Zobrazeno 1 - 10
of 1 192
pro vyhledávání: '"A. Rambow"'
Publikováno v:
SIGDIAL 2024
Hedges allow speakers to mark utterances as provisional, whether to signal non-prototypicality or "fuzziness", to indicate a lack of commitment to an utterance, to attribute responsibility for a statement to someone else, to invite input from a partn
Externí odkaz:
http://arxiv.org/abs/2408.03319
Publikováno v:
SIGDIAL 2024
We propose a framework for analyzing discourse by combining two interdependent concepts from sociolinguistic theory: face acts and politeness. While politeness has robust existing tools and data, face acts are less resourced. We introduce a new corpu
Externí odkaz:
http://arxiv.org/abs/2408.02798
We present Gram2Vec, a grammatical style embedding algorithm that embeds documents into a higher dimensional space by extracting the normalized relative frequencies of grammatical features present in the text. Compared to neural approaches, Gram2Vec
Externí odkaz:
http://arxiv.org/abs/2406.12131
Recent studies have proposed placing multiple problems in a single prompt to improve input token utilization for a more efficient LLM inference. We call this MPP, in contrast to conventional SPP that prompts an LLM with a single problem at a time. Wh
Externí odkaz:
http://arxiv.org/abs/2406.10786
Publikováno v:
Interspeech 2024
Recognizing a speaker's level of commitment to a belief is a difficult task; humans do not only interpret the meaning of the words in context, but also understand cues from intonation and other aspects of the audio signal. Many papers and corpora in
Externí odkaz:
http://arxiv.org/abs/2406.07466
Autor:
Soubki, Adil, Rambow, Owen
Publikováno v:
May 2024. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9143-9153, Torino, Italia. ELRA and ICCL
The notion of face described by Brown and Levinson (1987) has been studied in great detail, but a critical aspect of the framework, that which focuses on how intentions mediate the planning of turns which impose upon face, has received far less atten
Externí odkaz:
http://arxiv.org/abs/2406.04109
Autor:
Soubki, Adil, Murzaku, John, Jordehi, Arash Yousefi, Zeng, Peter, Markowska, Magdalena, Mirroshandel, Seyed Abolghasem, Rambow, Owen
Publikováno v:
ACL 2024 Findings
Evaluating the theory of mind (ToM) capabilities of language models (LMs) has recently received a great deal of attention. However, many existing benchmarks rely on synthetic data, which risks misaligning the resulting experiments with human behavior
Externí odkaz:
http://arxiv.org/abs/2403.02451
Autor:
Wang, Zhengxiang, Rambow, Owen
We propose a novel clustering pipeline to detect and characterize influence campaigns from documents. This approach clusters parts of document, detects clusters that likely reflect an influence campaign, and then identifies documents linked to an inf
Externí odkaz:
http://arxiv.org/abs/2402.17151
Autor:
Markowska, Magdalena, Taghizadeh, Mohammad, Soubki, Adil, Mirroshandel, Seyed Abolghasem, Rambow, Owen
Publikováno v:
Findings of EMNLP 2023
When we communicate with other humans, we do not simply generate a sequence of words. Rather, we use our cognitive state (beliefs, desires, intentions) and our model of the audience's cognitive state to create utterances that affect the audience's co
Externí odkaz:
http://arxiv.org/abs/2311.01273
Norm discovery is important for understanding and reasoning about the acceptable behaviors and potential violations in human communication and interactions. We introduce NormSage, a framework for addressing the novel task of conversation-grounded mul
Externí odkaz:
http://arxiv.org/abs/2210.08604