Paper Group NANR 74
Generating Natural Language Descriptions for Semantic Representations of Human Brain Activity. ``Who was Pietro Badoglio?’’ Towards a QA system for Italian History. A Corpus of Gesture-Annotated Dialogues for Monologue-to-Dialogue Generation from Personal Narratives. Pronoun Language Model and Grammatical Heuristics for Aiding Pronoun Prediction. T …
Generating Natural Language Descriptions for Semantic Representations of Human Brain Activity
| Title | Generating Natural Language Descriptions for Semantic Representations of Human Brain Activity |
| Authors | Eri Matsuo, Ichiro Kobayashi, Shinji Nishimoto, Satoshi Nishida, Hideki Asoh |
| Abstract | |
| Tasks | Image Captioning |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-3004/ |
| https://www.aclweb.org/anthology/P16-3004 | |
| PWC | https://paperswithcode.com/paper/generating-natural-language-descriptions-for |
| Repo | |
| Framework | |
``Who was Pietro Badoglio?’’ Towards a QA system for Italian History
| Title | ``Who was Pietro Badoglio?’’ Towards a QA system for Italian History | |
| Authors | Stefano Menini, Rachele Sprugnoli, Antonio Uva |
| Abstract | This paper presents QUANDHO (QUestion ANswering Data for italian HistOry), an Italian question answering dataset created to cover a specific domain, i.e. the history of Italy in the first half of the XX century. The dataset includes questions manually classified and annotated with Lexical Answer Types, and a set of question-answer pairs. This resource, freely available for research purposes, has been used to retrain a domain independent question answering system so to improve its performances in the domain of interest. Ongoing experiments on the development of a question classifier and an automatic tagger of Lexical Answer Types are also presented. |
| Tasks | Question Answering |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1069/ |
| https://www.aclweb.org/anthology/L16-1069 | |
| PWC | https://paperswithcode.com/paper/who-was-pietro-badoglio-towards-a-qa-system |
| Repo | |
| Framework | |
A Corpus of Gesture-Annotated Dialogues for Monologue-to-Dialogue Generation from Personal Narratives
| Title | A Corpus of Gesture-Annotated Dialogues for Monologue-to-Dialogue Generation from Personal Narratives |
| Authors | Zhichao Hu, Michelle Dick, Chung-Ning Chang, Kevin Bowden, Michael Neff, Jean Fox Tree, Marilyn Walker |
| Abstract | Story-telling is a fundamental and prevalent aspect of human social behavior. In the wild, stories are told conversationally in social settings, often as a dialogue and with accompanying gestures and other nonverbal behavior. This paper presents a new corpus, the Story Dialogue with Gestures (SDG) corpus, consisting of 50 personal narratives regenerated as dialogues, complete with annotations of gesture placement and accompanying gesture forms. The corpus includes dialogues generated by human annotators, gesture annotations on the human generated dialogues, videos of story dialogues generated from this representation, video clips of each gesture used in the gesture annotations, and annotations of the original personal narratives with a deep representation of story called a Story Intention Graph. Our long term goal is the automatic generation of story co-tellings as animated dialogues from the Story Intention Graph. We expect this corpus to be a useful resource for researchers interested in natural language generation, intelligent virtual agents, generation of nonverbal behavior, and story and narrative representations. |
| Tasks | Dialogue Generation, Text Generation |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1550/ |
| https://www.aclweb.org/anthology/L16-1550 | |
| PWC | https://paperswithcode.com/paper/a-corpus-of-gesture-annotated-dialogues-for |
| Repo | |
| Framework | |
Pronoun Language Model and Grammatical Heuristics for Aiding Pronoun Prediction
| Title | Pronoun Language Model and Grammatical Heuristics for Aiding Pronoun Prediction |
| Authors | Ngoc Quang Luong, Andrei Popescu-Belis |
| Abstract | |
| Tasks | Language Modelling, Machine Translation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/W16-2352/ |
| https://www.aclweb.org/anthology/W16-2352 | |
| PWC | https://paperswithcode.com/paper/pronoun-language-model-and-grammatical |
| Repo | |
| Framework | |
The SpeDial datasets: datasets for Spoken Dialogue Systems analytics
| Title | The SpeDial datasets: datasets for Spoken Dialogue Systems analytics |
