| 1. |
|
|
| 2. |
|
|
| 3. |
- Hong, Xudong, et al.
(författare)
-
Visual Coherence Loss for Coherent and Visually Grounded Story Generation
- 2023
-
Ingår i: Proceedings of the Annual Meeting of the Association for Computational Linguistics. - 0736-587X. - 9781959429777
-
Konferensbidrag (refereegranskat)abstract
- Local coherence is essential for text generation models. We identify two important aspects of local coherence within the visual storytelling task: (1) the model needs to represent re-occurrences of characters within the image sequence in order to mention them correctly in the story; (2) character representations should enable us to find instances of the same characters and distinguish different characters. In this paper, we propose a loss function inspired by a linguistic theory of coherence for learning image sequence representations. We further propose combining features from an object detector and a face detector to construct stronger character features. To evaluate visual grounding that current reference-based metrics do not measure, we propose a character matching metric to check whether the models generate referring expressions correctly for characters in input image sequences. Experiments on a visual story generation dataset show that our proposed features and loss function are effective for generating more coherent and visually grounded stories. Our code is available at https://github.com/vwprompt/vcl.
|
|
| 4. |
-
Proceedings of the 13th International Conference on Computational Semantics - Long Papers
- 2019
-
Proceedings (redaktörskap) (övrigt vetenskapligt/konstnärligt)abstract
- The 13th International Conference on Computational Semantics (IWCS 2019) was held at the University of Gothenburg, Sweden on the 23-27th May 2019. IWCS is the bi-yearly meeting of SIGSEM, the ACL special interest group on semantics; this year's edition was hosted by the Centre of Linguistic Theory and Studies in Probability (CLASP) at the Department of Philosophy, Linguistics and Theory of Science (FLoV). The aim of the IWCS conference is to bring together researchers interested in any aspects of the computation, annotation, extraction, and representation of meaning in natural language, whether this is from a lexical or structural semantic perspective. IWCS embraces both symbolic and machine learning approaches to computational semantics, and everything in between.
|
|
| 5. |
-
Proceedings of the 13th International Conference on Computational Semantics - Short Papers, 23-27 May 2019, Gothenburg, Sweden
- 2019
-
Proceedings (redaktörskap) (övrigt vetenskapligt/konstnärligt)abstract
- The 13th International Conference on Computational Semantics (IWCS 2019) was held at the University of Gothenburg, Sweden on the 23-27th May 2019. IWCS is the bi-yearly meeting of SIGSEM, the ACL special interest group on semantics; this year's edition was hosted by the Centre of Linguistic Theory and Studies in Probability (CLASP) at the Department of Philosophy, Linguistics and Theory of Science (FLoV). The aim of the IWCS conference is to bring together researchers interested in any aspects of the computation, annotation, extraction, and representation of meaning in natural language, whether this is from a lexical or structural semantic perspective. IWCS embraces both symbolic and machine learning approaches to computational semantics, and everything in between.
|
|
| 6. |
-
Proceedings of the 13th International Conference on Computational Semantics - Student Papers, 23–27 May 2019, Gothenburg, Sweden
- 2019
-
Proceedings (redaktörskap) (övrigt vetenskapligt/konstnärligt)abstract
- The 13th International Conference on Computational Semantics (IWCS 2019) was held at the University of Gothenburg, Sweden on the 23-27th May 2019. IWCS is the bi-yearly meeting of SIGSEM, the ACL special interest group on semantics; this year's edition was hosted by the Centre of Linguistic Theory and Studies in Probability (CLASP) at the Department of Philosophy, Linguistics and Theory of Science (FLoV). The aim of the IWCS conference is to bring together researchers interested in any aspects of the computation, annotation, extraction, and representation of meaning in natural language, whether this is from a lexical or structural semantic perspective. IWCS embraces both symbolic and machine learning approaches to computational semantics, and everything in between.
|
|
| 7. |
- Sayeed, Asad, 1980, et al.
(författare)
-
Verb-Second Effect on Quantifier Scope Interpretation
- 2019
-
Ingår i: Proceedings of the workshop on cognitive modeling and computational linguistics, 2019 conference of the North American chapter of the Association for Computational Linguistics. - 9781948087964
-
Konferensbidrag (refereegranskat)abstract
- Sentences like “Every child climbed a tree” have at least two interpretations depending on the precedence order of the universal quantifier and the indefinite. Previous experimental work explores the role that different mechanisms such as semantic reanalysis and world knowledge may have in enabling each interpretation. This paper discusses a web-based task that uses the verb-second characteristic of German main clauses to estimate the influence of word order variation over world knowledge.
|
|
| 8. |
- Zhai, F, et al.
(författare)
-
A Hybrid Model for Globally Coherent Story Generation
- 2019
-
Ingår i: Proceedings of the second workshop on storytelling, 57th annual meeting of the Association for Computational Linguistics. - 9781950737444
-
Konferensbidrag (refereegranskat)abstract
- Automatically generating globally coherent stories is a challenging problem. Neural text generation models have been shown to perform well at generating fluent sentences from data, but they usually fail to keep track of the overall coherence of the story after a couple of sentences. Existing work that incorporates a text planning module succeeded in generating recipes and dialogues, but appears quite data-demanding. We propose a novel story generation approach that generates globally coherent stories from a fairly small corpus. The model exploits a symbolic text planning module to produce text plans, thus reducing the demand of data; a neural surface realization module then generates fluent text conditioned on the text plan. Human evaluation showed that our model outperforms various baselines by a wide margin and generates stories which are fluent as well as globally coherent.
|
|
