FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2967994095> ?p ?o ?g. }

• W2967994095 abstract "Natural language understanding (NLU) of text is a fundamental challenge in AI, and it has received significant attention throughout the history of NLP research. This primary goal has been studied under different tasks, such as Question Answering (QA) and Textual Entailment (TE). In this thesis, we investigate the NLU problem through the QA task and focus on the aspects that make it a challenge for the current state-of-the-art technology. This thesis is organized into three main parts: In the first part, we explore multiple formalisms to improve existing machine comprehension systems. We propose a formulation for abductive reasoning in natural language and show its effectiveness, especially in domains with limited training data. Additionally, to help reasoning systems cope with irrelevant or redundant information, we create a supervised approach to learn and detect the essential terms in questions. In the second part, we propose two new challenge datasets. In particular, we create two datasets of natural language questions where (i) the first one requires reasoning over multiple sentences; (ii) the second one requires temporal common sense reasoning. We hope that the two proposed datasets will motivate the field to address more complex problems. In the final part, we present the first formal framework for multi-step reasoning algorithms, in the presence of a few important properties of language use, such as incompleteness, ambiguity, etc. We apply this framework to prove fundamental limitations for reasoning algorithms. These theoretical results provide extra intuition into the existing empirical evidence in the field." @default.
• W2967994095 created "2019-08-22" @default.
• W2967994095 creator A5043628255 @default.
• W2967994095 date "2019-08-14" @default.
• W2967994095 modified "2023-09-27" @default.
• W2967994095 title "Reasoning-Driven Question-Answering for Natural Language Understanding" @default.
• W2967994095 cites W11155487 @default.
• W2967994095 cites W12836875 @default.
• W2967994095 cites W131863957 @default.
• W2967994095 cites W1488025282 @default.
• W2967994095 cites W1493490255 @default.
• W2967994095 cites W1495683013 @default.
• W2967994095 cites W1496189301 @default.
• W2967994095 cites W1498436455 @default.
• W2967994095 cites W1505640990 @default.
• W2967994095 cites W1512387364 @default.
• W2967994095 cites W1528445643 @default.
• W2967994095 cites W1539746312 @default.
• W2967994095 cites W1544827683 @default.
• W2967994095 cites W1549997466 @default.
• W2967994095 cites W1559723967 @default.
• W2967994095 cites W1562811233 @default.
• W2967994095 cites W1563567452 @default.
• W2967994095 cites W1566346388 @default.
• W2967994095 cites W1601555688 @default.
• W2967994095 cites W1619326861 @default.
• W2967994095 cites W1640443237 @default.
• W2967994095 cites W1662133657 @default.
• W2967994095 cites W1664028424 @default.
• W2967994095 cites W1811279891 @default.
• W2967994095 cites W1814992895 @default.
• W2967994095 cites W1816599501 @default.
• W2967994095 cites W1825507529 @default.
• W2967994095 cites W191693080 @default.
• W2967994095 cites W1923459080 @default.
• W2967994095 cites W1957744914 @default.
• W2967994095 cites W1963496740 @default.
• W2967994095 cites W1971735090 @default.
• W2967994095 cites W1975879668 @default.
• W2967994095 cites W1977220278 @default.
• W2967994095 cites W1977970897 @default.
• W2967994095 cites W1978308858 @default.
• W2967994095 cites W1990989925 @default.
• W2967994095 cites W1997833443 @default.
• W2967994095 cites W2000985912 @default.
• W2967994095 cites W2002418751 @default.
• W2967994095 cites W2004763266 @default.
• W2967994095 cites W2005814556 @default.
• W2967994095 cites W2011992920 @default.
• W2967994095 cites W2014328192 @default.
• W2967994095 cites W2016089260 @default.
• W2967994095 cites W2018165967 @default.
• W2967994095 cites W2018285346 @default.
• W2967994095 cites W2021364241 @default.
• W2967994095 cites W2023286866 @default.
• W2967994095 cites W2027377866 @default.
• W2967994095 cites W2028781966 @default.
• W2967994095 cites W2029118765 @default.
• W2967994095 cites W2032135330 @default.
• W2967994095 cites W2038324640 @default.
• W2967994095 cites W2039234396 @default.
• W2967994095 cites W2039371384 @default.
• W2967994095 cites W2040870580 @default.
• W2967994095 cites W2055354597 @default.
• W2967994095 cites W2056891043 @default.
• W2967994095 cites W2070246124 @default.
• W2967994095 cites W2075745145 @default.
• W2967994095 cites W2080430334 @default.
• W2967994095 cites W2081580037 @default.
• W2967994095 cites W2086789740 @default.
• W2967994095 cites W2090243146 @default.
• W2967994095 cites W2094728533 @default.
• W2967994095 cites W2098844768 @default.
• W2967994095 cites W2105717194 @default.
• W2967994095 cites W2107658650 @default.
• W2967994095 cites W2112085250 @default.
• W2967994095 cites W2114485587 @default.
• W2967994095 cites W2114952278 @default.
• W2967994095 cites W2115164315 @default.
• W2967994095 cites W2115322217 @default.
• W2967994095 cites W2115758952 @default.
• W2967994095 cites W2115792525 @default.
• W2967994095 cites W2118656391 @default.
• W2967994095 cites W2119295783 @default.
• W2967994095 cites W2119409989 @default.
• W2967994095 cites W2120779048 @default.
• W2967994095 cites W2121227244 @default.
• W2967994095 cites W2121300346 @default.
• W2967994095 cites W2121773050 @default.
• W2967994095 cites W2122483056 @default.
• W2967994095 cites W2124301168 @default.
• W2967994095 cites W2125436846 @default.
• W2967994095 cites W2125444198 @default.
• W2967994095 cites W2127426251 @default.
• W2967994095 cites W2127978399 @default.
• W2967994095 cites W2129657639 @default.
• W2967994095 cites W2131357087 @default.
• W2967994095 cites W2133182690 @default.
• W2967994095 cites W2134755874 @default.
• W2967994095 cites W2142565826 @default.

• next