| Authors | Jos{'e} Lopes, Arodami Chorianopoulou, Elisavet Palogiannidi, Helena Moniz, Alberto Abad, Katerina Louka, Elias Iosif, Alex Potamianos, ros |
| Abstract | The SpeDial consortium is sharing two datasets that were used during the SpeDial project. By sharing them with the community we are providing a resource to reduce the duration of cycle of development of new Spoken Dialogue Systems (SDSs). The datasets include audios and several manual annotations, i.e., miscommunication, anger, satisfaction, repetition, gender and task success. The datasets were created with data from real users and cover two different languages: English and Greek. Detectors for miscommunication, anger and gender were trained for both systems. The detectors were particularly accurate in tasks where humans have high annotator agreement such as miscommunication and gender. As expected due to the subjectivity of the task, the anger detector had a less satisfactory performance. Nevertheless, we proved that the automatic detection of situations that can lead to problems in SDSs is possible and can be a promising direction to reduce the duration of SDS{'}s development cycle. |
| Tasks | Spoken Dialogue Systems |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1016/ |
| https://www.aclweb.org/anthology/L16-1016 | |
| PWC | https://paperswithcode.com/paper/the-spedial-datasets-datasets-for-spoken |
| Repo | |
| Framework | |
Adding Context to Semantic Data-Driven Paraphrasing
| Title | Adding Context to Semantic Data-Driven Paraphrasing |
| Authors | Vered Shwartz, Ido Dagan |
| Abstract | |
| Tasks | Natural Language Inference, Question Answering |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/S16-2013/ |
| https://www.aclweb.org/anthology/S16-2013 | |
| PWC | https://paperswithcode.com/paper/adding-context-to-semantic-data-driven |
| Repo | |
| Framework | |
News Sentiment and Cross-Country Fluctuations
| Title | News Sentiment and Cross-Country Fluctuations |
| Authors | Samuel Fraiberger |
| Abstract | |
| Tasks | |
| Published | 2016-11-01 |
| URL | https://www.aclweb.org/anthology/W16-5616/ |
| https://www.aclweb.org/anthology/W16-5616 | |
| PWC | https://paperswithcode.com/paper/news-sentiment-and-cross-country-fluctuations |
| Repo | |
| Framework | |
Semi-automatic Parsing for Web Knowledge Extraction through Semantic Annotation
| Title | Semi-automatic Parsing for Web Knowledge Extraction through Semantic Annotation |
| Authors | Maria Pia di Buono |
| Abstract | Parsing Web information, namely parsing content to find relevant documents on the basis of a user{'}s query, represents a crucial step to guarantee fast and accurate Information Retrieval (IR). Generally, an automated approach to such task is considered faster and cheaper than manual systems. Nevertheless, results do not seem have a high level of accuracy, indeed, as also Hjorland (2007) states, using stochastic algorithms entails: {\mbox{$\bullet$}} Low precision due to the indexing of common Atomic Linguistic Units (ALUs) or sentences. {\mbox{$\bullet$}} Low recall caused by the presence of synonyms. {\mbox{$\bullet$}} Generic results arising from the use of too broad or too narrow terms. Usually IR systems are based on invert text index, namely an index data structure storing a mapping from content to its locations in a database file, or in a document or a set of documents. In this paper we propose a system, by means of which we will develop a search engine able to process online documents, starting from a natural language query, and to return information to users. The proposed approach, based on the Lexicon-Grammar (LG) framework and its language formalization methodologies, aims at integrating a semantic annotation process for both query analysis and document retrieval. |
| Tasks | Information Retrieval |
| Published | 2016-05-01 |
| URL | https://www.aclweb.org/anthology/L16-1113/ |
| https://www.aclweb.org/anthology/L16-1113 | |
| PWC | https://paperswithcode.com/paper/semi-automatic-parsing-for-web-knowledge |
| Repo | |
| Framework | |
Claim Synthesis via Predicate Recycling
| Title | Claim Synthesis via Predicate Recycling |
| Authors | Yonatan Bilu, Noam Slonim |
| Abstract | |
| Tasks | Argument Mining, Recommendation Systems, Text Generation |
| Published | 2016-08-01 |
| URL | https://www.aclweb.org/anthology/P16-2085/ |
| https://www.aclweb.org/anthology/P16-2085 | |
| PWC | https://paperswithcode.com/paper/claim-synthesis-via-predicate-recycling |
| Repo | |
| Framework | |
Threat detection in online discussions
| Title | Threat detection in online discussions |
