October 15, 2019

1857 words 9 mins read

Paper Group NANR 159

Paper Group NANR 159

Just Talking - Modelling Casual Conversation. Can spontaneous spoken language disfluencies help describe syntactic dependencies? An empirical study. Introduction method for argumentative dialogue using paired question-answering interchange about personality. Part-of-Speech Annotation of English-Assamese code-mixed texts: Two Approaches. Proceedings …

Just Talking - Modelling Casual Conversation

Title Just Talking - Modelling Casual Conversation
Authors Emer Gilmartin, Christian Saam, Carl Vogel, Nick Campbell, Vincent Wade
Abstract Casual conversation has become a focus for artificial dialogue applications. Such talk is ubiquitous and its structure differs from that found in the task-based interactions which have been the focus of dialogue system design for many years. It is unlikely that such conversations can be modelled as an extension of task-based talk. We review theories of casual conversation, report on our studies of the structure of casual dialogue, and outline challenges we see for the development of spoken dialog systems capable of carrying on casual friendly conversation in addition to performing well-defined tasks.
Tasks
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-5006/
PDF https://www.aclweb.org/anthology/W18-5006
PWC https://paperswithcode.com/paper/just-talking-modelling-casual-conversation
Repo
Framework

Can spontaneous spoken language disfluencies help describe syntactic dependencies? An empirical study

Title Can spontaneous spoken language disfluencies help describe syntactic dependencies? An empirical study
Authors M. Zakaria Kurdi
Abstract This paper explores the correlations between key syntactic dependencies and the occurrence of simple spoken language disfluencies such as filled pauses and incomplete words. The working hypothesis here is that interruptions caused by these phenomena are more likely to happen between weakly connected words from a syntactic point of view than between strongly connected ones. The obtained results show significant patterns with the regard to key syntactic phenomena, like confirming the positive correlation between the frequency of disfluencies and multiples measures of syntactic complexity. In addition, they show that there is a stronger relationship between the verb and its subject than with its object, which confirms the idea of a hierarchical incrementality. Also, this work uncovered an interesting role played by a verb particle as a syntactic delimiter of some verb complements. Finally, the interruptions by disfluencies patterns show that verbs have a more privileged relationship with their preposition compared to the object Noun Phrase (NP).
Tasks Speech Recognition, Text Generation
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4108/
PDF https://www.aclweb.org/anthology/W18-4108
PWC https://paperswithcode.com/paper/can-spontaneous-spoken-language-disfluencies
Repo
Framework

Introduction method for argumentative dialogue using paired question-answering interchange about personality

Title Introduction method for argumentative dialogue using paired question-answering interchange about personality
Authors Kazuki Sakai, Ryuichiro Higashinaka, Yuichiro Yoshikawa, Hiroshi Ishiguro, Junji Tomita
Abstract To provide a better discussion experience in current argumentative dialogue systems, it is necessary for the user to feel motivated to participate, even if the system already responds appropriately. In this paper, we propose a method that can smoothly introduce argumentative dialogue by inserting an initial discourse, consisting of question-answer pairs concerning personality. The system can induce interest of the users prior to agreement or disagreement during the main discourse. By disclosing their interests, the users will feel familiarity and motivation to further engage in the argumentative dialogue and understand the system{'}s intent. To verify the effectiveness of a question-answer dialogue inserted before the argument, a subjective experiment was conducted using a text chat interface. The results suggest that inserting the question-answer dialogue enhances familiarity and naturalness. Notably, the results suggest that women more than men regard the dialogue as more natural and the argument as deepened, following an exchange concerning personality.
Tasks Decision Making, Question Answering
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-5008/
PDF https://www.aclweb.org/anthology/W18-5008
PWC https://paperswithcode.com/paper/introduction-method-for-argumentative
Repo
Framework

Part-of-Speech Annotation of English-Assamese code-mixed texts: Two Approaches

Title Part-of-Speech Annotation of English-Assamese code-mixed texts: Two Approaches
Authors Ritesh Kumar, Manas Jyoti Bora
Abstract In this paper, we discuss the development of a part-of-speech tagger for English-Assamese code-mixed texts. We provide a comparison of 2 approaches to annotating code-mixed data {–} a) annotation of the texts from the two languages using monolingual resources from each language and b) annotation of the text through a different resource created specifically for code-mixed data. We present a comparative study of the efforts required in each approach and the final performance of the system. Based on this, we argue that it might be a better approach to develop new technologies using code-mixed data instead of monolingual, {`}clean{'} data, especially for those languages where we do not have significant tools and technologies available till now. |
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4110/
PDF https://www.aclweb.org/anthology/W18-4110
PWC https://paperswithcode.com/paper/part-of-speech-annotation-of-english-assamese
Repo
Framework

