1 |
DeepL et Google Translate face à l'ambiguïté phraséologique
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03583995 ; 2022 (2022)
|
|
BASE
|
|
Show details
|
|
2 |
Islands and Bridges of Language: Bio-Inspired Structural Analysis of Language Embedding Data
|
|
|
|
BASE
|
|
Show details
|
|
3 |
VEREINDEUTIGUNG ZUR KLASSIFIZIERUNG LEXIKALISCHER OBJEKTE ; DISAMBIGUATION FOR THE CLASSIFICATION OF LEXICAL ITEMS ; DÉSAMBÏGUISATION POUR LA CLASSIFICATION DE LEXÈMES
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03598242 ; France, Patent n° : EP3937059A1. 2022 (2022)
|
|
BASE
|
|
Show details
|
|
4 |
Sentence Processing in Traumatic Brain Injury (Key-DeLyria, 2016) ...
|
|
|
|
BASE
|
|
Show details
|
|
5 |
Sentence Processing in Traumatic Brain Injury (Key-DeLyria, 2016) ...
|
|
|
|
BASE
|
|
Show details
|
|
6 |
Vikidia En/Fr bilingual dataset for Automatic Readability Assessment ...
|
|
|
|
BASE
|
|
Show details
|
|
7 |
Vikidia En/Fr bilingual dataset for Automatic Readability Assessment ...
|
|
|
|
BASE
|
|
Show details
|
|
8 |
VivesDebate: A New Annotated Multilingual Corpus of Argumentation in a Debate Tournament ...
|
|
|
|
BASE
|
|
Show details
|
|
9 |
VivesDebate: A New Annotated Multilingual Corpus of Argumentation in a Debate Tournament ...
|
|
|
|
BASE
|
|
Show details
|
|
11 |
VivesDebate: A New Annotated Multilingual Corpus of Argumentation in a Debate Tournament ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Task and language in Spanish–English narratives (Wofford et al., 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Task and language in Spanish–English narratives (Wofford et al., 2022) ...
|
|
|
|
BASE
|
|
Show details
|
|
17 |
Data of the Shared Task on the Disambiguation of German Verbal Idioms at KONVENS 2021 ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
Data of the Shared Task on the Disambiguation of German Verbal Idioms at KONVENS 2021 ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
DESIGNING TO SUPPORT SENSEMAKING IN CROSS-LINGUAL COMPUTER-MEDIATED COMMUNICATION USING NLP TECHNIQUES
|
|
|
|
Abstract:
218 pages ; Advances in machine translation (MT) and computer-mediated communication (CMC) tools now allow people to collaborate on common problems and interact with others across linguistic and cultural boundaries. However, communicating with linguistically different others, specifically, making sense of the meanings in foreign language messages, is still challenging. Because of the imperfect quality of MT and a lack of cultural and contextual knowledge regarding other cultures, people experience difficulties in extracting informative cues and interpreting the meanings of foreign language messages. Such challenges can diminish the capability of CMC platforms to facilitate communication and information exchange between linguistically and/or culturally diverse communities The main goal of this dissertation is to explore design solutions that can improve people’s sensemaking processes when they encounter foreign language messages. I investigate how people make sense of foreign language messages and identify their challenges and needs in their sensemaking process. Based on my findings, I design and develop sensemaking support tools and evaluate them in the context of social media sites and email communication. Specifically, I use natural language processing (NLP) techniques to generate useful cues for users’ sensemaking of foreign language messages. First, I design and develop SenseTrans –a browser extension that provides NLP-generated information about cultural referents, sentiments, and emotions using emotion/sentiment detection algorithms and entity extraction techniques. Second, I design the Politeness estimator, an email extension that provides politeness assessments of foreign language messages using language-specific classification algorithms in addition to MT outputs. The results from experimental evaluations of these tools provide initial evidence for the value of NLP techniques to improve cross-lingual sensemaking by increasing users’ confidence and accuracy in interpreting foreign language messages. Future, the deployment study of the tools in a real-world setting points to the need for further investigation of how users understand and utilize the NLP-generated information from the tools in their sensemaking process. The dissertation contributes to our understanding of current challenges in making sense of foreign language messages and the design of future tools for cross-lingual CMC and sensemaking.
|
|
Keyword:
Computer-Mediated Communication; Cross-lingual Communication; Human-Computer Interaction; Machine Translation; Natural Language Processing; Sensemaking
|
|
URL: https://doi.org/10.7298/gs0z-7064 http://dissertations.umi.com/cornellgrad:12417 https://hdl.handle.net/1813/109766
|
|
BASE
|
|
Hide details
|
|
20 |
The Mapping of Deep Language Models on Brain Responses Primarily Depends on their Performance
|
|
|
|
In: https://hal.archives-ouvertes.fr/hal-03361439 ; 2021 (2021)
|
|
BASE
|
|
Show details
|
|
|
|