| Authors | Aksel Wester, Lilja {\O}vrelid, Erik Velldal, Hugo Lewi Hammer |
| Abstract | |
| Tasks | Word Sense Disambiguation |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0413/ |
| https://www.aclweb.org/anthology/W16-0413 | |
| PWC | https://paperswithcode.com/paper/threat-detection-in-online-discussions |
| Repo | |
| Framework | |
Political Issue Extraction Model: A Novel Hierarchical Topic Model That Uses Tweets By Political And Non-Political Authors
| Title | Political Issue Extraction Model: A Novel Hierarchical Topic Model That Uses Tweets By Political And Non-Political Authors |
| Authors | Aditya Joshi, Pushpak Bhattacharyya, Mark Carman |
| Abstract | |
| Tasks | |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0415/ |
| https://www.aclweb.org/anthology/W16-0415 | |
| PWC | https://paperswithcode.com/paper/political-issue-extraction-model-a-novel |
| Repo | |
| Framework | |
How can NLP Tasks Mutually Benefit Sentiment Analysis? A Holistic Approach to Sentiment Analysis
| Title | How can NLP Tasks Mutually Benefit Sentiment Analysis? A Holistic Approach to Sentiment Analysis |
| Authors | Lingjia Deng, Janyce Wiebe |
| Abstract | |
| Tasks | Entity Linking, Semantic Role Labeling, Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0411/ |
| https://www.aclweb.org/anthology/W16-0411 | |
| PWC | https://paperswithcode.com/paper/how-can-nlp-tasks-mutually-benefit-sentiment |
| Repo | |
| Framework | |
Emotions and NLP: Future Directions
| Title | Emotions and NLP: Future Directions |
| Authors | Carlo Strapparava |
| Abstract | |
| Tasks | Emotion Classification, Sentiment Analysis |
| Published | 2016-06-01 |
| URL | https://www.aclweb.org/anthology/W16-0430/ |
| https://www.aclweb.org/anthology/W16-0430 | |
| PWC | https://paperswithcode.com/paper/emotions-and-nlp-future-directions |
| Repo | |
| Framework | |
An Efficient and Effective Online Sentence Segmenter for Simultaneous Interpretation
| Title | An Efficient and Effective Online Sentence Segmenter for Simultaneous Interpretation |
| Authors | Xiaolin Wang, Andrew Finch, Masao Utiyama, Eiichiro Sumita |
| Abstract | Simultaneous interpretation is a very challenging application of machine translation in which the input is a stream of words from a speech recognition engine. The key problem is how to segment the stream in an online manner into units suitable for translation. The segmentation process proceeds by calculating a confidence score for each word that indicates the soundness of placing a sentence boundary after it, and then heuristics are employed to determine the position of the boundaries. Multiple variants of the confidence scoring method and segmentation heuristics were studied. Experimental results show that the best performing strategy is not only efficient in terms of average latency per word, but also achieved end-to-end translation quality close to an offline baseline, and close to oracle segmentation. |
| Tasks | Machine Translation, Speech Recognition |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4613/ |
| https://www.aclweb.org/anthology/W16-4613 | |
| PWC | https://paperswithcode.com/paper/an-efficient-and-effective-online-sentence |
| Repo | |
| Framework | |
Implementation of a Workflow Management System for Non-Expert Users
| Title | Implementation of a Workflow Management System for Non-Expert Users |
| Authors | Bart Jongejan |
| Abstract | In the Danish CLARIN-DK infrastructure, chaining language technology (LT) tools into a workflow is easy even for a non-expert user, because she only needs to specify the input and the desired output of the workflow. With this information and the registered input and output profiles of the available tools, the CLARIN-DK workflow management system (WMS) computes combinations of tools that will give the desired result. This advanced functionality was originally not envisaged, but came within reach by writing the WMS partly in Java and partly in a programming language for symbolic computation, Bracmat. Handling LT tool profiles, including the computation of workflows, is easier with Bracmat{'}s language constructs for tree pattern matching and tree construction than with the language constructs offered by mainstream programming languages. |
| Tasks | Optical Character Recognition |
| Published | 2016-12-01 |
| URL | https://www.aclweb.org/anthology/W16-4014/ |
| https://www.aclweb.org/anthology/W16-4014 | |
| PWC | https://paperswithcode.com/paper/implementation-of-a-workflow-management |
| Repo | |
| Framework | |