Proceedings of the First Workshop on Natural Language Processing for Internet Freedom

Title Proceedings of the First Workshop on Natural Language Processing for Internet Freedom
Authors
Abstract
Tasks
Published 2018-08-01
URL https://www.aclweb.org/anthology/W18-4200/
PDF https://www.aclweb.org/anthology/W18-4200
PWC https://paperswithcode.com/paper/proceedings-of-the-first-workshop-on-natural
Repo
Framework

Community-Driven Crowdsourcing: Data Collection with Local Developers

Title Community-Driven Crowdsourcing: Data Collection with Local Developers
Authors Christina Funk, Michael Tseng, Ravindran Rajakumar, Linne Ha
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1254/
PDF https://www.aclweb.org/anthology/L18-1254
PWC https://paperswithcode.com/paper/community-driven-crowdsourcing-data
Repo
Framework

Sound Analogies with Phoneme Embeddings

Title Sound Analogies with Phoneme Embeddings
Authors Miikka P. Silfverberg, Lingshuang Mao, Mans Hulden
Abstract
Tasks Semantic Textual Similarity, Word Embeddings
Published 2018-01-01
URL https://www.aclweb.org/anthology/W18-0314/
PDF https://www.aclweb.org/anthology/W18-0314
PWC https://paperswithcode.com/paper/sound-analogies-with-phoneme-embeddings
Repo
Framework

No more beating about the bush : A Step towards Idiom Handling for Indian Language NLP

Title No more beating about the bush : A Step towards Idiom Handling for Indian Language NLP
Authors Ruchit Agrawal, Vighnesh Chenthil Kumar, Vigneshwaran Muralidharan, Dipti Sharma
Abstract
Tasks Machine Translation, Question Answering, Sentiment Analysis, Word Alignment
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1048/
PDF https://www.aclweb.org/anthology/L18-1048
PWC https://paperswithcode.com/paper/no-more-beating-about-the-bush-a-step-towards
Repo
Framework

BDPROTO: A Database of Phonological Inventories from Ancient and Reconstructed Languages

Title BDPROTO: A Database of Phonological Inventories from Ancient and Reconstructed Languages
Authors Egidio Marsico, Sebastien Flavier, Annemarie Verkerk, Steven Moran
Abstract
Tasks
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1262/
PDF https://www.aclweb.org/anthology/L18-1262
PWC https://paperswithcode.com/paper/bdproto-a-database-of-phonological
Repo
Framework

Pardon the Interruption: Managing Turn-Taking through Overlap Resolution in Embodied Artificial Agents

Title Pardon the Interruption: Managing Turn-Taking through Overlap Resolution in Embodied Artificial Agents
Authors Felix Gervits, Matthias Scheutz
Abstract Speech overlap is a common phenomenon in natural conversation and in task-oriented interactions. As human-robot interaction (HRI) becomes more sophisticated, the need to effectively manage turn-taking and resolve overlap becomes more important. In this paper, we introduce a computational model for speech overlap resolution in embodied artificial agents. The model identifies when overlap has occurred and uses timing information, dialogue history, and the agent{'}s goals to generate context-appropriate behavior. We implement this model in a Nao robot using the DIARC cognitive robotic architecture. The model is evaluated on a corpus of task-oriented human dialogue, and we find that the robot can replicate many of the most common overlap resolution behaviors found in the human data.
Tasks Spoken Dialogue Systems
Published 2018-07-01
URL https://www.aclweb.org/anthology/W18-5011/
PDF https://www.aclweb.org/anthology/W18-5011
PWC https://paperswithcode.com/paper/pardon-the-interruption-managing-turn-taking
Repo
Framework

GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction

Title GAL: Geometric Adversarial Loss for Single-View 3D-Object Reconstruction
Authors Li Jiang, Shaoshuai Shi, Xiaojuan Qi, Jiaya Jia
Abstract In this paper, we present a framework for reconstructing a point-based 3D model of an object from a single view image. Distance metrics, like Chamfer distance, were used in previous work to measure the difference of two point sets and serve as the loss function in point-based reconstruction. However, such point-point loss does not constrain the 3D model from a global perspective. We propose to add geometric adversarial loss (GAL). It is composed of two terms where the geometric loss ensures consistent shape of reconstructed 3D models close to ground-truth from different viewpoints, and the conditional adversarial loss generates a semantically-meaningful point cloud. GAL benefits predicting the obscured part of objects and maintaining geometric structure of the predicted 3D model. Both the qualitative results and quantitative analysis manifest the generality and suitability of our method.
Tasks 3D Object Reconstruction, Object Reconstruction
Published 2018-09-01
URL http://openaccess.thecvf.com/content_ECCV_2018/html/Li_Jiang_GAL_Geometric_Adversarial_ECCV_2018_paper.html
PDF http://openaccess.thecvf.com/content_ECCV_2018/papers/Li_Jiang_GAL_Geometric_Adversarial_ECCV_2018_paper.pdf
PWC https://paperswithcode.com/paper/gal-geometric-adversarial-loss-for-single
Repo
Framework

