Abstrakti
Accurate prediction of suitable discourse connectives (however, furthermore, etc.) is a key component of any system aimed at building coherent and fluent discourses from shorter sentences and passages. As an example, a dialog system might assemble a long and informative answer by sampling passages extracted from different documents retrieved from the Web. We formulate the task of discourse connective prediction and release a dataset of 2.9M sentence pairs separated by discourse connectives for this task. Then, we evaluate the hardness of the task for human raters, apply a recently proposed decomposable attention (DA) model to this task and observe that the automatic predictor has a higher F1 than human raters (32 vs. 30). Nevertheless, under specific conditions the raters still outperform the DA model, suggesting that there is headroom for future improvements.
Alkuperäiskieli | Englanti |
---|---|
Otsikko | LREC 2018 - 11th International Conference on Language Resources and Evaluation |
Toimittajat | Hitoshi Isahara, Bente Maegaard, Stelios Piperidis, Christopher Cieri, Thierry Declerck, Koiti Hasida, Helene Mazo, Khalid Choukri, Sara Goggi, Joseph Mariani, Asuncion Moreno, Nicoletta Calzolari, Jan Odijk, Takenobu Tokunaga |
Kustantaja | European Language Resources Association (ELRA) |
Sivut | 1643-1648 |
Sivumäärä | 6 |
ISBN (elektroninen) | 9791095546009 |
Tila | Julkaistu - 1 tammik. 2019 |
OKM-julkaisutyyppi | A4 Artikkeli konferenssijulkaisuussa |
Tapahtuma | International Conference on Language Resources and Evaluation - Miyazaki, Japani Kesto: 7 toukok. 2018 → 12 toukok. 2018 Konferenssinumero: 11 |
Conference
Conference | International Conference on Language Resources and Evaluation |
---|---|
Lyhennettä | LREC |
Maa/Alue | Japani |
Kaupunki | Miyazaki |
Ajanjakso | 07/05/2018 → 12/05/2018 |