Gestural Cues for Sentence Segmentation
In human-human dialogues, face-to-face meetings are often preferred over phone conversations.One explanation is that non-verbal modalities such as gesture provide additionalinformation, making communication more efficient and accurate. If so, computerprocessing of natural language could improve by a...
| Main Authors: | , |
|---|---|
| Language: | en_US |
| Published: |
2005
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/30540 |
| _version_ | 1811088043600248832 |
|---|---|
| author | Eisenstein, Jacob Davis, Randall |
| author_facet | Eisenstein, Jacob Davis, Randall |
| author_sort | Eisenstein, Jacob |
| collection | MIT |
| description | In human-human dialogues, face-to-face meetings are often preferred over phone conversations.One explanation is that non-verbal modalities such as gesture provide additionalinformation, making communication more efficient and accurate. If so, computerprocessing of natural language could improve by attending to non-verbal modalitiesas well. We consider the problem of sentence segmentation, using hand-annotatedgesture features to improve recognition. We find that gesture features correlate wellwith sentence boundaries, but that these features improve the overall performance of alanguage-only system only marginally. This finding is in line with previous research onthis topic. We provide a regression analysis, revealing that for sentence boundarydetection, the gestural features are largely redundant with the language model andpause features. This suggests that gestural features can still be useful when speech recognition is inaccurate. |
| first_indexed | 2024-09-23T13:55:21Z |
| id | mit-1721.1/30540 |
| institution | Massachusetts Institute of Technology |
| language | en_US |
| last_indexed | 2024-09-23T13:55:21Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | mit-1721.1/305402019-04-11T06:23:27Z Gestural Cues for Sentence Segmentation Eisenstein, Jacob Davis, Randall AI gesture natural language processing multimodal In human-human dialogues, face-to-face meetings are often preferred over phone conversations.One explanation is that non-verbal modalities such as gesture provide additionalinformation, making communication more efficient and accurate. If so, computerprocessing of natural language could improve by attending to non-verbal modalitiesas well. We consider the problem of sentence segmentation, using hand-annotatedgesture features to improve recognition. We find that gesture features correlate wellwith sentence boundaries, but that these features improve the overall performance of alanguage-only system only marginally. This finding is in line with previous research onthis topic. We provide a regression analysis, revealing that for sentence boundarydetection, the gestural features are largely redundant with the language model andpause features. This suggests that gestural features can still be useful when speech recognition is inaccurate. 2005-12-22T02:28:32Z 2005-12-22T02:28:32Z 2005-04-19 MIT-CSAIL-TR-2005-028 AIM-2005-014 http://hdl.handle.net/1721.1/30540 en_US Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory 13 p. 13772256 bytes 521371 bytes application/postscript application/pdf application/postscript application/pdf |
| spellingShingle | AI gesture natural language processing multimodal Eisenstein, Jacob Davis, Randall Gestural Cues for Sentence Segmentation |
| title | Gestural Cues for Sentence Segmentation |
| title_full | Gestural Cues for Sentence Segmentation |
| title_fullStr | Gestural Cues for Sentence Segmentation |
| title_full_unstemmed | Gestural Cues for Sentence Segmentation |
| title_short | Gestural Cues for Sentence Segmentation |
| title_sort | gestural cues for sentence segmentation |
| topic | AI gesture natural language processing multimodal |
| url | http://hdl.handle.net/1721.1/30540 |
| work_keys_str_mv | AT eisensteinjacob gesturalcuesforsentencesegmentation AT davisrandall gesturalcuesforsentencesegmentation |