
Repo
Framework

Training, feedback and productivity measurement with NMT and Adaptive MT

Title Training, feedback and productivity measurement with NMT and Adaptive MT
Authors Jean-Luc Saillard
Abstract
Tasks
Published 2018-03-01
URL https://www.aclweb.org/anthology/W18-1906/
PDF https://www.aclweb.org/anthology/W18-1906
PWC https://paperswithcode.com/paper/training-feedback-and-productivity
Repo
Framework
comments powered by Disqus