Zobrazeno 1 - 10
of 146
pro vyhledávání: '"Keh-Yih SU"'
Publikováno v:
智能科学与技术学报, Vol 2, Pp 26-35 (2020)
Previous approaches generally use context information to improve the word representation but ignore the importance of context similarity in aligning tokens.Furthermore,most of them uniformly weight various local decisions during aggregation for the g
Externí odkaz:
https://doaj.org/article/239557aab29a405499c92b41cb51bdd2
Publikováno v:
ACM Transactions on Asian and Low-Resource Language Information Processing. 19:1-23
This article proposes to conduct natural language inference with novel Enhanced-Relation-Head-Dependent triplets (RHD triplets) , which are constructed via enhancing each word in the RHD triplet with its associated local context. Most previous approa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::71c8b8f01eaf28ee2aab24e83e0bd4fe
https://doi.org/10.1145/3377704
https://doi.org/10.1145/3377704
Publikováno v:
ACL/IJCNLP (2)
With the recent advancements in deep learning, neural solvers have gained promising results in solving math word problems. However, these SOTA solvers only generate binary expression trees that contain basic arithmetic operators and do not explicitly
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::df8cd5e59565eba6fbc5f220093d8988
http://arxiv.org/abs/2106.00990
http://arxiv.org/abs/2106.00990
Publikováno v:
Computer Speech & Language. 54:176-206
Since statistical machine translation (SMT) and translation memory (TM) complement each other in TM matched and unmatched regions, a unified framework for integrating TM into phrase-based SMT is proposed in this paper. Unlike previous two-stage pipel
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::c1dd3ed9cfe0083bb9a52eecfe0a0f20
https://doi.org/10.1016/j.csl.2018.09.006
https://doi.org/10.1016/j.csl.2018.09.006
Autor:
Yi-Chung Lin, Keh-Yih Su
Publikováno v:
EACL
This paper empirically studies whether BERT can really learn to conduct natural language inference (NLI) without utilizing hidden dataset bias; and how efficiently it can learn if it could. This is done via creating a simple entailment judgment case
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::835e1b124cafed29be12ec46d0b0ef99
https://doi.org/10.18653/v1/2021.eacl-main.51
https://doi.org/10.18653/v1/2021.eacl-main.51
Publikováno v:
TAAI
The task of entailment judgment aims to determine whether a hypothesis is true (entailment), false (contradiction), or undetermined (neutral) given a premise. While previous methods strike successful in several benchmarks and even exceed the human ba
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::149aa6b1c4d9ff36dfe33fc81dea3f65
https://doi.org/10.1109/taai51410.2020.00024
https://doi.org/10.1109/taai51410.2020.00024
Publikováno v:
ACL
We present ASDiv (Academia Sinica Diverse MWP Dataset), a diverse (in terms of both language patterns and problem types) English math word problem (MWP) corpus for evaluating the capability of various MWP solvers. Existing MWP corpora for studying AI
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::059d660423d0675d83fd85cffe6c3e1c
https://doi.org/10.18653/v1/2020.acl-main.92
https://doi.org/10.18653/v1/2020.acl-main.92
Publikováno v:
NAACL-HLT
We introduce MeSys, a meaning-based approach, for solving English math word problems (MWPs) via understanding and reasoning in this paper. It first analyzes the text, transforms both body and question parts into their corresponding logic forms, and t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c5986eedd08a4a748f90e717c858911
Publikováno v:
ACM Transactions on Asian and Low-Resource Language Information Processing. 14:1-29
This article proposes a unified, character-based, generative model to incorporate additional resources for solving the out-of-vocabulary (OOV) problem of Chinese word segmentation, within which different types of additional information can be utilize
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::6b13e50f4f018f8b7a140512fed37cd2
https://doi.org/10.1145/2699940
https://doi.org/10.1145/2699940
Publikováno v:
IJCAI
A goal-oriented meaning-based statistical framework is presented in this paper to solve the math word problem that requires multiple arithmetic operations with understanding, reasoning and explanation. It first analyzes and transforms sentences into
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::f681aa976434ac2e2064633d3b09eb93
https://doi.org/10.24963/ijcai.2017/775
https://doi.org/10.24963/ijcai.2017/775