| 1 |
Implication textuelle : problèmes et méthodes pour le TAL
|
|
|
|
In: Langages, N 212, 4, 2018-12-18, pp.105-122 (2018)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Apprentissage d'inférences par édition d'arbres pour répondre à des questions
|
|
|
|
In: CORIA 2016 - Conférence en Recherche d'Informations et Applications ; Conférence en Recherche d'Information et Applications ; https://hal.archives-ouvertes.fr/hal-02282822 ; Conférence en Recherche d'Information et Applications, Mar 2016, Toulouse, France. pp.685-700 (2016)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
A Unified Kernel Approach For Learning Typed Sentence Rewritings
|
|
|
|
In: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, ; Annual Meeting of the Association for Computational Linguistics ; https://hal.archives-ouvertes.fr/hal-02281919 ; Annual Meeting of the Association for Computational Linguistics, The Association for Computer Linguistics, Jan 2015, Beijing, China. pp.939 - 949, ⟨10.3115/v1/P15-1091⟩ ; https://www.aclweb.org/anthology/P15-1091 (2015)
|
|
BASE
|
|
Show details
|
|
|
| 4 |
LIMSI-CNRS@ CLEF 2015: Tree Edit Beam Search for Multiple Choice Question Answering.
|
|
|
|
In: Working Notes of CLEF 2015 - Conference and Labs of the Evaluation forum ; CLEF 2015 ; https://hal.archives-ouvertes.fr/hal-02289246 ; CLEF 2015, Sep 2015, Toulouse, France ; http://ceur-ws.org/Vol-1391/ (2015)
|
|
BASE
|
|
Show details
|
|
|
| 5 |
LIMSI-CNRS@ CLEF 2014: Invalidating Answers for Multiple Choice Question Answering.
|
|
|
|
In: Working Notes for CLEF 2014 Conference, Sheffield, UK, September 15-18, 2014 ; CLEF 2014 ; https://hal.archives-ouvertes.fr/hal-02290008 ; CLEF 2014, Sep 2014, Sheffield, United Kingdom. pp.1386--1394 (2014)
|
|
Abstract:
International audience ; This paper describes our participation to the Entrance Exams Task of CLEF 2014’s Question Answering Track. The goal is to answer multiple-choice questions on short texts. Our system first retrieves passages relevant to the question, through lexical expansion involving a structured use of the Simple English Wiktionary and WordNet. Then it extracts predicate-argument structures (PAS) from each answer choice and aligns them to PAS found in the passages retrieved in the first step. Finally, manually crafted rules are applied to those alignments to try to invalidate answer choices. If enough answer choices are thus invalidated, we make a decision on the remaining answer choices based on their alignment scores with the passages. We submitted several runs in the task, only one of which reached the random baseline (c@1 of 0.25). In the last section, we provide an analysis of the differences between our relatively good results obtained on trial data and the poor performance of our test run.
|
|
Keyword:
[INFO.INFO-CL]Computer Science [cs]/Computation and Language [cs.CL]; [INFO]Computer Science [cs]; Passage Retrieval; Question Answering; Textual Entailment
|
|
URL: https://hal.archives-ouvertes.fr/hal-02290008/document
https://hal.archives-ouvertes.fr/hal-02290008
https://hal.archives-ouvertes.fr/hal-02290008/file/CLEF2014wn-QA-GleizeEt2014.pdf
|
|
BASE
|
|
Hide details
|
|
|
|
|