Commonsense Knowledge Base Completion and Generation

Title Commonsense Knowledge Base Completion and Generation
Authors Itsumi Saito, Kyosuke Nishida, Hisako Asano, Junji Tomita
Abstract This study focuses on acquisition of commonsense knowledge. A previous study proposed a commonsense knowledge base completion (CKB completion) method that predicts a confidence score of for triplet-style knowledge for improving the coverage of CKBs. To improve the accuracy of CKB completion and expand the size of CKBs, we formulate a new commonsense knowledge base generation task (CKB generation) and propose a joint learning method that incorporates both CKB completion and CKB generation. Experimental results show that the joint learning method improved completion accuracy and the generation model created reasonable knowledge. Our generation model could also be used to augment data and improve the accuracy of completion.
Tasks Knowledge Base Completion, Question Answering, Reading Comprehension
Published 2018-10-01
URL https://www.aclweb.org/anthology/K18-1014/
PDF https://www.aclweb.org/anthology/K18-1014
PWC https://paperswithcode.com/paper/commonsense-knowledge-base-completion-and
Repo
Framework

Leveraging Orthographic Similarity for Multilingual Neural Transliteration

Title Leveraging Orthographic Similarity for Multilingual Neural Transliteration
Authors Anoop Kunchukuttan, Mitesh Khapra, Gurneet Singh, Pushpak Bhattacharyya
Abstract We address the task of joint training of transliteration models for multiple language pairs (multilingual transliteration). This is an instance of multitask learning, where individual tasks (language pairs) benefit from sharing knowledge with related tasks. We focus on transliteration involving related tasks i.e., languages sharing writing systems and phonetic properties (orthographically similar languages). We propose a modified neural encoder-decoder model that maximizes parameter sharing across language pairs in order to effectively leverage orthographic similarity. We show that multilingual transliteration significantly outperforms bilingual transliteration in different scenarios (average increase of 58{%} across a variety of languages we experimented with). We also show that multilingual transliteration models can generalize well to languages/language pairs not encountered during training and hence perform well on the zeroshot transliteration task. We show that further improvements can be achieved by using phonetic feature input.
Tasks Information Retrieval, Machine Translation, Multi-Task Learning, Transliteration
Published 2018-01-01
URL https://www.aclweb.org/anthology/Q18-1022/
PDF https://www.aclweb.org/anthology/Q18-1022
PWC https://paperswithcode.com/paper/leveraging-orthographic-similarity-for
Repo
Framework

Identifying Affective Events and the Reasons for their Polarity

Title Identifying Affective Events and the Reasons for their Polarity
Authors Ellen Riloff
Abstract Many events have a positive or negative impact on our lives (e.g., {``}I bought a house{''} is typically good news, but {''}My house burned down{''} is bad news). Recognizing events that have affective polarity is essential for narrative text understanding, conversational dialogue, and applications such as summarization and sarcasm detection. We will discuss our recent work on identifying affective events and categorizing them based on the underlying reasons for their affective polarity. First, we will describe a weakly supervised learning method to induce a large set of affective events from a text corpus by optimizing for semantic consistency. Second, we will present models to classify affective events based on Human Need Categories, which often explain people{'}s motivations and desires. Our best results use a co-training model that consists of event expression and event context classifiers and exploits both labeled and unlabeled texts. We will conclude with a discussion of interesting directions for future work in this area. |
Tasks Sarcasm Detection
Published 2018-10-01
URL https://www.aclweb.org/anthology/W18-6201/
PDF https://www.aclweb.org/anthology/W18-6201
PWC https://paperswithcode.com/paper/identifying-affective-events-and-the-reasons
Repo
Framework

Laying the Groundwork for Knowledge Base Population: Nine Years of Linguistic Resources for TAC KBP

Title Laying the Groundwork for Knowledge Base Population: Nine Years of Linguistic Resources for TAC KBP
Authors Jeremy Getman, Joe Ellis, Stephanie Strassel, Zhiyi Song, Jennifer Tracey
Abstract
Tasks Knowledge Base Population
Published 2018-05-01
URL https://www.aclweb.org/anthology/L18-1245/
PDF https://www.aclweb.org/anthology/L18-1245
PWC https://paperswithcode.com/paper/laying-the-groundwork-for-knowledge-base
Repo
Framework
comments powered by Disqus